Bridging Semantics and Physics with Constrained LLMs for Safe and Trustworthy Robotic Manipulation

2026-08-29

AI Summary

研究通过约束大语言模型和物理验证，解决机器人在复杂环境中安全执行任务的问题，提高操作成功率。

Abstract

A language-guided robot operating in a real kitchen must do more than produce a plan that appears correct. It must also execute that plan safely in cluttered environments under imperfect perception. Large language models (LLM) can decompose instructions into action sequences, yet a language-action gap remains: a plan may appear valid linguistically while being physically infeasible under kinematic and collision constraints. We bridge this gap by formalizing the reasoning-execution boundary as a typed contract. From RGB-D observations, the system grounds perceived objects in an explicit, collision-aware scene model and constrains language-level decisions through schema-validated tool calls defined by the Model Context Protocol (MCP), rejecting malformed commands before they reach the robot. Each validated call is deterministically grounded in a MoveIt Task Constructor pipeline, where candidate motions are evaluated against the reconstructed planning scene in a verify-then-act step. Only trajectories that pass both kinematic and collision checks are sent to the robot. On a physical UFactory 850, the method achieves up to 80% success across ten trials per task on pouring tasks involving liquids, granular media, and discrete solids. It achieves 90% success on a grasp-and-place task using the same planning, protocol, and verification stack. Although a scripted policy slightly outperforms our method on the easiest task, its success rate falls to 10% on the hardest, compared with 60% for our method.

Problem

• language-guided robot
• real kitchen environment
• large language models (LLM)
• physical constraints
• safety

Innovation

• typed contract
• collision-aware scene model
• Model Context Protocol (MCP)
• verify-then-act