Trust the PRoC3S: Solving Long-Horizon Robotics Problems with LLMs and Constraint Satisfaction

TL;DR

This paper introduces PRoC3S, a method that leverages large language models to generate and solve continuous constraint satisfaction problems for complex robotic manipulation tasks, improving efficiency and effectiveness over existing methods.

Contribution

The paper presents a novel approach combining LLMs with constraint satisfaction techniques to handle continuous parameters and constraints in robotics planning.

Findings

PRoC3S effectively solves complex manipulation tasks with constraints.

The approach outperforms existing baselines in simulated domains.

Re-prompting LLMs helps address unsatisfiable constraint problems.

Abstract

Recent developments in pretrained large language models (LLMs) applied to robotics have demonstrated their capacity for sequencing a set of discrete skills to achieve open-ended goals in simple robotic tasks. In this paper, we examine the topic of LLM planning for a set of continuously parameterized skills whose execution must avoid violations of a set of kinematic, geometric, and physical constraints. We prompt the LLM to output code for a function with open parameters, which, together with environmental constraints, can be viewed as a Continuous Constraint Satisfaction Problem (CCSP). This CCSP can be solved through sampling or optimization to find a skill sequence and continuous parameter settings that achieve the goal while avoiding constraint violations. Additionally, we consider cases where the LLM proposes unsatisfiable CCSPs, such as those that are kinematically infeasible, dynamically unstable, or lead to collisions, and re-prompt the LLM to form a new CCSP accordingly. Experiments across three different simulated 3D domains demonstrate that our proposed strategy, PRoC3S, is capable of solving a wide range of complex manipulation tasks with realistic constraints on continuous parameters much more efficiently and effectively than existing baselines.