Open AccessLearning Push Recovery Strategies for Bipedal Walking
Author(s) -
Dicksiano Carvalho Melo,
Marcos R. O. A. Máximo,
Adilson Marques da Cunha
Publication year - 2021
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5753/wtdr_ctdr.2021.18686
Subject(s) - computer science , league , humanoid robot , controller (irrigation) , work (physics) , robot , physics engine , simulation , artificial intelligence , human–computer interaction , control engineering , engineering , physics , astronomy , mechanical engineering , agronomy , biology
The present work provides an implementation of a Push Recovery controller that aids the walking engine used by a humanoid simulated robot. The simulation environment is the Robocup Soccer 3D Simulation League. The learned movement policies exceeded our original walking engine. In addition, we evaluated the policies and detected undesired biases. New methodologies were introduced in order to eliminate it.