Path Planning Using Instruction-Guided Probabilistic Roadmaps

This work presents a novel data-driven path planning algorithm named Instruction-Guided Probabilistic Roadmap (IG-PRM). Despite the recent development and widespread use of mobile robot navigation, the safe and effective travels of mobile robots still require significant engineering effort to take into account the constraints of robots and their tasks. With IG-PRM, we aim to address this problem by allowing robot operators to specify such constraints through natural language instructions, such as “aim for wider paths” or “mind small gaps”. The key idea is to convert such instructions into embedding vectors using large-language models (LLMs) and use the vectors as a condition to predict instruction-guided cost maps from occupancy maps. By constructing a roadmap based on the predicted costs, we can find instruction-guided paths via the standard shortest path search. Experimental results demonstrate the effectiveness of our approach on both synthetic and real-world indoor navigation environments.

Authors

• Jiaqi Bao
• Ryo Yonetani

Keywords

• Costs
• Natural languages
• Predictive models
• Probabilistic logic
• Prediction algorithms
• Vectors
• Path planning
• Planning
• Mobile robots
• Standards
• Natural Language
• Cost Function
• Shortest Path
• Real-world Environments
• Mobile Robot
• Embedding Vectors
• Robot Operating
• Robot Navigation
• Standard Search
• Path Search
• Navigation In Environments
• Occupancy Map
• Indoor Navigation
• Synthetic Environment
• Neural Network
• State Space
• Free Space
• Language Model
• Rapidly-exploring Random Tree
• Wheeled Robot
• Problem Instances
• Feasible Path
• Robot Operating System
• Continuous State Space
• Retail Stores
• Goal Position
• Solution Path
• Node Samples