# IvLabs


## Posts

- [NIDAR Competition, 2026](https://ivlabs.in/nidar-competition-2026/): We are proud to share that our team representing Visvesvaraya National Institute of Technology (VNIT), Nagpur participated in the 𝐍𝐈𝐃𝐀𝐑 Competition organized by the 𝐃𝐫𝐨𝐧𝐞 𝐅𝐞𝐝𝐞𝐫𝐚𝐭𝐢𝐨𝐧 𝐨𝐟 𝐈𝐧𝐝𝐢𝐚 (𝐃𝐅𝐈) in collaboration with the 𝐌𝐢𝐧𝐢𝐬𝐭𝐫𝐲 𝐨𝐟 𝐄𝐥𝐞𝐜𝐭𝐫𝐨𝐧𝐢𝐜𝐬 𝐚𝐧𝐝 𝐈𝐧𝐟𝐨𝐫𝐦𝐚𝐭𝐢𝐨𝐧 𝐓𝐞𝐜𝐡𝐧𝐨𝐥𝐨𝐠𝐲 (𝐌𝐞𝐢𝐭𝐘), 𝐆𝐨𝐯𝐞𝐫𝐧𝐦𝐞𝐧𝐭 𝐨𝐟 𝐈𝐧𝐝𝐢𝐚. Achievements: 𝐈𝐠𝐧𝐢𝐭𝐞 𝐏𝐫𝐢𝐳𝐞 𝐖𝐢𝐧𝐧𝐞𝐫 – Precision Agriculture Problem StatementCash Prize: ₹𝟏,𝟎𝟎,𝟎𝟎𝟎National Standing: Among the 𝐓𝐨𝐩 𝟓 teams in India, with participation of more than 100 teams 𝐀𝐛𝐨𝐮𝐭 𝐭𝐡𝐞 𝐜𝐡𝐚𝐥𝐥𝐞𝐧𝐠𝐞The Precision Agriculture task required designing and fabricating the entire drone structure from scratch & demonstrating a complete autonomous drone ecosystem capable of :• Autonomously scanning a 2-acre field• […]
- [Drone Helix competition, SVNIT Surat](https://ivlabs.in/drone-helix-competition-svnit-surat/): We achieved 2nd place at the Drone Helix Competition held at SVNIT, Surat. We built a drone that autonomously takes off, navigates to a GPS-marked location, drops a payload within 0.75 meters of accuracy, and returns to base — all without manual control. Out of 38 participants, 11 teams made it to the final test flight round. Our team designed custom scripts on Raspberry Pi and used Mission Planner software for autonomous waypoint navigation during the live challenge. Here is our system architecture –
- [Gujurat Robofest 4.0](https://ivlabs.in/gujurat-robofest-4-0/): 𝗦𝘂𝗰𝗰𝗲𝘀𝘀𝗳𝘂𝗹𝗹𝘆 𝗪𝗿𝗮𝗽𝗽𝗲𝗱 𝗨𝗽 𝗚𝘂𝗷𝗮𝗿𝗮𝘁 𝗥𝗼𝗯𝗼𝗳𝗲𝘀𝘁 𝟰.𝟬 –We’re excited to share that our team, 𝗣𝗿𝗮𝘃𝗮𝗿𝘁𝗮𝗸, reached the finals of Robofest 4.0 in the Rover Category, competing alongside 27+ talented teams. Advancing to this stage was a rewarding experience that reflects our dedication, innovation, and teamwork. With the invaluable guidance of Prof. Shital Chiddarwar, Ph.D. and the relentless efforts of our core team—Aiden D’souza, Phani Raj Telukunta, Koyaneni Yaswanth, Yuvraj Gupta, Shubham Pandere-we built an autonomous rover.We would also like to express our gratitude to Manish Maurya Sir and Mayank Lonkar for their invaluable technical insights and constant encouragement throughout the competition. […]
- [Open Day 2025](https://ivlabs.in/open-day-2025/): OpenDay 2025, held on April 4th and 5th, was a vibrant display of the incredible work happening in our lab. The event brought together faculty, researchers, and students in an inspiring two-day celebration of technology and innovation. We were honoured to have our institute’s Director, Dr. Prem Lal Patel, inaugurate the event, along with professors and Ph.D. scholars from various departments. On Day 2, we welcomed students of VNIT, who enthusiastically engaged with the wide range of projects on display. From cutting-edge robotics to impactful AI/ML applications, here’s what we showcased:𝗥𝗼𝗯𝗼𝘁𝗶𝗰𝘀: Gesture Control Robot, Bipedal Robot, Voice Navigation Robot, Hexapod, […]
- [DRDO Scientist Prahlada Ramarao Visits IvLabs: Insights & Inspiration](https://ivlabs.in/drdo-scientist-prahlada-ramarao-visits-ivlabs-insights-inspiration/): We had the incredible opportunity to host Dr. Prahlada Ramarao, the distinguished Indian missile scientist and former Director of the Defence Research and Development Laboratory (DRDL), at IvLabs, VNIT Nagpur. His visit was a moment of great honor and inspiration, as he shared his wisdom and insights with our team. Dr. Ramarao took a keen interest in our VTOL (Vertical Take-Off and Landing) project, engaging in an in-depth discussion with team members Mayank Lonkar, Aiden D’souza, and Sanchet Dhalwar. As we showcased the project’s design, capabilities, and innovations, he was quick to grasp the underlying concepts and provided invaluable feedback. […]
- [Paper Accepted at NeurlPS'21 Workshop](https://ivlabs.in/paper-accepted-at-neurlps21-workshop/): 𝗧𝗵𝗲 𝗽𝗮𝗽𝗲𝗿 𝗼𝗻 “𝗘𝗻𝗵𝗮𝗻𝗰𝗶𝗻𝗴 𝗖𝗼𝗻𝘁𝗲𝘅𝘁 𝗧𝗵𝗿𝗼𝘂𝗴𝗵 𝗖𝗼𝗻𝘁𝗿𝗮𝘀𝘁” 𝗵𝗮𝘀 𝗯𝗲𝗲𝗻 𝗮𝗰𝗰𝗲𝗽𝘁𝗲𝗱 𝗮𝘁 𝘁𝗵𝗲 𝗡𝗲𝘂𝗿𝗜𝗣𝗦’𝟮𝟭 𝗣𝗿𝗲-𝗿𝗲𝗴𝗶𝘀𝘁𝗿𝗮𝘁𝗶𝗼𝗻 𝘄𝗼𝗿𝗸𝘀𝗵𝗼𝗽. Founded in 1987, NeurIPS is one of the most renowned conferences in machine learning and computational neuroscience, with an h-index of 192. The paper proposes a novel pipeline that focuses on maximizing Mutual Information between representations of sentences that share similar semantics. This additional step would improve multilingual embeddings for the downstream task of Neural Machine Translation. Further details would be released post-publication. The IvLabs team congratulates all authors Prasad Vagdargi, Rishika Bhagwatkar, Khurshed Fitter, Kshitij Ambilduke, Aneesh Shetye, Diksha Bagade, Dr. Shital Chiddarwar for their accomplishment. […]

## Pages

- [Quadruped](https://ivlabs.in/quadruped/): Overview The objective of this project is to design and develop a quadruped robot from scratch, focusing on building a deep understanding of fundamental robotics principles rather than relying on pre-built platforms. The system aims to achieve stable locomotion using a crawl gait by integrating concepts from kinematics, control theory, mechanical design, and embedded systems. The robot is capable of standing stably and executing controlled walking in a straight line, serving as a foundational platform for advanced legged robotics research. Approach The development followed a structured, end-to-end pipeline covering theory, simulation, design, and hardware implementation: Mathematical Foundation We began by […]
- [Rocket Lander using DRL](https://ivlabs.in/rocket-lander-using-drl/): Objective This project focuses on training an AI agent to land a rocket safely in the ROCKET LANDER environment, similar to how SpaceX lands their reusable rockets. We’ll use Deep Reinforcement Learning (DRL) techniques to teach our rocket to make landing decisions on its own. Our goal is to create an AI that can control a simulated rocket and guide it to a successful landing. The AI will: Overview What is reinforcement learning? Approach 🌌 Environment Description The custom environment simulates a 2D rocket controlled via thrust and torque.It provides continuous feedback about position, velocity, and contact status. Termination Conditions: […]
- [Bipedal Robot](https://ivlabs.in/bipedal-robot/): Overview The objective of this project is to develop a bipedal robot—a two-legged robotic system designed to replicate human gait dynamics. The system focuses on achieving stable locomotion by combining precise limb positioning through Inverse Kinematics (IK) with real-time stability management of the Center of Mass. By integrating control theory with robotic vision and hardware, the robot can simulate and execute balanced walking motions. Approach The development followed a modular path, starting from basic control theory and progressing to complex 3D robotic simulation and hardware integration: Key Modules Summary The system operates by calculating a rhythmic trajectory for each leg. […]
- [Gesture Controlled Quadcopter](https://ivlabs.in/gesture-controlled-quadcopter/): Overview Our goal is to develop an advanced drone capable of autonomous flight, seamlessly responding to gesture-based commands from a ground-based pilot. The drone will interpret and execute these commands with precision, enabling dynamic and user-friendly control for a range of applications. Implement wireless communication protocols to transmit precise gesture-based commands from a Ground Control Station (GCS) to the drone. Approach Key Modules Summary Team Members Mentors
- [Frontier Exploration Robot](https://ivlabs.in/frontier-exploration-robot/): Overview This project aims to develop an autonomous frontier exploring robot capable of navigating through obstacles and creating an accurate 2D map of unexplored environments. The system utilizes BFS-based frontier cell clustering and centroid selection to determine goals, which are then processed by the Nav2 stack for autonomous navigation. Real-time map visualization is handled via RViz2, allowing for a seamless transition from simulated environments to real-world hardware. Approach Key Modules Summary Team Members Mentors
- [Region Captioning](https://ivlabs.in/region-captioning/): Overview This project implements a Region Captioning System that bridges the gap between Computer Vision and Natural Language Processing using Deep Learning. Unlike traditional image captioning models that describe an entire image with a single sentence, Region Captioning focuses on generating fine-grained, natural language descriptions for specific regions within an image, offering a more localized and contextual understanding. Approach The project follows a progressive learning and implementation pipeline: Dataset and Preprocessing Source: Flickr30k Entities (an extension of Flickr8k/30k) The Flickr30k dataset contains about 31,000 real-world images, each paired with 5 human-written English captions describing the scene. Preprocessing Pipeline 1. Parsing 2. Image Preprocessing 3. Caption […]
- [Batch 2026](https://ivlabs.in/batch-2026/)
- [NIDAR Competition 2026](https://ivlabs.in/nidar-competition-2026/): We are proud to share that our team representing Visvesvaraya National Institute of Technology (VNIT), Nagpur participated in the 𝐍𝐈𝐃𝐀𝐑 Competition organized by the 𝐃𝐫𝐨𝐧𝐞 𝐅𝐞𝐝𝐞𝐫𝐚𝐭𝐢𝐨𝐧 𝐨𝐟 𝐈𝐧𝐝𝐢𝐚 (𝐃𝐅𝐈) in collaboration with the 𝐌𝐢𝐧𝐢𝐬𝐭𝐫𝐲 𝐨𝐟 𝐄𝐥𝐞𝐜𝐭𝐫𝐨𝐧𝐢𝐜𝐬 𝐚𝐧𝐝 𝐈𝐧𝐟𝐨𝐫𝐦𝐚𝐭𝐢𝐨𝐧 𝐓𝐞𝐜𝐡𝐧𝐨𝐥𝐨𝐠𝐲 (𝐌𝐞𝐢𝐭𝐘), 𝐆𝐨𝐯𝐞𝐫𝐧𝐦𝐞𝐧𝐭 𝐨𝐟 𝐈𝐧𝐝𝐢𝐚. Achievements: 𝐈𝐠𝐧𝐢𝐭𝐞 𝐏𝐫𝐢𝐳𝐞 𝐖𝐢𝐧𝐧𝐞𝐫 – Precision Agriculture Problem StatementCash Prize: ₹𝟏,𝟎𝟎,𝟎𝟎𝟎National Standing: Among the 𝐓𝐨𝐩 𝟓 teams in India, with participation of more than 100 teams 𝐀𝐛𝐨𝐮𝐭 𝐭𝐡𝐞 𝐜𝐡𝐚𝐥𝐥𝐞𝐧𝐠𝐞The Precision Agriculture task required designing and fabricating the entire drone structure from scratch & demonstrating a complete autonomous drone ecosystem capable of :• Autonomously scanning a 2-acre field• […]
- [Autonomous Car driving using DRL](https://ivlabs.in/autonomous-car-driving-using-drl/): Overview Autonomous Driving Using Deep Reinforcement Learning implements an end-to-end PPO agent that learns to follow lanes and control speed in the gym-donkeycar simulator using only raw 120×160 RGB camera input. Through a progressive learning path—from classic RL algorithms to CNN vision processing and Actor-Critic methods—the agent masters continuous steering (-5 to +5) and throttle (0-1) control. A carefully designed reward function balances lane centering and forward velocity while penalizing collisions. PPO’s clipped objectives, GAE advantages, and sample efficiency enable stable training, achieving smooth lap completion and generalization to challenging mountain tracks purely from visual observations. Approach Environment: gym-donkeycar Action Space […]
- [Gesture Controlled Quadcopter](https://ivlabs.in/summer-projects/gesture-controlled-quadcopter/): Overview This project implements an advanced autonomous drone system that responds to gesture-based commands from a ground pilot. The drone interprets these gestures in real time and executes the corresponding actions with accurate control, enabling flexible and dynamic operation across various applications. Implemented wireless communication protocols to transmit precise gesture-based commands from a Ground Control Station (GCS) to the drone. Gesture Recognition Approach for Data Collection Model Training Command Mapping and Forwarding Setup and Running SITL Setup Installation Requirements- Gazebo Setup Simulation Run- Run all the applications in order all in new terminal. Implementation Team Members Mentors
- [Image Processing FPGA](https://ivlabs.in/image-processing-fpga/): This project aims to develop a custom hardware-accelerated photo viewer and image processor that runs on an FPGA development board. It receives a digital image from a computer, stores it in the FPGA’s internal memory, applies selected image filters using hardware-based processing, and outputs the final result to a VGA monitor. Project Overview The system takes a digital image from a computer, saves it in the FPGA’s internal memory, applies various filters, and sends the outcome to a VGA monitor. Key Functionality Image Input: A Python program on a PC transmits QVGA (320×240) image data (RGB444) through USB-to-UART (Universal Asynchronous Receiver-Transmitter). […]
- [Human Pose Generation using GANs](https://ivlabs.in/human-pose-generation-using-gans/): Overview PoseGAN is a GAN-based architecture for generating realistic images of people conditioned on new poses. It uses two separate encoders to extract appearance and pose features, deforms source features to align with the target pose, and employs a decoder to synthesize the output image. A discriminator network ensures the generated image is realistic and preserves the person’s identity. The approach combines perceptual, nearest neighbour, and smoothness losses to maintain fine details and spatial coherence, enabling high-quality pose-driven image synthesis Approach Custom Dataset – MarketPoseDataset This project includes a custom PyTorch dataset class called MarketPoseDataset, designed for pose-guided image generation. […]
- [Genesis - The Rover](https://ivlabs.in/rover/): Overview This rover prototype is designed for robust exploration on uneven terrains and inclines of up to 45 degrees, featuring GPS-guided autonomous navigation, obstacle detection, and adaptability to harsh environments. It was developed by Team Pravartak as part of Gujarat Robofest 4.0. Rover Description Electronic Components Component Description NVIDIA Jetson (e.g., Jetson Nano) Onboard processing unit for running algorithms and controlling the rover’s systems. Ultrasonic Distance Sensor (HC-SR04) Measures distance to surrounding objects, used for obstacle detection. L298N Dual H-Bridge Motor Driver Powers and controls motors, enabling forward and backward movement. Orange High Torque DC Motors (555 series) Provides torque for movement on […]
- [Batch 2025](https://ivlabs.in/batch-2025/): Atul Jaiswar Electrical and Electronics Engineering Soham Sarpotdar Mechanical Engineering Harsh Wadibhasme Electrical and Electronics Engineering Kishore P Chandra Electronics and Communication Engineering​ Mayank Lonkar Mechanical​ Engineering Nakul Singh Mechanical Engineering Pratyush Chakraborty Mechanical Engineering​ Ravi Agrawal Mechanical​ Engineering Rutvik Kulkarni Electrical and Electronics Engineering
- [Autonomous Lane Following Robot](https://ivlabs.in/autonomous-lane-following-robot/): Aim: This project aims to identify lanes and steer the robot between the lanes along the detected path. Overview: Autonomous driving is a huge and complex project, involving many technologies.In our project we have created a system which guides robot in lane following using computer vision and robotics technology. The robot uses OpenCV for image processing and ROS for communication and control. Robot uses live camera feed and processed it through OpenCV to detect the lanes and calculate a path for the manoeuvre of the robot within the lanes. Working Principle: The algorithm mainly depended on the two Hough lines that we […]
- [Ball and plate system](https://ivlabs.in/ball-and-plate-system/): Description: This project primarily aims to achieve balance control of a ball at any specific position on a plate using a PID controller. ​ Working Principle: A Ball and Beam system was initially designed to achieve the objective of balancing a ball at any desired position on the beam. This system underwent a two-step implementation process. Firstly, it was developed and simulated in Python, allowing for the refinement of control algorithms. Subsequently, the system was translated into a hardware setup using an Arduino UNO, an ultrasonic sensor, and a servo motor.  The Arduino UNO served as the primary controller, executing the […]
- [Kuiper Escape using RL](https://ivlabs.in/kuiper-escape-using-rl/): Overview To simulate and analyze an agent’s navigation in the custom Kuiper belt environment and hence train it to maximize rewards by avoiding obstacles and exploring efficiently using reinforcement learning algorithms. Custom Gym Environment The objective of the game is to live as long as you can, while avoiding the asteroids in the Kuiper Belt. The player starts centered in the screen, an can move in any direction using the keyboard arrows. Asteroids are generated with random sizes, speeds, and starting locations. The game ends once all player lives have expired. Actions The user has the following discrete actions: Note: […]
- [Playing Doom Using Deep Reinforcement Learning.](https://ivlabs.in/playing-doom-using-deep-reinforcement-learning/): Overview This project showcases the training of a Reinforcement Learning (RL) agent using Proximal Policy Optimization (PPO) within a custom environment designed for the game Doom, utilizing the VizDoom library. The RL agent learns to interact with the game environment, developing effective strategies for navigation and survival. Approach To understand RL concepts, we first trained on various environments. a)FrozenLake Environment:For FrozenLake, we used Dynamic Programming, which quickly converged to an optimal solution in the deterministic setting. In contrast, Monte Carlo and SARSA(λ), better suited for model-free scenarios, required extensive exploration and hyperparameter tuning to perform well in the stochastic version. […]
- [Cryptic Knock Door Lock : Project Janus](https://ivlabs.in/cryptic-knock-door-lock-project-janus/): Overview Nothing says “There’s something valuable here!” than the sight of a lock. But what if the lock was invisible and the unlocking key could be transmitted through solid matter? No one would even know there was a lock, much less how to pick it. That’s what he does. It hides all of the lock mechanism away and can only be unlocked by something you know: a secret pattern of knocks.​ Tools Used Approach Block Diagram Impact on society The idea of using a completely different mechanism for unlocking a door, where there is no need for a visible lock […]
- [2D XY Plotter](https://ivlabs.in/2d-xy-plotter/): We built a 2d xy plotter machine which can efficiently print letters and words and control it through bluetooth using an android app. There are two stepper motors-one which controlled the movement along y direction which moved the whole central limb(having a metal plate ,servo motor and pen and the second stepper motor) .The second stepper controlled the movement along x direction by moving the pen holding plate. Components Used Solidworks Base model of our Design Stepper Motors – L298N Motor Driver Stepper motors are DC motors that move in discrete steps. They have multiple coils that are organized in groups called “phases”. […]
- [Single Phase Inverter](https://ivlabs.in/single-phase-inverter/): Single Phase Inverter is an electric apparatus that changes direct current (DC) to alternating current (AC) using the power MOSFETs’ H-bridge. Power MOSFETs’ gate being protected by Gate Drivers. Gate Drivers powered by the rectifiers which can be replaced by DC source Tools Used Rectifier Circuit Rectifiers convert the ac mains supply to the dc voltage which can be regulated to desired DC output.  The output of the rectifier is given to the Gate Drivers, which gates the power MOSFETs at the desired time.  These rectifiers can be replaced by the DC source to be free from the AC source dependence as […]
- [Wizard's Chess](https://ivlabs.in/wizards-chess/): A GUI application to play 2-player chess using speech recognition. Tools used Speech Recognition Wizards’ Chess uses CMU’s Sphinx4 library for this purpose. It is an open source library based in Java for speech to text conversion. Input is taken through the microphone. It is converted to text by Sphinx4, and this text is further used to determine what move the user wants to make in chess. Making a move in the game You need to specify the initial and final position of the piece using standard board coordinates. However, we have changed the A-H and 1-8 notation to 1-8 and 1-8 notation […]
- [FROMO Bot](https://ivlabs.in/fromo-bot/): Fromo is a robot which is built using android Operating System that performs the following functions: Tools Used RC Mode Aim: To implement remote control movements to the bot with the remote being an android app.Process in short:1. An activity was built in the FROMO app which consisted of the image buttons of the respective directions.2. In this app Bluetooth was interfaced.3. On clicking any button of the app activity a data is send corresponding to the button to the Arduino Uno which is interfaced via Bluetooth module HC05.4. Corresponding to the data send, the Arduino instructs the motor driver L293D […]
- [Robotic Platform to Learn and Implement AI Algorithms](https://ivlabs.in/robotic-platform-to-learn-and-implement-ai-algorithms/): Overview ​Automatic path planning is one of the most challenging problems confronted by autonomous robots. Generating optimal paths for autonomous robots are some of the heavily studied subjects in mobile robotics applications. The aim of the project is to develop a rapid prototyping platform to run and test path planning algorithms. It uses overhead camera for 2D environment mapping, Bluetooth for wireless communication and the robot has calibrated PID controller for smooth trajectories. It overlooks the hardware complications and provides easy implementation for search algorithms. Tools Used Arena The environment consists of a thermocol sheet containing  obstacles. Color papers have been […]
- [E Braille Reader](https://ivlabs.in/e-braille-reader/): Overview Around nine out of ten blind people in the world live in low-income settings. So we thought, why not make an economical and portable device that bridges the gap between the electronic domain of knowledge and the visually impaired? After all, why can’t the blind browse the internet or use WhatsApp?Keeping in mind the blind’s reading and writing habits, the device is designed to take an electronic file as input and then display the corresponding characters from their conventional braille script. The characters come one by one at the slits (provided in the outer casing), eventually covering the entire […]
- [Flappy Bird using RL](https://ivlabs.in/flappy-bird-using-rl/): The project aims to train an agent (a bird) to score by crossing pillars in a Flappy-Bird-gym environment created for OpenAI. The agent bird learns to score by crossing pipes with the Q-Learning Algorithm. Environment Description State Space Action Space Reward Termination Algorithm Result Team Mentors
- [Autonomous Exploration](https://ivlabs.in/autonomous-exploration/): Aim:  To explore an unknown area using a mobile robot, avoiding all obstacles and simultaneously generating a 2D map of the area with the help of a LiDAR sensor. Working Principle: This algorithm is mainly dependent on lidar data we are obtaining from YDLIDAR. The LiDAR sensor mounted on the robot was used to detect obstacles in front, left and right directions and based on the information, the robot moved in a direction where obstacles were farther or absent. Mapping was done using hector mapping package to create a 2D occupancy grid map of the area. In hector mapping, the robot […]
- [Neural Style Fusion](https://ivlabs.in/neural-style-fusion/): The project aimed to implement the Neural Style Transfer Algorithm, one of the exciting applications of Convolutional Neural Networks. The technique involves taking two images—a content image(C) and a style reference image(S) (such as an artwork by a famous painter)—and blending them together such that the output image(G) looks like the content image, but “painted” in the style of the style reference image (as shown beside). Procedure Results After fine tuning of the parameters, the following results were obtained. One can infer that if the Content and Style images are chosen appropriately, the result may turn out to be a fantastic and artistically pleasing image. Team […]
- [Face Recognition](https://ivlabs.in/face-recognition/): This project demonstrates the implementation of a face recognition system using Siamese networks. Siamese networks are widely used in face recognition tasks because they can effectively measure the similarity between two images, making them ideal for verification and identification purposes. Algorithm Siamese Networks Contrastive Loss This is the loss function used for learning the similarity function. where Dw is defined as the Euclidean distance between the outputs of the sister networks, Y is either 1 or 0. If the first image and second image are from the same class, then the value of Y is 0, otherwise, Y is 1. […]
- [Hand gesture control bot](https://ivlabs.in/hand-gesture-control-bot/): OVERVIEW: What if a physically handicapped person sits in a chair and can move   anywhere just by his hand gesture .Inspired from such an idea we made a small robot   model which is moved by the hand gestures of the person. INSIGHT: IMU(MPU 6050):The MPU-6050 is made by Invensense and consists of a MEMS (microelectromechanical system) accelerometer and gyroscope with 16-bit analog-to-digital converters The MPU-6050 has a remarkable innovation called the Digital Motion Processor (DMP) integrated into the chip whose programming is proprietary to Invensense. It allows 6-axis sensor fusion calculations to be performed by the DMP at a fixed rate of […]
- [Self Balancing Platform](https://ivlabs.in/self-balancing-platform-2/): Overview Control system is designed to stabilize the camera gimbal system used in different airborne systems for applications such as target tracking, surveillance, aerial photography, autonomous navigation and so on. The technique is applied in everything from self-stabilizing cameras to helicopters and noise reducing equipment. This camera gimbal system replaces many traditional tracking systems such as radar which are heavy and large to mount on air vehicles. So, the stabilization of camera gimbal is very important to eliminate shakes and vibrations in photography, provides accuracy in tracking moving target and so on. Mechanical Aspect 1) DIMENSIONS:            […]
- [Sun Tracker On Mobile Robot](https://ivlabs.in/sun-tracker-on-mobile-robot/): Overview Main objective of our project is to make an all-terrain robot with a sun tracking mechanism on  it.The bot can traverse all kinds of terrain, climb steps up to 15 cm’s high and can withstand a gradient of about 45 degrees.The Sun-Tracker must always point towards the sun to absorb maximum solar energy at any given time.The tapped solar energy charges a battery that runs the robot. Hardware Used Software Used Arduino IDE Dassault Systemes Solidworks Proteus Design Suite Solidworks Assembly Circuit For Rocker-Bogie Codes Used Features Solar panels always remain perpendicular to sun rays to maximise solar energy […]
- [​IOT Based Ambience Monitoring System ](https://ivlabs.in/iot-based-ambience-monitoring-system/): Overview The IOT Ambiance Monitoring system is designed to monitor the environmental aspects of its surroundings . It is equipped to monitor the temperature,humidity,air quality and noise. It sends this data to its mobile application. It has  tremendous  potential as it can be upgraded and equipped with more sensors which will increase its capabilities .Therefore it can be of use in the industrial sector , mining sector , hospitals , offices , military etc. ​ Hardware Used NodeMCU ESP8266 NodeMCU is an open-source firmware and development kit that helps you to prototype or build IoT product.  It includes firmware which runs […]
- [Face Gesture Laptop Control](https://ivlabs.in/face-gesture-laptop-control/): Overview It is a Human computer interaction project. Here we have written a code such that if we wink(😉) right eye, right click is done and if we wink left, left click is done. If we move nose, it will move the cursor across the screen. Also if we open our mouth, scrolling mode is enabled and the same can be used to disable the scrolling mode. Tools Used Features Without the use of any physical help, the user can now be able to use the mouse using simple facial gestures such as blinking. A face is divided into 68 distinct landmarks. Exploiting […]
- [Auto Surveillance Mobile Robot](https://ivlabs.in/auto-surveillance-mobile-robot/): Overview We have developed a bot which will alert the user of a intruder if the latter is detected . At any given time you can access the Live Feed recorded by the camera of the bot. Major Components Used 1. Raspberry PI Zero W 2. Ultrasonic Sensor (HC-SR04) 3. PIR Sensor( HC-SR501) 4. Camera Module 5. BO Motors x2 6. Motor Driver Module (L298N) 7. LIPO Batteries x2 (450 mAh, 3.7V) 8. Power Bank Working In Brief Application Details and Code Block Diagram 3D Model Video Demonstration http://www.youtube.com/embed/PWTPQx9G8Ao?wmode=opaque Our Team Members Mentors
- [RFID Security System](https://ivlabs.in/rfid-security-system/): Overview ​Its a security system in which when authorized RFID tag gets scanned entrance is allowed and a message of who has entered is send to owner. If a guest entry happens camera feed is recorded and can be accessed by owner later on. A  LCD  display shows name of entered person. Applications Components Arduino Mega 2560 It has 54 digital input/output pins (of which 14 can be used as PWM outputs),16 analog inputs, 4 UARTs (hardware serial ports), a 16 MHz crystal oscillator, a USB connection, a power jack, an ICSP header, and a reset button. RFID sensor & tags Radio-frequency identification (RFID) uses electromagnetic […]
- [Laptop Hand Gesture Control](https://ivlabs.in/laptop-hand-gesture-control/): Overview As the technology tends to make human life easier and safer. So our main aim is to reduce the effort of interaction with computers through input devices using simple gestures. You might have seen Hand Gesture Controlled Robots, where the motion of a robot is controlled by the gestures of the hand. Another interesting project based on a similar principle is an Arduino based Hand Gesture Control of your computer or laptop.Instead of using a keyboard, mouse or joystick, we can use our hand gestures to control certain functions of a computer like play/pause a video, move left/right in […]
- [Real Time Digit Classifier](https://ivlabs.in/real-time-digit-classifier/): Abstract Numbers are one of the first things taught to us in school or at home, but the computer is not lucky enough to have a home or go to school.​So, it relies on us to teach it things, even the basics like recognizing digits. The techniques and algorithms used in training a machine to do specific tasks are grouped under a subject called Machine Learning and Neural Networks. Approaches Employed Single Layer Perceptron The first approach was a naive one and used just a single layer of 10 Nodes that took all the pixels as individual inputs and gave a prediction […]
- [FIXED WING UAV](https://ivlabs.in/fixed-wing-uav/): Aim: To design and develop a fixed-wing Unmanned aerial vehicle. This will involve aerodynamic design, performance analysis using XFLR5, and fabrication of the fixed wing. DESIGN METHODOLOGY AIRFOIL SELECTION Airfoil selection is done by selecting different airfoils and then analysing them using XFLR5. We found that NACA2412 with camber 4% gives us Cl=1 at 4 ∘ -5 ∘ AOA. The simulation graphs are shown below.  We have designed rectangular wing using this airfoil and elevator, rudder are kept Flat. WEIGHT ESTIMATION For estimation of weight, we have found weight of each component individually and then added to get final weight of plane. The estimated weight was found […]
- [Background Subtraction](https://ivlabs.in/background-subtraction/): Overview Visual world is dynamic and we constantly come across video scenes with many moving objects like vehicles , pedestrian etc. Many applications do not need to know everything about the evolution of movement in a video sequence , but the only requirement is , the information of changes in the scene , because an image’s regions of interest are objects ( humans, cars, etc. ) in its foreground. After the stage of image preprocessing  object localisation is required which may make use of this technique. Background subtraction is a widely used approach for detecting moving objects in videos from […]
- [Binary Classifier](https://ivlabs.in/binary-classifier/): It seems to be a really easy task to differentiate between an apple and an orange ,but is that so simple for a machine also? No absolutely not !  This  seemingly simple task requires an efficient algorithm  for machine to understand the difference  between the two. This forms the basis of understanding the machine learning algorithm.  Demonstration Team Members Mentors
- [Sudoku Solver](https://ivlabs.in/sudoku-solver/): OVERVIEW Sudoku is one of the most popular puzzle of all time. The goal of Sudoku is to fill 9×9 grid such that each row, each column and 3×3 grid contains all of the digits between 1 to 9. In this project we aim to create a real time Sudoku solver  which recognise the elements of Sudoku puzzle and providing a digital solution using Computer Vision. Sudoku Solver is the collection of very basic image processing techniques. A very good way to start is the OpenCV library which can be compiled on almost all the platforms.  PRE-REQUISITES  OF  THE  PROJECT​ […]
- [OmniDirectional Gesture Robot](https://ivlabs.in/omnidirectional-robot/): Overview The objective of this project was to build a robot that can move in all directions without changing its orientation using mecanum wheels, controlled entirely through intuitive hand movement for effortless, gesture-based navigation.  Approach The system architecture is divided in two parts, the gesture controlled unit (sender) and the robot chassis (receiver).  Consequently, the project is organized in three phases ,kinematics for omnidirectional motion, connection between the two units and hardware implementation.  In the first phase, existing mathematical formulas and algorithms were utilized to enable movement in all directions without changing orientation, and these were implemented in the code. […]
- [Stylus Snake](https://ivlabs.in/stylus-snake/): Overview Stylus controlled snake game is similar to classical snake game but differs in the way we control it which is done by a Stylus. A stylus refers to an object of any color that is first detected and then later can be used to control the motion of the snake. Abstract For the stylus, the camera feed is taken, Gaussian blur is applied, frames are converted from BGR to HSV, morphological transformations are applied to remove noise, then thresholded to find the required part of the stylus. Approaches used for stylus detection Using trackbars to find the HSV values […]
- [Stereo Reconstruction](https://ivlabs.in/stereo-reconstruction/): Overview Abstract To obtain 3D Reconstructed Image   Relation between Disparity and DepthDisparity refers to the apparent pixel difference between pair of stereo images. Suppose you are holding an object at a distance X from the center of distance between both eyes and now you just close and open each eye simultaneously, you will observe that there is a significant jump of the position of that object. Now increase the Distance to 2X and repeat the process of closing and opening each eye simultaneously and you will observe that the object will move a little bit and there is no significant […]
- [Quadcopter](https://ivlabs.in/quadcopter/): Overview This project deals with implementation of control systems. This includes autonomous control of 2D quadcopter whose motion is governed by a differential equation of motion and a PD controller.The input thrust and moment to maneuver the quadrotor is determined by the controller based on magnitude of the error in position— current position to desired position.The controller has two segments, Proportional § and Derivative(D), which have to be tuned in order to have steady control and motion. Aim ​The main focus of this project is to design a quadcopter capable of autonomously navigating through a trajectory in a 2D plane. […]
- [Maze Solver](https://ivlabs.in/maze-solver-2/): Overview As children, we’ve all solved mazes. People are captivated by mazes. Let’s have a look at how a robot, equipped with a LiDAR sensor, solves a maze without having any prior knowledge of the environment. Our project’s primary objective is to use the Robot Operating System (ROS) to simulate a robot solving a maze in a gazebo environment. The robot is completely unaware of the maze’s surroundings. Approach This project was completed in three steps:Motion control of SAHAYAK Bot.Using the wall following algorithm on a single wall.Solving the Maze environment.   The Sahayak bot is controlled by delivering velocity to […]
- [Image Denoising](https://ivlabs.in/image-denoising/): Overview ​Abstract: ​With the increase in digital images taken every day the demand for more accurate and pleasing images has also increased.Image Denoising will help the above task as the name itself suggests we will remove noise from the noisy image to restore the original image. We at IvLabs gave a try at this task of Image Denoising with the help of Convolutional Denoising Autoencoder. Approach:The denoising autoencoder is implemented with PyTorch and is applied on the MNIST and Fashion MNIST datasets.The encoder network consists of three convolutional layers while the decoder network has three trans convolutional layers.Encoder downsamples the data and then decoder reconstructs the original […]
- [Hand Gesture](https://ivlabs.in/hand-gesture/): Overview Aim This project deals with the implementation of OpenCV and ROS. It includes detecting the hand gestures and publishing different velocities to the turtlebot3 in the gazebo environment. Applications Hand gesture detection can be used in various industries as advances in computer vision, sensors, machine learning, and deep learning have made it more available and accurate.Hand gesture detection finds its use in:1. Virtual environment control2. Remotely control robots3. Sign language translation Working in Brief Detection of Hand GesturesFirst, we isolate hand from the background for this we separate the skin color from the input frame using HSV or another […]
- [Doodle Classifier](https://ivlabs.in/doodle-classifier/): Overview The Doodle classifier is based on a Convolutional Neural Network which classifies the doodle input given by the user in 20 different classes. ​ Abstract: Computers are advancing at great speed in this age. If they have the ability to understand our doodles or quick line drawings, it will allow for much more advanced and simplified forms of communication. Drawing and understanding images is a way of communication when words fall short or language is inadequate due to different cultural and literacy levels . The techniques and algorithms used in training a machine to do specific tasks are grouped […]
- [Automatic Speaker Recognition](https://ivlabs.in/automatic-speaker-recognition/): Overview The project Automatic Speaker Recognition (referred to as ASR) is designed to recognize and distinguish between multiple voices of different persons. A very large dataset of various speakers is used and every single audio sample is tested with the existing audio samples and matched with the audio sample whose features are mostly matching. Finally, the accuracy of these results is checked to know the working of the project. Abstract From the very famous voice assistants designed by the sophisticated developers of the world, SIRI and ALEXA have been ruling the signal processing world for many years. This project is […]
- [Mobile Robot](https://ivlabs.in/mobile-robot/): OVERVIEW A customized autonomous robot with the ability of exact localization in an unknown environment.In this project , we aim to demonstrate the possibility of using  IR wheel encoders and communicating with Robot Operating System(ROS) for location finding. An autonomous groundvehicle must be able to locate the exact co-ordinates and navigate to it without having priorknowledge of the environment. Considering  the starting point as reference and navigating through thepath and detecting the final co-ordinates of the mobile robot. HARDWARE  USED ​DC-DC step down voltage converter. 2 DC Johnson motors of 100 RPM were used for locomotion. Motor speed is varied […]
- [AI Snake](https://ivlabs.in/ai-snake/): Overview The project is an attempt to solve Classic Snake Game using Reinforcement Learning Tabular method i.e. Q-learning. The goal of the agent, the snake, is to maximize cumulative reward which it does by generating a table called Q-table which is used to decide action for each state. The values in this table are called state-action values as they represent the value of performing a particular action in a particular state. The state is information that an agent receives for a particular situation that is used to estimate future outcomes. The policy tells us about the behavior of the agent. […]
- [MUSIC GENRE CLASSIFICATION](https://ivlabs.in/music-genre-classification/): Aim: The main aim of the project is to identify the genre of the music clips.This is done using GTZAN dataset. With the help of PyTorch , Convolutional neural network is made of 3 convolutional and 4 linear layers . ReLu activation function and SGD optimizer with learning rate =0.0005 is used . Basic Flow: For the input the spectograms were generated which were then passed to the convolutional neural network and with the help of genre as labels the classification was done. Genres: Accuracy Train set : 100 % Test set : 65 % Accuracy plot : Loss plot […]
- [Image Colorization](https://ivlabs.in/image-colorization/): Overview: We are thrilled to share our recent project, where we successfully tackled the challenge of colorizing grayscale images using deep learning methods. Deep neural networks can be difficult to train, especially as their depth increases, which often leads to problems such as vanishing and exploding gradient descent, impacting the accuracy of the network. We followed the section 3.1 CNN Model of Paper.​To overcome these challenges, our team utilized Residual Networks (ResNets) and skip connections in our implementation. We employed an autoencoder, a neural network consisting of an encoder, bottleneck latent space, and decoder, to achieve accurate colorization results. Additionally, we […]
- [BB8](https://ivlabs.in/bb8/): A Spherical Robot OVERVIEW BB-8 is a spherical shaped robot with a robotic head that always stays in a stable position at top of the moving sphere. Main aim of the project is to stabilize and balance the system. It also includes to stabilize the head of bot during its motion so that it always remains at the top of the sphere. ​INSIGHT 1. Arduino Nano : Small and compact micro controller to control the bot. Owing to its small size it can easily be fitted inside internal circuit which is to be placed inside the spherical shell which forms […]
- [SpyBot](https://ivlabs.in/spybot/): Overview  Spybot is the robot that can be controlled wirelessly on computer, laptop or smartphone . We can see wireless live feed  on the  browser by entering the IP address. The surrounding environment will be in under surveillance and secretly we can keep eye on the surrounding. Tools Used Softwares Used Application Block Diagram Circuit Diagram ​Design in solidworks Video Team Mentors Team Members
- [Maze Solver](https://ivlabs.in/maze-solver/):  Maze Solver is an Autonomous Bot that can solve any maze with dead ends without confusing at intersection points. Components: Atmega8 Development Board: We used Atmega 8 Board which also includes L293D motor driver circuitry. It takes data from the sensors and based on that data it takes action. IR Sensors: We used IR sensors to detect position of the line to be followed with respect to the robot’s position. They are based on the basic observation that “the white surface reflects the light and the black surface absorbs it DC Motors: Two DC motors of 150 RPM. Battery: To […]
- [Rubik's Cube Solver](https://ivlabs.in/rubiks-cube-solver/): Rubik’s Cube Solver(RCS) is a complete program that can solve any scrambled 3X3X3 cube in less than 22 moves. It uses kociemba algorithm for finding the most optimum solution of a scrambled cube.  ​Tools Used: ​Image Acquisition: RCS use OpenCV for image acquisition and Image Processing. Image can be acquired from a webcam. All the faces of the cube are scanned successively. The image is stored using HSV color space. Color of each face is detected as soon as the face is properly aligned. Further the color data is processed to find the position of different colors on the cube. This data is passed on […]
- [Controls Theory](https://ivlabs.in/controls-theory/): Overview Control theory deals with the control of dynamical systems in engineered processes and machines. The objective is to develop a control model for controlling such systems using a control action in an optimum manner without delay or overshoot and ensuring control stability. Fundamentally, there are two types of control loops: A control system possessing monitoring feedback, the deviation signal formed as a result of this feedback being used to control the action of a final control element in such a way as to tend to reduce the deviation to zero. Summer Projects Cruise Controller  AIM Designing cruise controller to reach  desired […]
- [Computer Vision](https://ivlabs.in/computer-vision/): Overview The sole motive of Computer Vision is to train and make the computers self-reliant in interpreting and understanding the details of the visual world. Understanding in this context signifies the transformation of visual images (the input of the retina) into an array of pixels and numerical values reflecting the shades of red, green and blue. When fed with the digital images or videos from the camera, the system can accurately identify and distinguish between objects, giving them the  means to practically ‘see’ their surroundings and then react as trained.  Basic forms of computer vision includes :  Image segmentation, Object detection, Facial recognition, Edge detection, […]
- [Localization](https://ivlabs.in/localization/): Overview Primary goal of localization is to use noisy inputs from multiple sensors, to estimate, as accurately as possible, the current location of the robot within its environment, and also, in some cases, build a map of its surroundings as it explores the area . Navigation is one of the most challenging competencies required of a mobile robot. Success in navigation requires success at the four building blocks of navigation: ​● Perception– the robot must interpret its sensors to extract meaningful data● Localization– the robot must determine its position in the environment● Cognition– the robot must decide how to act to achieve its goals● Motion […]
- [Robo Lamp](https://ivlabs.in/robo-lamp/): Overview A robo-lamp is a robotic arm with three degree of freedom whose end effector is LED array along with a webcam. The arm is intended to follow the object by performing the necessary movements so that the light is focused at that object.  The video of the object was captured using a webcam and then it was processed with OpenCV. This processes include motion detection, image thresholding and finding the centroid of that particular object. So according to the coordinates acquired (centroid) the arm was supposed to change its position.  Components To capture the video It   provides   the   […]
- [2 Degree-Of-Freedom Handheld Gimbal](https://ivlabs.in/2-degree-of-freedom-handheld-gimbal/): Overview This project showcases a two degree-of-freedom gimbal system with independent control over each axis. The primary purpose of this gimbal system is to provide a stable platform for various applications, such as camera stabilization. Tech Stack Components Type Model Quantity Microcontroller Development Board Arduino UNO 1 Inertial Measurement Unit (IMU) MPU-6050 1 Servo Motors MG996R 2 IMU and Servo Simulation Using PID, we simulated an IMU and mapped the angle change onto two servos. We used Wokwi for simulation. Here, our goal was to simulate the hardware environment before transitioning to the actual hardware components. Results: Polar Plot of IMU-Measured Angles […]
- [Indoor Navigation using ArUco Markers](https://ivlabs.in/indoor-navigation-using-aruco-markers/): Overview In our project, we’ve employed Turtlebot for autonomous indoor navigation which involves using marker-based localization, like ArUco. These markers act as crucial reference points for the robot’s autonomous movement within unfamiliar indoor spaces. This approach is cost-effective, simply requiring the deployment of marker patterns and protective measures. For the completion of this project, we also made use of ROS, OpenCV, and Gazebo simulation, enabling us to navigate, control, and process data for various robotic applications, which could include warehouse management Methodology We performed simple tasks on Turtlesim node to get practical knowledge about ROS. How to write code in […]
- [Anti Theft Device](https://ivlabs.in/anti-theft-device/): Best things for you and your precious things….. Overview In today’s world where cases of theft of valuables are increasing significantly, we felt the need of a smart wearable device to prevent and catch theft . To create a basic  prototype of this device , we shall link the smart device to a handheld by means of a wireless connection. Through this link of the device and an Android phone, the user will be able to lock the device from anywhere remotely. Moreover, when in-sync the device can also send distress / panic signal to the Android using the SOS […]
- [Micromouse](https://ivlabs.in/micromouse/): Objectives The objectives of the project were to create a compact( 8 x 8 cm) robot that can autonomously solve and obtain the fastest path for any given maze. Methodology Software Implementation In the initial weeks, we worked on implementing the maze-solving algorithms in Python. We implemented and explored a set of algorithms, namely After this, we built a maze using corrugated sheets ,The dimensions used were 16 x 16 cell. The maze consists of plus shaped holders that can be used to hold two or more sheets according to requirements. Subsequently initiated work on hardware components, which involved tasks […]
- [Self Balancing ​Platform](https://ivlabs.in/self-balancing-platform/): Overview Control system is designed to stabilize the camera gimbal system used in different airborne systems for applications such as target tracking, surveillance, aerial photography, autonomous navigation and so on. The technique is applied in everything from self-stabilizing cameras to helicopters and noise reducing equipment. This camera gimbal system replaces many traditional tracking systems such as radar which are heavy and large to mount on air vehicles. So, the stabilization of camera gimbal is very important to eliminate shakes and vibrations in photography, provides accuracy in tracking moving target and so on. Mechanical Aspect 1) Dimensions:            […]
- [Facial Landmarks Detection](https://ivlabs.in/facial-landmarks-detection/): Overview This project implements a facial landmark detection system using the Xception model, trained on the ibug dataset. The goal is to accurately detect facial landmarks from images and provide a user-friendly web application for real-time detection. This model will support real-time inference for applications such as: Learning Process Dataset used Procedure Network Design Results Team Mentors
- [Laser Security System](https://ivlabs.in/laser-security-system/):                                                                       ​OVERVIEW Crooks and cons are getting smarter in  performing their unethical actions  with the advancement in technology, thus there is a sincere need for security systems to evolve as well. Laser security system provides a better alternative for the protection of confidential assets.We know that as laser light is not visible to the naked eye hence this can be used as an advantage to design a […]
- [Quadruped Robot](https://ivlabs.in/quadruped-robot/): A MECHANICAL ROBOT….                      OVERVIEW Our Robotics industry is mainly focused on making wheeled robots but the main problem with the wheel mechanism is that it has got limitations of transversing on different terrains.​This problem can be overcome by introducing new type of mechanism inspired from biological designs of animals.Project Quadruped mainly focuses on making a mechanism of walking by observing motion of animals around.​​This type of motion helps us to achieve advantages over the traditional wheeled robots and a giving a futuristic approach.  COMPONENTS USED ​1. ARDUINO UNO A  Microcontroller which helps […]
- [FSRCNN](https://ivlabs.in/fsrcnn/): FAST SUPER RESOLUTION CONVOLUTIONAL NEURAL NETWORKS Overview FSRCNN (Fast Super-Resolution Convolutional Neural Network) is a model tailored for real-time image super-resolution. It utilizes a unique architecture with smaller filter sizes and an efficient sequence of convolutional and deconvolutional layers, which first extracts features, reduces dimensionality, and then upscales the image. This design achieves high-quality, high-resolution outputs with minimal computational cost, making FSRCNN suitable for fast, high-performance applications in super-resolution tasks. Approach Evaluation Metric and Loss Functions Model Architecture Results Use Cases of the Project Team Mentors
- [Shape Tracing with Robotic Arm](https://ivlabs.in/shape-tracing-with-robotic-arm-3/): Aim: This project aims to make a planar serial manipulator, with 3-DOF, that can trace various shapes. Working Principle:      The shape tracing mainly based on concept like Forward kinematics, Inverse Kinematics and Trajectory generation.  Software: Arduino IDE Hardware Components: Arduino UNO MG996 Servo Motor Media: Team Members: Mentors:
- [Osmos](https://ivlabs.in/osmos/): Omni-Directional Spherical Modular Snake Robot Overview Mechanical Design Video Demonstration Authors
- [Controller Design for  Multi Agent Path Planner​](https://ivlabs.in/controller-design-for-multi-agent-path-planner/): Overview Multirobot systems offer flexibility, sensor coverage which makes them attractive for task such as surveillance, rescue, and warehouse automation. One of the foundational problems for multirobot systems is finding safe, collision free paths that takes robots to configurations at which they can perform tasks, which is termed the multi robot path planning problem. Insight Principle To solve this problem, the whole workspace was divided into several polygonal controllers. Now there exists Path Planner algorithm which tells us polygonal controller should be executed after a particular polygonal controller. This will lead to execution of controllers in a chain, which act […]
- [Assistive Glove](https://ivlabs.in/assistive-glove/): Overview The objective of the project is to bridge the existing gap of communication between society and the hearing and speaking disabled. By the use of an array of features such as speech to text and text to speech conversion, tactile keys to act as a keyboard and mouse pointer control help further control of computers and other digital environments.​An android application will also help in making the learning process more interactive too. The major application of this device is proposed in schools, to help the hearing and speaking disabled to learn in public schools. Hardware This device is made […]
- [Multi-Focus Image Fusion](https://ivlabs.in/multi-focus-image-fusion/): Introduction In the field of digital photography, it is often difficult for an imaging device like a digital single-lens reflex camera to take an image in which all the objects are captured in focus. Typically, under a certain focal setting of optical lens, only the objects within the depth-of-field (DOF) have sharp appearance in the photograph while other objects are likely to be blurred. A popular technique to obtain an all-in-focus image is fusing multiple images of the same scene taken with different focal settings, which is known as multi-focus image fusion. Aim Aim of the project is to capture […]
- [ReBIS](https://ivlabs.in/rebis/): Overview Robots capable of switching between snake-like and bipedal motion have advantages of greater manoeuvrability. The ReBiS (Reconfigurable Bipedal Snake) robot is a novel modular design mechanism which can quickly transform between various configurations without rearrangement of modules. Reconfiguration without rearrangement has advantages of lighter weight, lower power consumption and higher efficiency, by eliminating the requirement of actuators and mechanisms needed for rearrangement. The video on the right, shows the gaits implemented on ReBiS. Possible gaits are divided into three categories; snake gaits, transforming gaits and walking gaits. An example gait, belonging each of the three categories, is implemented and […]
- [Blind Navigator](https://ivlabs.in/blind-navigator-2/): Overview What if a visually challenged person could perceive the environment around him without making any physical contact? What if he/she could distinguish whether the object is stationary or moving? If moving, is it moving away or towards? The Blind Navigator answers them all, taking the blind vision to next level. The Blind Navigator is a simple electronic device which measures the distances from an obstacle using proximity sensors, simultaneously providing vibratory and audio (through earphones)  responses to the user. This enables the blind to ‘map’ the environment around him and navigate safely. The project is being accomplished under the […]
- [Writing Arm](https://ivlabs.in/writing-arm/): Overview  Ever imagined a hand which can write your name !!And which can grab things like we humans do!! The Robotic Arm is all what you need  Robotic Arm is a 3 DOF arm, which can write any input given by the user . The input is given via keyboard .It is a type of mechanical arm,  programmed, with similar functions to a human arm  for writing and grabbing.The links of the manipulator are connected by joints allowing  rotational motion  which are in kinematic chain . Insight USB2Dynamixel is a device used to operate Dynamixel directly from PC.  USB2Dynamixel is connected to USB […]
- [Prosthetic Hand](https://ivlabs.in/prosthetic-hand/): Overview ​​As the perspective of technology tends to make human life easier and safer a vital contribution still remains in the field of upper limb prosthetics. In view of these aspects the students at IvLabs developed an 6DOF robotic hand as a cost-efficient replacement to existing Prosthetic hands yet retaining the functionality of human hand. Working Principle Each finger has an individual motor to move independently replicating HUMAN HAND. The fingers are under-actuated with their Actuation driven by high torque mini servo actuators through tendons as non-linear parameters. The thumb also has roll motion at its base, which is the […]
- [VTOL Fixed-wing UAV](https://ivlabs.in/vtol-fixed-wing-uav/): Overview Aim To design and control custom-fabricated Fixed-wing UAV with Vertical takeoff and landing (VTOL)  capabilities for payload delivery and surveillance purposes. Prototype 1 Maximum Takeoff weight 6 kg Payload Capacity 0.5 kg Calculated endurance 30 mins Cruise velocity 15 m/s Range 18-20 km Test Flight To test the vertical takeoff and landing, a test flight was conducted. Team members
- [Ductor](https://ivlabs.in/ductor/): Overview Manual cleaning of air ducts is a mundane and highly time consuming task, which has lead to disastrous accidents and unexpected overhead costs, and can be extremely detrimental to a duct cleaning professional’s health, especially in hazardous environments such as hospitals, or buildings where toxic substances are processed. Duct cleaning robots are the clear solution to these occupational hazards, and these products are on high demand by responsible duct cleaning professionals world-wide. Hence, a series of robots were developed at IvLabs in collaboration with Ozone House of Nirmitee Group under the guidance of Dr. Shital Chiddarwar , Dept. of […]
- [​Turtlebot 2](https://ivlabs.in/turtlebot-2-2/): TurtleBot is a low-cost, personal robot kit with open-source software. With TurtleBot, you’ll be able to build a robot that can drive around your house, see in 3D, and have enough horsepower to create exciting applications. PROJECTS ON TURTLEBOT SO FAR: 1 .Line Follower: Developed an algorithm of weighted mean which sets priorities to the near region of turtlebot in captured image. A web cam is mounted on turtlebot to track the line and according to algorithm it is able to traverse any type of curves. ​2.Navigaton using Parabolic Reflector ​Integrated a parabolic mirror to a webcam giving it 360-degree […]
- [​Natural Language Processing](https://ivlabs.in/natural-language-processing/): Overview Natural languages, though seemingly easy for humans to understand, contain various aspects that make it difficult for a machine to infer and extract information from. The field of Natural Language Processing (NLP) deals with representing natural languages in a way that facilitates machines to perform various downstream tasks. This is a crucial step in human-machine interaction and opens up various other possibilities.  Some of the real-life applications of NLP are seen in products like Amazon’s Alexa, Google Translate and Grammarly. Aim To have a bird’s eye view of the field of Natural Language Processing by implementing fundamental Language and […]
- [Garuda](https://ivlabs.in/garuda/): Overview The aim is to develop a drone which is capable of delivering a package of 500 gm autonomously from point A to B Control Flow Hardware Cyber-Physical Architecture For more info on off-board control of drone and simulation, refer this  site. Progress : Working Video Team
- [Shape Tracing with Robotic Arm](https://ivlabs.in/shape-tracing-with-robotic-arm/): Aim: This project aims to make a planar serial manipulator, with 3-DOF, that can trace various shapes. Working Principle:  The shape tracing mainly based on concept like Forward kinematics, Inverse Kinematics and Trajectory generation.  Forward Kinematics: –  It is used to know the position of the end effector when we know the joint angles and is calculated using D-H parameters. To calculate forward kinematics, we used Denavit-Hartenberg parameters.                                        1. Found D-H parameters.                            […]
- [Swayat](https://ivlabs.in/swayat/): 20 Dof kid sized Humanoid Robot About Swayat With an aim to build a generalized cross-platform robot to study, implement and explore the fields of Computer Vision, Electronics, Controls and Gait Designing, the students of IVLab’s have developed a 20DOF Humanoid. Mechanical Design Fabricated with 3mm Aluminum sheet using CNC Milling and the detailed parts were 3D printed using ABS plastic. Modelling and Simulation of individual subassemblies of arms and legs were also performed. Electronic Subsystem The sub controller circuit is based on the ARM CORTEX-M4 32-bit Processor, acting as the link between the robot’s Intel Atom processor and the different actuators, sensors […]
- [Robotic Arm](https://ivlabs.in/robotic-arm/): Precision in Motion About Robotic Arm This robotic arm, developed by IvLabs students, performs precise pick-and-place tasks with high accuracy. Utilizing servos and efficient mechanical design, it automates object movement between predefined points, ideal for manufacturing and material handling applications. OVERVIEW The robotic arm is a pioneer of modern robotics and finds its applications in industries, laboratories, human-assisted operations, medical robotics, and even in prosthesis. Kriti, the 3-DOF robotic arm, is a single-handed attempt to replicate the prodigy and a doorway to learn and culminate Mechanical Design, Image Processing, and Syndicated Programming. The robot can perform simple pick-and-place operations. INSIGHT THE […]
- [Autonomous Stair Climbing Robot](https://ivlabs.in/autonomous-stair-climbing-robot/): Overview This project presents deep learning based approaches for stair detection, statistical filtering on images for the estimation of stair alignment, and novel mechanical design for an autonomous stair climbing robot. The primary objective is to solve the problem of indoor locomotion over staircases with the proposed implementation. This project was partially sponsored by the IEEE VNIT Student Branch and made possiblethrough the active efforts of the Branch Counselor, Dr. Pradyumn Chaturvedi. Novel Contributions Hardware Specifications Electrical Aspects Mechanical Aspects Design Aspects Cyber Physical Architecture Stair Detection using YOLOv3 Transfer Learning was done for tiny-YOLOv3 using the ImageNet trained weights […]
- [Butler Bot](https://ivlabs.in/butler-bot/): Overview This project of butler robot is basically an idea of interfacing the computer vision with the present day robotics. This is one of the long term projects which has a huge scope of advancement in manual assistance, machine learning and artificial intelligence. Keeping these aspects of this project in mind , our team from IVLABS took a step towards the advancement anddevelopment of butler robots. Features A helping hand for your daily chores. Autonomously moving bot, performing your task. Easy manual control through your phone. robots helping with dull and tedious household chores; robots taking on new roles in […]
- [Sahayak- An Autonomous COVID Bot](https://ivlabs.in/sahayak-an-autonomous-covid-bot/): Introduction Medical personnel regularly put themselves at risk of infection to protect patients, a fact that everyone has been acutely aware of during the COVID-19 pandemic. Development of an autonomous robot for hospital environment aiming to reduce the risk of the health care workers at their work has exponentially increased in the ongoing pandemic.  Sahayak, a COVID aid bot that is capable of navigating autonomously in simulated static environments. The aim is to provide a general framework for developing medical assistive robots.  A prototype of Sahayak was successfully deployed at AIIMS Nagpur.   Mechanical Design Previous Work Pipeline Overview Pipeline Visual Odometry Visual Odometry Real-Time […]
- [Autonomous Driving Platform](https://ivlabs.in/autonomous-driving-platform/): Overview This is the first version of IvLab’s autonomous driving platform. Built using the chassis of a racing grade 1/10th RC car, it can be used in outdoor road environments. It has additional sensors and components which enable perception, localization, planning and control for autonomous driving applications.The ongoing project for which this platform has been developed is ‘Autonomous Delivery Robot’, which aims to accomplish A to B navigation with obstacle avoidance within our institute campus. Mechanical Aspects Electric Drive and Steering Sensors and Controllers Progress so far Semantic Segmentation 360 degree Vision using Catadioptric Camera Setup Rectified Images (Cylindrical Projection) […]
- [Hexapod](https://ivlabs.in/hexapod/): Overview This project aims to develop an hexapod robot capable of omnidirectional locomotion and obstacle climbing. Hardware Specifications Body Architecture The hexapod robot features a circular base with legs placed in a radially symmetrical configuration for enhanced stability and maneuverability. Leg Structure The hexapod’s legs have three degrees of freedom (DoF) to control forward/backward motion and height independently, allowing for versatile locomotion. For joints and actuators, high-torque MG996R servo motors are used for actuation, with servo mounts serving as joints. The motors are distributed among the coxa, femur, and tibia sections. Electronics The robot is powered by a Raspberry Pi 3b+ microcontroller, […]
- [Batch 2024](https://ivlabs.in/batch-2024/): Aaditya Rudra Research Assistant IQOQI, Vienna. Research Intern at Politehnica University Timisoara Aditya Jivoji Fullstack Developer at Finstack, Research Intern at University of Verona Dheeraj Deevi Management Trainee at Genpact Harsh Sharma Engineer at TATA Elxis Joel Vijo Program Associate at Well Fargo Lovesh Goyal PhD Researcher in Aerospace, IIT Madras Malhar Limaye Computer Science ​and Engineering Om Bhise Graduate Engineering Trainee at Hindustan Zinc, Poojan Gandhi Software Engineer at Concentrix Catalyst, Data Scientist at BarRaiser Prajyot Jadhav Research Intern at Vidyasirimedhi Institute of Science and Technology Pushkar Dave MS in Robotics, Northwestern University Rutu Shrirame Intern Analyst at Wells […]
- [Batch 2023](https://ivlabs.in/batch-2023/): Akshansh Malviya Program Associate at Wells Fargo, Hyderabad Amit Sawant Master’s student at Czech technical university Aneesh Shetye MS in Computer Engineering at NYU Diksha Bagade MS in Computer Science at NYU Ayush Singh Robotics Software Founding Engineer, Stealth Robotics Startup, Bengaluru Bipasha Parui Electronics and Communication​ Engineering Luqman Farooqui Technical Associate at GSK, Bengaluru Fauzan Farooqui Scientist (B) at CDOT (Centre for Development of Telematics) Kshitij Ambilduke MS in computer science at Université Paris Saclay, France Nachiket Sawwalakhe ASIC Digital Design, Sr Engineer at Synopsys Inc Karthik Raman MS in Robotics Engineering at WPI – Aug 2025 Muhammed Abdullah […]
- [Batch 2022](https://ivlabs.in/batch-2022/): Aadesh Varude MVP Robotics M.S. at Worcester Polytechnic Institute Khurshed Fitter M.S. Ecole Polytechnique Fédérale de Lausanne(EPFL) Rishika Bhagwatkar M.S. at Quebec Artificial Intelligence Institute Aadhithya Iyer At Fauna Robotics, Manhattan, New York M.S. at New York University Kushagra Srivastav ML Engineer at Burro, Philadelphia M.S. Worcester Polytechnic Institute Ritik Agrawal AI Engineer at Eudia, Palo Alto, California, M.S. at Duke University Aditya Shirwatkar At ATARI Labs, MIRMI, IISc, Bangalore (PhD Cyber Physical System) Prakrut Kotecha Research Assistant at IITH Hyderabad, IISc, Bangalore (PhD Cyber Physical System) Saketh Bachu ML Engineer at EvenUp, San Francisco, California, M.S. University of California, […]
- [Batch 2021](https://ivlabs.in/batch-2021/): Khush Agrawal WORKING AT BIOROBOTICS LAB CARNEGIE MELLON UNIVERSITY,USA Satyam Gupta GET MOBILE ROBOTICS ENGINEER ADDVERB,NOIDA Mohammad Saad GET – R&D VIRTUAL COMMISSIONING AND MOBILE ROBOTICS ADDVERB,NOIDA Rishesh Agarwal SDE-III @ Google, Bengaluru Rohit Lal Computer Scientist II @ NASA-IMPACTUniversity of California, Riverside, Masters in Electrical Engineering, Robotics and Computer Vision Specialization. Harshad Zade MS IN ROBOTICS SYSTEMS AND DEVELOPMENT AT CARNEGIE MELLON UNIVERSITY, USA Uddesh Tople ASSOCIATE ANALYST AT INFOCEPTS Amrapali Khandare EMBEDDED ENGINEER AT RIGHTBOT , BENGALURU Mayuresh Sarode SYSTEM ENGINEER AT TCS, PUNE Himanshu Patil UNDERGRADUATE ECE, INTERN AT NUS Sharan Bajjuri ASSOCIATE APPLICATIONS DEVELOPER AT ORACLE […]
- [Batch 2020](https://ivlabs.in/batch-2020/): Akshay Kulkarni PhD CS at UCSD, Prev. Sony R&D and VAL, IISc Aniket Gujarathi Robotic Assistance Devices M.S. University of Toronto (UTIAS) Unmesh Patil Motion planning Lucid Motors MS Robotic OregonState Aman Jain Multimodal Perception Engineer @Autonomous Driving at Qualcomm Navid Panchi Phd student at Institute for Multiscale Simulation (MSS) Rajeshree Deotalu Co-Founder & CTO | Building VECROS – Autonomy Powered Drones Yogesh Phalak Ph.D. Student at Virginia Tech Uav Devops Engineer @Octobotics Tech Lokesh Malke BFSI Consulting at The Digital Fifth MBA @ IIM Visakhapatnam
- [Batch 2019](https://ivlabs.in/batch-2019/): Kartik Paigwar ​Master Of Science – Robotics And Autonomous Systems Arizona State University Shubhanshu Gupta Masters In Aerospace Engineering At IIT Kanpur Gaurav Charpe Software EngineerHi-tech Robotic Systemz Ltd Rupali Garewal Technical ConsultantArtpark, Bengaluru R Sharath Chandra MSc StudentMila – Quebec Artificial Intelligence Institute Pranay Pourkar Hackerspace Intern Navstik Labs Sai Pothan Research InternSwaayatt Robots Anish Gupta Research Assistant IIIT Hyderabad Vikas Jha Firmware DeveloperSling Media Pvt. Ltd Vedant Ranade University Of Maryland Zeeshan Ul Islam Robotics Graduate StudentUniversity Of Pennsylvania Aditya Bastapure Research And Development AssociateDassault Systems Solutions Lab Disha Kamale ​PHD Student Lehigh University, Pennsylvania Anil Kota University […]


[comment]: # (Generated by Hostinger Tools Plugin)