For the purpose of realizing the humanoid robot walking on uneven terrain, this paper proposes the kinodynamic gait planning method where both kinematics and dynamics of the system are considered. We can simultaneously plan both the foot-place and the whole-body motion taking the dynamical balance of the robot into consideration. As a dynamic constraint, we consider the differential equation of the robot's CoG. To solve this constraint, we use a walking pattern generator. We randomly sample the configuration space to search for the path connecting the start and the goal configurations. To show the effectiveness of the proposed methods, we show simulation and experimental results where the humanoid robot HRP-2 walks on rocky cliff with hands contacting the environment.
Read full abstract