On Differential Drive Robot Learning Convex Policy with Application to Path-Tracking

Autor(es)

Ribeiro, A. M. ; Quiroz, C. H. C. ; Fioravanti, A. R. ; Kurka, P. R. G.

• Tipo de documento: Artigo Científico
• Fonte: IFAC PAPERSONLINE; v. 54, n. 4, p. 6-pg., 2021-10-29.

Resumo

This paper presents an experimental validation of a learning convex policy for path-tracking on a differential drive robot. An online implementation of the convex control policy (COCP) is provided in the ROS environment using the CVXGEN package that runs on the on-board computer in a real-time application. The control policies are trained in an off-board computer considering a stochastic kinematic description of the robot and using approximate gradient method for a given cost-to-go metric function. The policy is validated through simulation and experimental evaluation. In addition, to certify the training efficacy, the experiment is also evaluated using the untuned policy. A discussion regarding trajectory errors is presented as well as final considerations for the solver and real-time concerns. Copyright (C) 2021 The Authors. (AU)

• Processo FAPESP: 18/05712-2 - Identificação e controle de um veículo elétrico robótico com diferencial eletrônico
• Beneficiário: Alexandre Monteiro Ribeiro
• Modalidade de apoio: Bolsas no Brasil - Doutorado