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

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 this link.

Authors

• Chak Lam Shek
• Xiyang Wu
• Wesley A. Suttle
• Carl E. Busart
• Erin G. Zaroukian
• Dinesh Manocha
• Pratap Tokekar
• Amrit Singh Bedi

Keywords

• Visualization
• Translation
• Navigation
• Foundation models
• Reinforcement learning
• Observers
• Robot sensing systems
• Robustness
• Robots
• Videos
• Unstructured Environments
• Contextual Information
• Language Model
• Human Observers
• Interpretation Of Information
• Human Language
• Robot Navigation
• Reinforcement Learning Agent
• Navigation In Environments
• Ambiguous Language
• Contextual Embedding
• Dynamic Environmental Changes
• Decision-making Process
• Natural Language
• Environmental Context
• Environmental Dimensions
• Qualitative Description
• Reward Function
• Robot Control
• Domain Adaptation
• Proximal Policy Optimization
• Human-robot Collaboration
• High Damping
• One-hot Vector
• Universal Policy
• Low Friction
• High-level Tasks
• Navigation Task
• High Reward
• Human Interpretation