• Trained End-to-end model for short term collsion free navigaiton in dynamic environemnts using deep reinforcement learning
• Used domain randomization to learn robust control strategies
• Open sourced gazebo based training environment with complete codebase and pretrained models.
• Implemented robust perception system by combining classical computer vision techniques with deep learning using kalman filtering
• Developed end-to-end motion planning models using pure control systems as well as learning based techniques
• Currently experimenting Reinforcement Learning techniques in the Carla simulator
• Developed a deep learning library from Scratch in Python.
• Intuitive API similar to pytorch.
• Designed and fabricated 4 dof Aluminium Robotics arm. Interfaced to ROS Moveit to implement Inverse Kinematics
• Interfaced to ROS Moveit to implement Inverse Kinematics.