Robot Navigation Anticipative Strategies in Deep Reinforcement Motion Planning
This work addresses the problem of safe and human-aware robot navigation for applications in urban settings, presenting an incremental improvement by combining existing methods.
The paper tackled robot navigation in dynamic urban environments by developing and analyzing three anticipative strategies to avoid collisions with moving objects like pedestrians and bicycles, achieving very good results in both simulation and real-life experiments across various scenarios.
The navigation of robots in dynamic urban environments, requires elaborated anticipative strategies for the robot to avoid collisions with dynamic objects, like bicycles or pedestrians, and to be human aware. We have developed and analyzed three anticipative strategies in motion planning taking into account the future motion of the mobile objects that can move up to 18 km/h. First, we have used our hybrid policy resulting from a Deep Deterministic Policy Gradient (DDPG) training and the Social Force Model (SFM), and we have tested it in simulation in four complex map scenarios with many pedestrians. Second, we have used these anticipative strategies in real-life experiments using the hybrid motion planning method and the ROS Navigation Stack with Dynamic Windows Approach (NS-DWA). The results in simulations and real-life experiments show very good results in open environments and also in mixed scenarios with narrow spaces.