Sampling-Based Path Planning in Highly Dynamic and Crowded Pedestrian Flow

Autonomous pedestrian-aware navigation in shared human-robot environments is a challenging problem. Here we consider a common situation in which a large crowd of pedestrians moves together in a limited space. Traditional planners struggle to find collision-free paths in such situations since the free space is limited and always changing. To solve this problem, we proposed a flow map-based RRT* method (FM-RRT*) containing a velocity layer and a minimally-intrusive layer. The proposed method models the velocity of the pedestrian flow and the area where the robot is less invasive to pedestrians. Furthermore, we propose an adaptive bias sampling, which drives the robot considering relative velocity, or minimal intrusion, according to the pedestrian flow. The evaluation is conducted in the Crowdbot Challenge simulator. The results show that our method can find a feasible path considering collision risk while simultaneously avoiding intrusive human movement.

Automated summary

This paper addresses the problem of autonomous pedestrian-aware navigation in shared human-robot environments and proposes a flow map-based RRT* method (FM-RRT*) to solve it. The method models the velocity of pedestrian flow and the area where the robot is less invasive, and uses adaptive bias sampling to drive the robot considering relative velocity or minimal intrusion. The evaluation conducted in the Crowdbot Challenge simulator shows that the method can find a feasible path while avoiding intrusive human movement.