Gautam Salhotra
Robotics & AI Research
I am robotics reseacher at Intrinsic, working with Stefan Schaal. Previously, I completed my PhD in computer science (robotics) at the University of Southern California (USC), advised by Gaurav Sukhatme. My thesis was on learning visuomotor manipulation skills for robotic arms, using the methods of learning from demonstration (LfD) and Reinforcement Learning (RL). I have applied this primarily to dexterous manipulation such as cloth manipulation and precision assembly tasks. More broadly, I have worked on combining planning algorithms with learning to achieve greater autonomy for robots, with experience in object manipulation, control theory, and learning.
- Dexterous Robot Manipulation
- Deformable Objects
- Learning from Demonstrations
- Reinforcement Learning
-
PhD in Computer Science (Robotics), 2024
University of Southern California
News
-
Aug 2025 I gave an invited research talk at Berkeley Lab.
-
May 2025 I gave an invited research talk about dexterous manipulation at the SIA Lab in Stanford University.
-
Apr 2025 I gave an invited research talk about dexterous manipulation at Arizona State University.
-
Aug 2024 I founded the RASC Robotics Blog at USC.
-
Jun 2024: I joined as a robotics researcher at Intrinsic LLC (Alphabet).
-
May 2024: Our multi-organization collaborative effort on the Open X-Embodiment dataset and the RT-X family of models has been awarded the Best Conference Paper at ICRA 2024.
-
Dec 2023: I defended my PhD thesis.
-
Aug 2023: Our paper on cross-embodied learning for deformable object manipulation has been accepted to CoRL 2023! See you in Atlanta!
-
Feb 2023: I started the USC Robotics Seminar (URoS) along with Prof. Somil Bansal, for robotics researchers to present and discuss their work at USC.
Selected Publications
See Google Scholar for a full list