How can a robot learn to use its different parts for interactions?
How can we go beyond proprioception for robust mobile manipulation?
What abstractions are necessary to describe multiple tasks?

To find some answers to the above questions, I am currently a PhD student at ETH Zurich advised by Marco Hutter, and a Research Scientist at NVIDIA Research.

Over the span of my career, I have had the opportunity to work with some amazing robotic groups on many different robotic platforms. I have been a visiting student researcher at Vector Institute, a research intern at NNAISENSE, and a part-time research engineer at ETH Zurich. During my undergrad at IIT Kanpur, I was a visiting student at University of Freiburg, Germany, working closely with Abhinav Valada and Wolfram Burgard. I also founded the AUV-IITK team, where I worked on different hardware and software aspects of building an autonomous underwater vehicle.

If you have questions or would like to discuss ideas, feel free to reach out through email!

news

Oct 18, 2024 Our paper on ‘Guided Reinforcement Learning for Robust Multi-Contact Loco-Manipulation’ is accepted for an oral presentation at CoRL 2024 :tada:
Sep 6, 2024 Our paper on ‘Perceptive Pedipulation with Local Collision Avoidance’ is accepted to ICHR 2024
Jun 24, 2024 Gave a talk at the IWIALS 2024 on Isaac Lab and learning robust legged mobile manipulation
Jun 15, 2024 Gave a talk at the RSS Workshop on Data Generation for Robotics on how simulation-based scaling can aid in learning robust skills
Jun 3, 2024 Our work on Orbit has evolved into Isaac Lab, which is now officially supported by NVIDIA. A huge thank to the team and collaborators to make this possible!

some publications

  1. Guided Reinforcement Learning for Robust Multi-Contact Loco-Manipulation Jean-Pierre Sleiman*, Mayank Mittal*, and Marco Hutter CoRL 2024 [Abs] [arXiv] [Website]
  2. Perceptive Pedipulation with Local Obstacle Avoidance Jonas Stolle, Philip Arm, Mayank Mittal, and Marco Hutter ICHR 2024 [Abs] [arXiv] [Website]
  3. Symmetry Considerations for Learning Task Symmetric Robot Policies Mayank Mittal*, Nikita Rudin*, Victor Klemm, Arthur Allshire, and Marco Hutter ICRA 2024 [Abs] [arXiv]
  4. Pedipulate: Enabling Manipulation Skills using a Quadruped Robot’s Leg Philip Arm, Mayank Mittal, Hendrik Kolvenbach, and Marco Hutter ICRA 2024 [Abs] [arXiv] [Video] [Website]
  1. ORBIT: A Unified Simulation Framework for Interactive Robot Learning Environments Mayank Mittal, Calvin Yu, Qinxi Yu, Jingzhou Liu, Nikita Rudin, David Hoeller, and others IEEE RA-L 2023 [Abs] [arXiv] [Website] [Code]
  1. A Collision-Free MPC for Whole-Body Dynamic Locomotion and Manipulation Jia-Ruei Chiu, Jean-Pierre Sleiman, Mayank Mittal, Farbod Farshidian, and Marco Hutter ICRA 2022 [Abs] [arXiv] [Video]
  2. Articulated Object Interaction in Unknown Scenes with Whole-Body Mobile Manipulation Mayank Mittal, David Hoeller, Farbod Farshidian, Marco Hutter, and Animesh Garg IROS 2022 [Abs] [arXiv] [Website]