Teaching robot navigation behaviors to optimal RRT planners

This work presents an approach for learning navigation behaviors for robots using Optimal Rapidly-exploring Random Trees (RRT*) as the main planner. A new learning algorithm combining both Inverse Reinforcement Learning (IRL) and RRT* is developed to learn the RRT* ’s cost function from demonstratio...

Descripción completa

Detalles Bibliográficos
Autores: Pérez Higueras, Noé, Caballero, Fernando, Merino, Luis
Tipo de recurso: artículo
Fecha de publicación:2017
País:España
Institución:Universidad Pablo de Olavide (UPO)
Repositorio:RIO. Repositorio Institucional Olavide
Idioma:inglés
OAI Identifier:oai:rio.upo.es:10433/25604
Acceso en línea:https://hdl.handle.net/10433/25604
Access Level:acceso abierto
Palabra clave:Path Planning
Learning from Demonstration
Social Robots
Descripción
Sumario:This work presents an approach for learning navigation behaviors for robots using Optimal Rapidly-exploring Random Trees (RRT*) as the main planner. A new learning algorithm combining both Inverse Reinforcement Learning (IRL) and RRT* is developed to learn the RRT* ’s cost function from demonstrations. A comparison with other state-of-the-art algorithms shows how the method can recover the behavior from the demonstrations. Finally, a learned cost function for social navigation is tested in real experiments with a robot in the laboratory.