Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments

2024-07-14

arXiv.org

AI Summary

Existing long-horizon task planning for partially observable multi-robot environments suffers from insufficient robustness, while current large language models (LLMs) lack support for online adaptation and self-correction. Method: We propose LLaMAR, a cognitive architecture built upon a plan-act-correct-verify closed-loop framework that enables simulator-free, oracle-free online dynamic planning and execution correction. Contribution/Results: We introduce MAP-THOR—the first benchmark for multi-agent long-horizon tasks—integrating LLM-based reasoning, multi-agent collaborative planning, and execution-feedback-driven dynamic correction within the AI2-THOR environment. Evaluated on MAP-THOR and real-world search-and-rescue scenarios, our approach achieves a 30% higher task success rate than state-of-the-art LLM-based methods, significantly improving robustness under partial observability and cross-task generalization capability.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Multiagent Planning
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

The ability of Language Models (LMs) to understand natural language makes them a powerful tool for parsing human instructions into task plans for autonomous robots. Unlike traditional planning methods that rely on domain-specific knowledge and handcrafted rules, LMs generalize from diverse data and adapt to various tasks with minimal tuning, acting as a compressed knowledge base. However, LMs in their standard form face challenges with long-horizon tasks, particularly in partially observable multi-agent settings. We propose an LM-based Long-Horizon Planner for Multi-Agent Robotics (LLaMAR), a cognitive architecture for planning that achieves state-of-the-art results in long-horizon tasks within partially observable environments. LLaMAR employs a plan-act-correct-verify framework, allowing self-correction from action execution feedback without relying on oracles or simulators. Additionally, we present MAP-THOR, a comprehensive test suite encompassing household tasks of varying complexity within the AI2-THOR environment. Experiments show that LLaMAR achieves a 30% higher success rate than other state-of-the-art LM-based multi-agent planners in MAP-THOR and Search &Rescue tasks. Code can be found at https://github.com/nsidn98/LLaMAR

Problem

• Long-term planning
• Adaptive adjustment
• Multi-robot collaboration

Innovation

• LLaMAR
• Long-term Planning
• Multi-Robot Collaboration