Study on Gait Pattern Generation With Improved Hip Vertical Motion for Biped Robots

Gait pattern generation plays a significant role in the quality of a walking robot. This paper mainly focuses on hip vertical motion effects on gait pattern generation for biped robots. Inspired by human walking, gait pattern with hip undulating motion (GPHUM) is proposed. Firstly, we defined cyclic gaits for a seven-link biped robot with several design parameters. Then, design parameters are obtained by optimization. The optimization criterion is minimizing the energy consumption of the joint actuators. Finally, optimal walking gait is simulated. In order to compare the performance of the proposed common gait pattern with fixed hip height pattern (GPFHH), we generated the optimal gait for the two gait patterns with different step lengths and different walking periods. The comparison of simulation results shows that GPHUM is more than 20% energy-efficient than GPFHH; therefore, the proposed GPHUM can greatly improve the walking time of the robot with battery as the power source. Moreover, the hip height parameters are related to the step length, and the change of the walking period has no significant effect on these parameters; thus, hip height parameters corresponding to different step length can be calculated off-line for the online gait pattern generation. In addition, the proposed GPHUM has larger optimal step length than GPFHH, and it allows the biped robot walk more efficiently with a larger stride.