LANCAR: Leveraging Language for Context-Aware Robot Locomotion in Unstructured Environments

TL;DR

LANCAR introduces a novel approach combining large language models with reinforcement learning to enable robots to interpret human language context for improved navigation in unstructured terrains, demonstrating superior adaptability and reward gains.

Contribution

This work presents a new framework that integrates language-based context understanding with RL for robot locomotion, addressing ambiguity in human language and improving navigation performance.

Findings

7.4% increase in episodic reward over alternatives

Enhanced generalizability across terrains

Effective interpretation of ambiguous human language

Abstract

Navigating robots through unstructured terrains is challenging, primarily due to the dynamic environmental changes. While humans adeptly navigate such terrains by using context from their observations, creating a similar context-aware navigation system for robots is difficult. The essence of the issue lies in the acquisition and interpretation of context information, a task complicated by the inherent ambiguity of human language. In this work, we introduce LANCAR, which addresses this issue by combining a context translator with reinforcement learning (RL) agents for context-aware locomotion. LANCAR allows robots to comprehend context information through Large Language Models (LLMs) sourced from human observers and convert this information into actionable context embeddings. These embeddings, combined with the robot's sensor data, provide a complete input for the RL agent's policy network. We provide an extensive evaluation of LANCAR under different levels of context ambiguity and compare with alternative methods. The experimental results showcase the superior generalizability and adaptability across different terrains. Notably, LANCAR shows at least a 7.4% increase in episodic reward over the best alternatives, highlighting its potential to enhance robotic navigation in unstructured environments. More details and experiment videos could be found in http://raaslab.org/projects/LLM_Context_Estimation/