Technology Category
Natural Language Processing: Safety and RobustnessIntelligent Robots: Motion and Path PlanningPlanning, Routing, and Scheduling: Planning with Language Models
Bayesian BIM-Guided Construction Robot Navigation with NLP Safety Prompts in Dynamic Environments
🤖 AI Summary
In dynamic construction environments, building robots struggle to respond appropriately to verbal human safety warnings. Method: This paper proposes a risk-adaptive navigation framework integrating Building Information Modeling (BIM) semantics with natural language understanding. It innovatively couples NLP-based sentiment analysis with BIM semantic parsing to construct a Bayesian probabilistic model that dynamically tunes an exponential potential field for path planning. Furthermore, it introduces an object-aware, semantics-driven hierarchical risk navigation paradigm. Results: Experiments demonstrate a 50% increase in minimum obstacle avoidance distance under safety-critical scenarios and support differentiated path generation for contrastive voice commands (e.g., “danger” vs. “safe”), balancing safety and navigational rationality. The core contribution is an interpretable and verifiable mapping from natural-language safety instructions to real-time robot navigation policies.
Technology Category
Application Category
📝 Abstract
Construction robotics increasingly relies on natural language processing for task execution, creating a need for robust methods to interpret commands in complex, dynamic environments. While existing research primarily focuses on what tasks robots should perform, less attention has been paid to how these tasks should be executed safely and efficiently. This paper presents a novel probabilistic framework that uses sentiment analysis from natural language commands to dynamically adjust robot navigation policies in construction environments. The framework leverages Building Information Modeling (BIM) data and natural language prompts to create adaptive navigation strategies that account for varying levels of environmental risk and uncertainty. We introduce an object-aware path planning approach that combines exponential potential fields with a grid-based representation of the environment, where the potential fields are dynamically adjusted based on the semantic analysis of user prompts. The framework employs Bayesian inference to consolidate multiple information sources: the static data from BIM, the semantic content of natural language commands, and the implied safety constraints from user prompts. We demonstrate our approach through experiments comparing three scenarios: baseline shortest-path planning, safety-oriented navigation, and risk-aware routing. Results show that our method successfully adapts path planning based on natural language sentiment, achieving a 50% improvement in minimum distance to obstacles when safety is prioritized, while maintaining reasonable path lengths. Scenarios with contrasting prompts, such as"dangerous"and"safe", demonstrate the framework's ability to modify paths. This approach provides a flexible foundation for integrating human knowledge and safety considerations into construction robot navigation.
Problem
Research questions and friction points this paper is trying to address.
Construction Robots
Verbal Safety Instructions
Complex Construction Sites
Innovation
Methods, ideas, or system contributions that make the work stand out.
Emotion Understanding
Safety-focused Path Planning
Human-Robot Interaction in Construction
🔎 Similar Papers
No similar papers found.
