Embedded Files
- Abhik Singla*, Shounak Bhattarchya, Dhaivat Dholakia, Shalabh Bhatnagar, Ashitava Ghosal, Bhardwaj Amrutur and Shishir Kolathaya. "Realizing Learned Quadruped Locomotion Behaviors through Kinematic Motion Primitives", Accepted for presentation in IEEE International Conference of Robotics and Automation (ICRA), 2019. [Link]
- Shounak Bhattacharya, Abhik Singla*, Abhimanyu, Dhaivat Dholakiya, Shalabh Bhatnagar, Bharadwaj Amrutur, Ashitava Ghosal, Shishir Kolathaya. "Learning Active Spine Behaviors for Dynamic and Efficient Locomotion in Quadruped Robots". Accepted for presentation in IEEE International Conference on Robot & Human Interactive Communication (Ro-Man) 2019. [Link]
- Shishir Kolathaya, Ashish Joglekar, Suhan Shetty, Dhaivat Dholakiya, Abhimanyu, Aditya Sagi,Shounak Bhattacharya, Abhik Singla*, Shalabh Bhatnagar, Ashitava Ghosal, Bharadwaj Amrutur. "Trajectory based Deep Policy Search for Quadrupedal Walking". Accepted for presentation in IEEE International Conference on Robot & Human Interactive Communication (Ro-Man) 2019. [Link]
- Dhaivat Dholakiya, Shounak Bhattacharya, Ajay Gunalan, Abhik Singla*, Shalabh Bhatnagar, Bharadwaj Amrutur, Ashitava Ghosal, Shishir Kolathaya. "Design, Development and Experimental Realization of a Quadrupedal Research Platform: Stoch", Accepted in IEEE International Conference on Control, Automation and Robotics (ICCAR), April 2019, China. [Link]
- Economic Times' media coverage [Link]
Snapshot of the Quadruped
My current research revolves around learning robust locomotion behavior for an in-house built, small-sized Quadruped with 18-dof using Deep Reinforcement Learning. Classical approaches for locomotion control requires complete dynamic and kinematic model of the robot. Based on these models, an expert designs the end-point trajectory to be executed, with tedious fine-tuning. These mathematical models however, fail to utilize the robot's capabilities and fail to provide adaptive and robust control.
Deep Reinforcement Learning (Deep-RL) techniques automate the process and enable the quadruped to explore in it's action space and learn to walk from scratch based on the scalar signals. Deep-RL however, has its own challenges like sample inefficiency.
Dealing with these challenges, my aim is to design an efficient and robust controller that learns to walk. I have built a physics-based simulator to train the robot model. In addition to it, I am working on the methodologies to effectively transfer the learning from a simulation environment to the real hardware.
The hardware is designed and manufactured in-house by Dhaivat Dholakia and Shounak Bhattacharya (IISc).
Updates:
Updates:
ICRA 19 accepted video
ICRA 19 accepted video
Demonstration of learnt trajectories on physical robot
Demonstration of learnt trajectories on physical robot
Timelapse v6.mp4A fun video of Quadruped's assembly
A fun video of Quadruped's assembly
Google Sites
Report abuse