7 papers
Any-Body Guard: Universal Safeguarding for Manipulation Policies via Action Masking
Alex Beaudin, Hanna Krasowski, Kartik Nagpal +3
Ensuring safety of learning-enabled robotic manipulation across diverse embodiments and tasks still requires significant manual engineering. Existing approaches typically rely on h…
Learning Control Policies to Provably Satisfy Hard Affine Constraints for Black-Box Hybrid Dynamical Systems
Aayushi Shrivastava, Kartik Nagpal, Sairam Jinkala +2
Ensuring safety for black-box hybrid dynamical systems presents significant challenges due to their instantaneous state jumps and unknown explicit nonlinear dynamics. Existing solu…
DDAT: Diffusion Policies Enforcing Dynamically Admissible Robot Trajectories
Jean-Baptiste Bouvier, Kanghyun Ryu, Kartik Nagpal +3
Diffusion models excel at creating images and videos thanks to their multimodal generative capabilities. These same capabilities have made diffusion models increasingly popular in…
Leveraging Large Language Models for Effective and Explainable Multi-Agent Credit Assignment
Kartik Nagpal, Dayi Dong, Jean-Baptiste Bouvier +1
Recent work, spanning from autonomous vehicle coordination to in-space assembly, has shown the importance of learning collaborative behavior for enabling robots to achieve shared g…
Optimal Robotic Assembly Sequence Planning: A Sequential Decision-Making Approach
Kartik Nagpal, Negar Mehr
The optimal robot assembly planning problem is challenging due to the necessity of finding the optimal solution amongst an exponentially vast number of possible plans, all while sa…
POLICEd RL: Learning Closed-Loop Robot Control Policies with Provable Satisfaction of Hard Constraints
Jean-Baptiste Bouvier, Kartik Nagpal, Negar Mehr
In this paper, we seek to learn a robot policy guaranteed to satisfy state constraints. To encourage constraint satisfaction, existing RL algorithms typically rely on Constrained M…