수동 동역학 보행로봇을 위한 강화학습 기반의 제어기 설계

주백석, 홍대희, 박주영 · 대한기계학회 춘추학술대회 · 2006

Passive dynamic walker is a kind of bipedal walking robots that are able to walk stably down a small decline without using any actuators. The purpose of this research is to design a controller in order to build actuated robots capable of walking on flat terrain based on passive dynamic walking. To achieve the objective, the control algorithm used in this research is reinforcement learning (RL) method. RL is a goal-directed learning of a mapping from situations to actions. The goal of RL is to maximize a reward which is an evaluative feedback from the environment. Constructing the reward of the actuated passive dynamic walker, the control objective, which is stable walking on level ground, is included. In this research, RL algorithm based on actor-critic architecture and gradient-following algorithm is applied. The control algorithm is verified with computer simulations. It is confirmed that with the suggested controller, the control objective is sufficiently achieved.

Cited by 0 works.

Authors