3P-LLM: Probabilistic Path Planning using Large Language Model for Autonomous Robot Navigation
Ehsan Latif
TL;DR
This work investigates using GPT-3.5-turbo to perform probabilistic path planning for autonomous robots by translating planning problems into natural language and grounding actions back to motion. It introduces a probabilistic framework separating task-grounding and world-grounding and demonstrates a GPT-3.5-turbo–driven route-planning pipeline, tested in Gazebo with ROS, Lidar, and GMapping. Compared to A* and RRT, the LLM-based approach achieves significantly lower processing times but at the cost of lower path accuracy and longer path lengths, suggesting a viable real-time option that could be enhanced via hybridization with classical planners. The study highlights the potential of LLMs to enable real-time, adaptable navigation while underscoring the need for improvements in accuracy and optimality for robust deployment in dynamic environments.
Abstract
Much worldly semantic knowledge can be encoded in large language models (LLMs). Such information could be of great use to robots that want to carry out high-level, temporally extended commands stated in natural language. However, the lack of real-world experience that language models have is a key limitation that makes it challenging to use them for decision-making inside a particular embodiment. This research assesses the feasibility of using LLM (GPT-3.5-turbo chatbot by OpenAI) for robotic path planning. The shortcomings of conventional approaches to managing complex environments and developing trustworthy plans for shifting environmental conditions serve as the driving force behind the research. Due to the sophisticated natural language processing abilities of LLM, the capacity to provide effective and adaptive path-planning algorithms in real-time, great accuracy, and few-shot learning capabilities, GPT-3.5-turbo is well suited for path planning in robotics. In numerous simulated scenarios, the research compares the performance of GPT-3.5-turbo with that of state-of-the-art path planners like Rapidly Exploring Random Tree (RRT) and A*. We observed that GPT-3.5-turbo is able to provide real-time path planning feedback to the robot and outperforms its counterparts. This paper establishes the foundation for LLM-powered path planning for robotic systems.