Hi! I am Utkarsh Mishra. I am a dcotoral candidate in Robotics at Georgia Tech with Dr. Yongxin Chen from Summer 2022. I graduated from IIT Roorkee with a B. Tech. Mechanical Engineering in 2021. I have worked with Prof. Matthew E. Taylor at the Inverse Reinforcement Learning lab, University of Alberta and Prof. Shishir Kolathaya at the Stochastic Robotics lab, Indian Institute of Science. I am particularly interested in exploring self-supervised task representations and planning based supervision to achieve efficient robot learning and safe autonomy. Recently, I have finished my work on exploring accelerated hardware-in-loop reinforcement learning and locomotion in legged robots. Previously, I have collaborated with Prof. Auke Ijspeert and Dr. Dimitar Stanev at the Biorobotics Laboratory, EPFL.

Updates:
  • "Learning Representations for Control over Pixels: What Matters and Why." accepted by TMLR.
  • I am reviewing for NeurIPS 2022.
  • I am attending RLDM 2022 at Brown University, Providence and will be presenting an accepted poster.
  • I am attending ICRA 2022 in Philadelphia and will be presenting one of my two accepted publications.
  • I have joined the Ph.D. Robotics program with Dr. Yongxin Chen at Gerogia Tech.
Selected Articles

Learning Representations for Control over Pixels: What Matters and Why.
Manan Tomar*, Utkarsh A. Mishra*, Amy Zhang and Matthew E. Taylor.
Transactions in Machine Learning Research 2022.
Poster: Reinforcement Learning and Decision Making 2022.
Poster: Ecological RL workshop at NeurIPS 2021.
Website    Paper    Code    Video
Dynamic Mirror Descent based Model Predictive Control for Accelerating Robot Learning.
Utkarsh A. Mishra*, Soumya R. Samineni*, Prakhar Goel, Chandravaran Kunjeti, Himanshu Lodha, Aman Singh, Aditya Sagi, Shalabh Bhatnagar and Shishir Kolathaya.
ICRA 2022.
Poster: 2nd Offline RL workshop at NeurIPS 2021.
Poster: Deep RL Workshop at NeurIPS 2021.
Website    Paper    Code    Video
Linear Policies are Sufficient to Realize Robust Bipedal Walking on Challenging Terrains.
Lokesh Krishna*, Guillermo A. Castillo*, Utkarsh A. Mishra, Ayonga Hereid, Shishir Kolathaya
IEEE RAL + ICRA 2022.
Website    Paper    Code    Video
Learning Control Policies to Imitate Human Gaits.
Utkarsh A. Mishra, Dimitar Stanev, Auke J. Ijspeert, and Pushparaj M. Pathak.
Bachelor Thesis Report
Website    Paper    Code    Video
Learning Linear Policies for Robust Bipedal Locomotion on Terrains with Varying Slopes.
Lokesh Krishna, Utkarsh A. Mishra, Guillermo A. Castillo, Ayonga Hereid, Shishir Kolathaya
IROS 2021
Website    Paper    Code    Video
Forward Kinematics for Suspended Under-Actuated Cable-Driven Parallel Robots: A Neural Network Approach.
Utkarsh A. Mishra, Stéphane Caro
ASME Journal of Mechanism and Robotics
Special Issue: IDETC/CIE 2021 M&R Conference.
Website    Paper    Code    Video
Kinematic Stability based AFG-RRT* Path Planning for Cable-Driven Parallel Robots.
Utkarsh A. Mishra, Marceau Métillon, Stéphane Caro
ICRA 2021
Website    Paper    Code    Video





Last Updated: 20 Nov 2022
Coming soon..