Safe and Trustworthy Robot Pathfinding with BIM, MHA*, and NLP

2024-11-22

AI Summary

To address the high computational overhead of SLAM, low real-time obstacle avoidance accuracy, and insufficient safety for robots operating in dynamic and complex construction sites, this paper proposes a BIM-driven Multi-Heuristic A* (MHA*) path planning framework. The method tightly integrates BIM-derived spatial semantic information with real-time sensor data, innovatively couples an Artificial Potential Field (APF) module for responsive dynamic obstacle handling, and leverages a Large Language Model (LLM) to parse BIM-associated textual instructions—enabling semantic-aware autonomous decision-making. Experimental results demonstrate an 80% increase in the average robot–obstacle distance, with no statistically significant increase in path length. Thus, task efficiency is preserved while collision risk is substantially reduced, significantly enhancing environmental adaptability, operational safety, and mission reliability of construction robots.

Technology Category

Intelligent Robots: Motion and Path PlanningPlanning, Routing, and Scheduling: Planning with Language ModelsHumans and AI: Human-Aware Planning and Behavior Prediction

Application Category

Search and Retrieval-Augmented AI: Agentic searchSemantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMsResponsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Construction robots have gained significant traction in recent years in research and development. However, the application of industrial robots has unique challenges. Dynamic environments, domain-specific tasks, and complex localization and mapping are significant obstacles in their development. In construction job sites, moving objects and complex machinery can make pathfinding a difficult task due to the possibility of object collisions. Existing methods such as simultaneous localization and mapping are viable solutions to this problem, however, due to the precision and data quality required by the sensors and the processing of the information, they can be very computationally expensive. We propose using spatial and semantic information in building information modeling (BIM) to develop domain-specific pathfinding strategies. In this work, we integrate a multi-heuristic A* (MHA*) algorithm using APFs from the BIM spatial information and process textual information from the BIM using large language models (LLMs) to adjust the algorithm for dynamic object avoidance. We show increased robot object proximity by 80% while maintaining similar path lengths.

Problem

• Robot Navigation
• SLAM Optimization
• Construction Sites

Innovation

• BIM Integration
• MHA* Algorithm
• NLP for Navigation