🚀🔬 Research Experience 📈🧪
🎓👨🔬Graduate Assitant
Jan’23 - Present
AI4CE Lab, New York University
Supervisor: Dr. Chen Feng, NYU
- Proposed a spatiotemporal backbone to harness the sequential information for Visual Place Recognition(VPR)
- Implementing self-attention and cross-attention mechanisms to enable the model to focus on the most relevant regions in each frame and across the sequence
- Evaluating different network configurations on benchmark VPR datasets to quantify accuracy gains compared to baseline approaches in Pytorch
🛠️Research Intern
Feb’21 - June’21
Formal Control and Autonomous Systems(FOCAS) Lab
Robert-Bosch Centre for Cyber-Physical Systems (RBCCPS)
Indian Institute of Science (IISc), Bangalore
Supervisor: Dr. Pushpak Jagtap, IISc, Bangalore
- Led the setup and calibration of PhaseSpace Motion Capture System and developed ROS support for integrating the system with Turtlebot3 robots
- Deployed Turtlebot3 robots with differential and mecanum drive configurations and utilized motion capture for accurate robot position tracking and real-time control adjustments
- Implemented a Control Lyapunov Function (CLF) based controller in Python to guide unicycle modeled agents (robots) to desired poses
- Implemented a barrier certificate-based collision avoidance algorithm for multi-agent systems using ROS(Python)
- Achieved a 30cm safety radius in a 6m x 5m arena
(Video 1) (Video 2)
🛠️Research Intern
Robotics Innovations Lab(RIL), Indian Institute of Science, Bangalore
Jul’21 – Dec’21
Supervisor: Dr. Abhra Roy Chowdhury, Indian Institute of Science
- Constructed a differential drive rover robot platform with DC motors, encoders, microcontroller, and forklift
- Developed models and control programs in MATLAB to enable autonomous navigation:
- Characterized gear motor response through PWM speed sweeps and data analysis
- Implemented differential drive kinematics for low-level control of driving and arm motions
- Derived and simulated kinematic and dynamic models of rover motion and used for open loop control
- Designed and tuned a PID controller with wheel encoder feedback for precise closed loop position and heading control
- Added webcam and localization algorithms to determine rover location within the test arena
- Integrated navigation and vision systems for high-level arena navigation and object manipulation tasks
- Enhanced autonomy with line following and obstacle avoidance behaviors
- This advanced robotic system incorporated mechanical design, modeling, control theory, computer vision, PID control, path planning, and autonomous decision-making
- Demonstrated expertise in mechatronics, autonomous robotics, and advanced control algorithms
(Project Report) (Project Video)