Robot navigation anticipative strategies in deep reinforcement motion planning

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...

Descripción completa

Detalles Bibliográficos
Autores: Gil Viyuela, Óscar, Sanfeliu, Alberto
Tipo de recurso: artículo
Estado:Versión aceptada para publicación
Fecha de publicación:2022
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/306630
Acceso en línea:http://hdl.handle.net/10261/306630
Access Level:acceso abierto
Palabra clave:Deep reinforcement learning
Robot navigation
Social force model
Human-robot interaction
Anticipation
Descripción
Sumario: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.