Robust biped locomotion using deep reinforcement learning on top of an analytical control approach

• Tipo: Artigo em Revista Científica Internacional
• Data: 2021

Autores

Kasaei, M (Autor) Outra; Abreu, M (Autor) Outra; lau, n (Autor) Outra; Pereira, A (Autor) Outra; reis, lp (Autor) FEUP

Revista

Título: Robotics and Autonomous Systems

Vol. 146

ISSN: 0921-8890

Editora: Elsevier

Indexação

ISI Web of Knowledge - 0 Citações

Outras Informações

ID Authenticus: P-00V-KPY

DOI: 10.1016/j.robot.2021.103900

Abstract (EN): This paper proposes a modular framework to generate robust biped locomotion using a tight coupling between an analytical walking approach and deep reinforcement learning. This framework is composed of six main modules which are hierarchically connected to reduce the overall complexity and increase its flexibility. The core of this framework is a specific dynamics model which abstracts a humanoid's dynamics model into two masses for modeling upper and lower body. This dynamics model is used to design an adaptive reference trajectories planner and an optimal controller which are fully parametric. Furthermore, a learning framework is developed based on Genetic Algorithm (GA) and Proximal Policy Optimization (PPO) to find the optimum parameters and to learn how to improve the stability of the robot by moving the arms and changing its center of mass height. A set of simulations are performed to validate the performance of the framework using the official RoboCup 3D League simulation environment. The results validate the performance of the framework, not only in creating a fast and stable gait but also in learning to improve the upper body efficiency.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 13