Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence
Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence
An effective trajectory generation method for bipedal walking
Robotics and Autonomous Systems
Neuro-fuzzy ZMP control of a biped robot
SMO'06 Proceedings of the 6th WSEAS International Conference on Simulation, Modelling and Optimization
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Near-optimal gait generations of a two-legged robot on rough terrains using soft computing
Robotics and Computer-Integrated Manufacturing
Hi-index | 0.00 |
Trunk motions are typically used in biped robots to stabilize the locomotion. However, they can be very large for some leg trajectories unless they are carefully designed. This paper proposes a fuzzy-logic zero-moment-point (ZMP) trajectory generator that would eventually reduce the swing motion of the trunk significantly even though the leg trajectory is casually designed, for example, simply to avoid obstacles. The fuzzy-logic ZMP trajectory generator uses the leg trajectory as an input. The resulting ZMP trajectory is similar to that of a human one and continuously moves forward in the direction of the locomotion. The trajectory of the trunk to stabilize the locomotion is determined by solving a differential equation with the ZMP trajectory and the leg trajectory known. The proposed scheme is simulated on a 7-DOF biped robot in the sagittal plane. The simulation results show that the ZMP trajectory generated by the proposed fuzzy-logic generator increases the stability of the locomotion and thus reduces the motion range of the trunk significantly.