Improved coverage path planning for indoor robots based on BIM and robotic configurations

Robotics holds great potential to improve productivity in construction, and coverage path planning (CPP) is an essential capability crucial to various applications, including floor cleaning and environmental monitoring. However, there is still a lack of a comprehensive CPP system that can handle complex indoor conditions and various robotic properties. An improved CPP (ICCP) system that leverages building information modeling (BIM) and robotic configurations for indoor robots is proposed in this study. Firstly, BIM is semantically enriched to generate semantic trapezoidal grid maps (TGMs); Next, a novel concept called “coverage bonus” is incorporated into coverage pattern analysis to enable farsighted decision making; Finally, the coverage sequence is optimized by solving the cluster generalized traveling salesman problem, resulting in routes that minimize both coverage distances and disruptions in indoor activities. Experimental validation shows that the ICPP system can not only attain optimal coverage performance with the highest coverage ratio (97.6%) but also ensure the adherence to indoor coverage rules. Future research will focus on enhancing coverage ratio through tunable hyperparameters, optimizing computation time in ICCP, and expanding the study to multi-robot scenarios.