InteLiPlan: Interactive Lightweight LLM-Based Planner for Domestic Robot Autonomy

2024-09-22

arXiv.org

AI Summary

To address the low autonomy, poor robustness, heavy reliance on large-scale datasets, and limited cross-platform generalizability of domestic robots in dynamic environments, this paper proposes a robot-agnostic, lightweight, LLM-driven interactive planning framework. Methodologically, it integrates embodied intelligence alignment, kinematic constraint modeling, and human-in-the-loop closed-loop feedback control to enable real-time onboard inference and human-assisted recovery. An efficient fine-tuning strategy is employed, and the framework is jointly validated in simulation and on the physical Toyota HSR platform. Experiments on “fetch me” tasks achieve a 93% success rate—significantly outperforming baselines and matching the performance of large-model-based approaches—while satisfying real-time latency requirements. The core contribution is the first lightweight, deployable, human-robot collaborative, and cross-robot-platform LLM-based planning pipeline tailored for embodied intelligence.

Technology Category

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

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

We introduce a lightweight LLM-based framework designed to enhance the autonomy and robustness of domestic robots, targeting onboard embodied intelligence. By addressing challenges such as kinematic constraints and dynamic environments, our approach reduces reliance on large-scale data and incorporates a robot-agnostic pipeline. Our framework, InteLiPlan, ensures that the LLM model's decision-making capabilities are effectively aligned with robotic functions, enhancing operational robustness and adaptability, while our human-in-the-loop mechanism allows for real-time human intervention in the case where the system fails. We evaluate our method in both simulation and on the real Toyota HSR robot. The results show that our method achieves a 93% success rate in the fetch me task completion with system failure recovery, outperforming the baseline method in a domestic environment. InteLiPlan achieves comparable performance to the state-of-the-art large-scale LLM-based robotics planner, while guaranteeing real-time onboard computing with embodied intelligence.

Problem

• Enhance domestic robot autonomy and robustness
• Reduce reliance on large-scale data for planning
• Enable real-time human intervention in robot tasks

Innovation

• LLM-based framework enhances robot autonomy
• Robot-agnostic pipeline reduces data reliance
• Human-in-the-loop enables real-time intervention