DynaCon: Dynamic Robot Planner with Contextual Awareness via LLMs
Gyeongmin Kim¹†, Taehyeon Kim²†, Shyam Sundar Kannan², Vishnunandan L. N. Venkatesh²,
Donghan Kim³ and Byung-Cheol Min²
¹SungKyunKwan University, ²Purdue University, ³Kyung Hee University
†Equal contribution
Abstract
Mobile robots often rely on pre-existing maps for effective path planning and navigation. However, when these maps are unavailable, particularly in unfamiliar environments, a different approach become essential. This paper introduces DynaCon, a novel system designed to provide mobile robots with contextual awareness and dynamic adaptability during navigation, eliminating the reliance of traditional maps. DynaCon integrates real-time feedback with an object server, prompt engineering, and navigation modules. By harnessing the capabilities of Large Language Models (LLMs), DynaCon not only understands patterns within given numeric series but also excels at categorizing objects into matched spaces. This facilitates dynamic path planner imbued with contextual awareness. We validated the effectiveness of DynaCon through an experiment where a robot successfully navigated to its goal using reasoning.
Framework of DynaCon
Within the subsections of real-time feedback, prompt engineering, and navigation task, DynaCon processes task inputs, recognizes objects from the environment in real-time, and performs navigation towards the desired object by reasoning based on designed prompts. In the real-time feedback section, the Object Server periodically retrieves information about nearby objects and the current position of the robot to update the object list. In the prompt engineering phase, a uniquely structured prompt is sent to the Large Language Model (LLM) to output the desired object, serving as the main task of navigation. Finally, the ROS move base applied for navigation.
DynaCon's Prompt Structure
The red box represents the role component, the blue represents the main task, and orange box signifies the instruction for limiting the reasoning boundary.
(a)-(d) describe specific constraints:
(a) Illustrates the format of the received object list
(b) Denotes the real-time situation
(c) Outlines the prerequisites and desired output format for objects
(d) Provides scenario examples for the reasoning process
Prompt Engineering Evaluation
Experimental Setup and Video
