GenCHiP: Generating Robot Policy Code for High-Precision and Contact-Rich Manipulation Tasks
This addresses the challenge of enabling LLMs to handle precise and contact-sensitive robotic tasks, which is incremental as it builds on existing LLM-based policy generation methods.
The paper tackled the problem of generating robot policy code for high-precision and contact-rich manipulation tasks using LLMs, achieving over 3x and 4x improvement in policy generation compared to non-compliant action spaces by reparameterizing the action space to include compliance with force and stiffness constraints.
Large Language Models (LLMs) have been successful at generating robot policy code, but so far these results have been limited to high-level tasks that do not require precise movement. It is an open question how well such approaches work for tasks that require reasoning over contact forces and working within tight success tolerances. We find that, with the right action space, LLMs are capable of successfully generating policies for a variety of contact-rich and high-precision manipulation tasks, even under noisy conditions, such as perceptual errors or grasping inaccuracies. Specifically, we reparameterize the action space to include compliance with constraints on the interaction forces and stiffnesses involved in reaching a target pose. We validate this approach on subtasks derived from the Functional Manipulation Benchmark (FMB) and NIST Task Board Benchmarks. Exposing this action space alongside methods for estimating object poses improves policy generation with an LLM by greater than 3x and 4x when compared to non-compliant action spaces