DELTA: Decomposed Efficient Long-Term Robot Task Planning using Large Language Models

2024-04-04

arXiv.org

AI Summary

To address hallucination, low plan feasibility, and poor computational efficiency of large language models (LLMs) in long-horizon robotic task planning, this paper proposes an LLM-coordinated planning framework grounded in scene graph representation and autoregressive goal decomposition. Our approach features three key contributions: (1) novel integration of structured scene graphs into LLM prompts to enhance domain awareness and action constraint modeling; (2) hierarchical, executable subgoal decomposition of high-level goals via LLMs; and (3) end-to-end collaboration with classical planners (e.g., FF, Fast Downward) to jointly leverage semantic understanding and symbolic reasoning. Evaluated on multi-scenario long-horizon task benchmarks, our method achieves significantly higher planning success rates than state-of-the-art approaches while reducing average planning time by 62%. The resulting pipeline delivers fully automated, highly feasible, and low-latency robotic task planning.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Motion and Path Planning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Recent advancements in Large Language Models (LLMs) have sparked a revolution across many research fields. In robotics, the integration of common-sense knowledge from LLMs into task and motion planning has drastically advanced the field by unlocking unprecedented levels of context awareness. Despite their vast collection of knowledge, large language models may generate infeasible plans due to hallucinations or missing domain information. To address these challenges and improve plan feasibility and computational efficiency, we introduce DELTA, a novel LLM-informed task planning approach. By using scene graphs as environment representations within LLMs, DELTA achieves rapid generation of precise planning problem descriptions. To enhance planning performance, DELTA decomposes long-term task goals with LLMs into an autoregressive sequence of sub-goals, enabling automated task planners to efficiently solve complex problems. In our extensive evaluation, we show that DELTA enables an efficient and fully automatic task planning pipeline, achieving higher planning success rates and significantly shorter planning times compared to the state of the art. Project webpage: https://delta-llm.github.io/

Problem

• Improve robot task plan feasibility using LLMs
• Enhance computational efficiency in long-term planning
• Automate decomposition of complex goals into sub-goals

Innovation

• Uses scene graphs for environment representation
• Decomposes goals into autoregressive sub-goals
• Enhances planning success and reduces time