Shivam Vats

Robotics Institute, Carnegie Mellon University.

profile_pic.jpeg

I am a final year robotics PhD candidate at CMU co-advised by Prof. Maxim Likhachev and Prof. Oliver Kroemer. My research is focused on leveraging planning for efficiency in robot learning. In my work, I have come up with algorithms that tell a robot what to learn so that it makes the best use of the available resources. This is important in human-robot collaboration and contact-rich manipulation tasks where acquiring data involves bothering a human or querying a slow simulator. I am currently looking at ways to use planners for guidance in hard reinforcement learning tasks.

More broadly, I am excited by problems that involve both planning and learning, for example, planning with learned models and using learning to speed up planning.

I am grateful for coverage of my work by ASME, CMU News and ACM among other news platforms.

Note: I am actively searching for full-time research and postdoc positions in robotics. Feel free to reach out at svats[at]cs.cmu.edu.

Before joining CMU, I studied maths and computing at Indian Institute of Technology (IIT) Kharagpur where I worked with Prof. P.P. Chakrabarti and Prof. Bibhas Adhikari on heuristic search and simplicial complexes. I was a core developer of SymPy and an active contributor to SymEngine for many years. I also regularly participated in the Intelligent Ground Vehicle Competition as a member of the Autonomous Ground Vehicle Group.

news

Feb 23, 2024 Invited talk on Planning What to Learn at the Georgia Tech RoboGrads Seminar (slides).
Nov 5, 2023 Presented SCALE at CoRL, 2023 in Atlanta.
Nov 4, 2022 Invited talk at Prof. George Konidaris’ group at Brown.
Nov 1, 2022 Invited talk at Prof. Lerrel Pinto’s group at NYU.
May 27, 2022 I was a finalist for the outstanding HRI paper award in ICRA.

selected publications

  1. 2023_icra.jpeg
    Efficient Recovery Learning using Model Predictive Meta-Reasoning
    Shivam Vats, Maxim Likhachev, and Oliver Kroemer
    In 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023
  2. 2022_icra_adl.png
    Synergistic scheduling of learning and allocation of tasks in human-robot teams
    Shivam Vats, Oliver Kroemer, and Maxim Likhachev
    In 2022 International Conference on Robotics and Automation (ICRA), 2022
    Finalist for the Outstanding Paper Award in Human-Robot Interaction
  3. 2017_peerj.png
    SymPy: symbolic computing in Python
    Aaron Meurer, and  others
    PeerJ Computer Science, 2017