We are a team of legged robot enthusiasts based out of Indian Institute of Science, Bengaluru. We are mainly interested in advanced mobility in extremely challenging terrains. The team consists of technical staff members, students, interns and faculty with varying backgrounds and interests.
News
-
January 26, 2023
Our recent work titled “Force control for Robust Quadruped Locomotion: A Linear Policy Approach” has been accepted to 2023 IEEE International Conference on Robotics and Automation (ICRA), London, UK. (ICRA 2023).
-
January 20, 2022
Our recent work titled “Dynamic Mirror Descent MPC for Model-based Model-free Reinforcement Learning” has been accepted to 2022 IEEE International Conference on Robotics and Automation (ICRA), Philadelphia (PA), USA. (ICRA 2022).
-
January 15, 2022
Our recent work titled “Learning Controllers for Robust Bipedal Locomotion on Challenging Terrains” has been accepted to 2022 IEEE International Conference on Robotics and Automation (ICRA), Philadelphia (PA), USA. (ICRA 2022).
-
June 30, 2021
Our recent work titled “Learning Linear Policies for Robust Bipedal Locomotion on Terrains with Varying Slopes” has been accepted to 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems, Prague, Czech Republic. (IROS 2021).
Research
Off-Policy Average Reward Actor-Critic with Deterministic Policy Search
Policy gradient theorem for average reward criteria with deterministic policy.
Dridh Bipedal Robot
Design, development and experimental realisation of a Bipedal Robot research platform: Dridh
Collision Cone Control Barrier Functions (C3BF)
Control Barrier Functions for Kinematic Obstacle Avoidance :A Collision Cone Approach
Force control for Robust Quadruped Locomotion: A Linear Policy Approach
A framework for designing controllers to achieve robust blind quadrupedal walking using force control thorugh learnt linear policies.
Dynamic Mirror Descent MPC for Model-based Model-free Reinforcement Learning
A framework for utilizing experience for generating predictive simulations and learning from them.
Learning Controllers for Robust Bipedal Locomotion on Challenging Terrains
A framework for sythesizing controllers to achieve blind bipedal walking on challenging terrains thorugh learnt linear policies.
Robust Quadrupedal Locomotion on Sloped Terrains
This paper presents a linear policy approach to achieve walking on sloped terrains
Stoch 1
A complete description of the hardware design and control architecture of our custom built quadruped robot, called the Stoch
Active Spine on Stoch 2
Learning Active Spine Behaviors for Dynamic and Efficient Locomotion
Trajectory Optimization on Stoch 2
Trajectory based Deep Policy Search for Quadrupedal Walking
Augmented Random Search (RL Algorithm)
Reinforcement Learning using ARS (Augmented random Search)to generate Gaits
People
Faculty
Shishir Kolathaya (HEAD)
Bharadwaj Amrutur
Shalabh Bhatnagar
Ashitava Ghosal
Staff
Srihari Vemuru
Darshit Darji
Vishnu Joshi
Mohit Javale
Karthik Garg
Ketan Nehete
Karthik Rajgopal
Vedvyas Danturi
Naman Saxena
Abhishek Ranjan
Nithin Vasishta
Ravi Kola
PhD Students
Manan Tayal
Vamshi Kumar Kurva
Aditya Shirwatkar
Pramod Pal
