IEEE Robotics & Automation Magazine · 2007 · 79 citations · 29 references
EngineeringComputer ScienceRobotics EngineeringRobot ControlRobot LearningRoboticsBipedal LocomotionLegged LocomotionLegged Robot ControlLocomotion LearningModel-based Robot LearningReinforcement LearningBipedal ControlGait LearningLearning-based LocomotionModel-based Locomotion LearningModel-based Reinforcement LearningPoincaré Map AnalysisReinforcement Learning For LocomotionWalking
The study proposes a model‑based reinforcement learning algorithm that enables a biped robot to modulate an observed walking pattern. The algorithm detects via‑points using a minimum‑jerk criterion, models the Poincaré map between single‑support states, and controls these via‑points to generate walking, tested on both simulation and a real biped. The approach successfully learns walking policies that enable stable biped locomotion.
We propose a model-based reinforcement learning (RL) algorithm for biped walking in which the robot learns to appropriately modulate an observed walking pattern. Via-points are detected from the observed walking trajectories using the minimum jerk criterion. The learning algorithm controls the via-points based on a learned model of the Poincare map of the periodic walking pattern. The model maps from a state in the single support phase and the controlled via-points to a state in the next single support phase. We applied this approach to both a simulated robot model and an actual biped robot. We show that successful walking policies were acquired.
29
Reinforcement Learning: An Introduction
Richard S. Sutton, Andy Barto · IEEE Transactions on Neural Networks · 1998 · 27.1K citations
Reinforcement Learning: An Introduction
IEEE Transactions on Neural Networks · 2005 · 25.8K citations