ABSTRACT
Robot arm motion control is a fundamental aspect of robot capabilities, with arm reaching ability serving as the foundation for complex arm manipulation tasks. However, traditional inverse kinematics-based methods for robot arm reaching struggle to cope with the increasing complexity and diversity of robot environments, as they heavily rely on the accuracy of physical models. In this paper, we introduce an innovative approach to robot arm motion control, inspired by the cognitive mechanism of inner rehearsal observed in humans. The core concept revolves around the robot's ability to predict or evaluate the outcomes of motion commands before execution. This approach enhances the learning efficiency of models and reduces the mechanical wear on robots caused by excessive physical executions. We conduct experiments using the Baxter robot in simulation and the humanoid robot PKU-HR6.0 II in a real environment to demonstrate the effectiveness and efficiency of our proposed approach for robot arm reaching across different platforms. The internal models converge quickly and the average error distance between the target and the end-effector on the two platforms is reduced by 80% and 38%, respectively.
ABSTRACT
OBJECTIVE: To evaluate the center of pressure (COP) progression similarity and its change during walking and jogging in Anterior Cruciate Ligament deficient (ACLD) patients. METHODS: A study was performed in 64 unilateral ACLD subjects and 32 healthy volunteers who walked and jogged on footscan® system at a self-selected speed. COP trajectory during walking and jogging was calculated. The robustness and similarity scores of COP (SSCOP, similarity scores with respect to corresponding COP trajectories) were computed, and then the Analysis of Variance test was employed to compare among different conditions (left or right side, within a subject or between subjects, walking or jogging). RESULTS: (1) During the same motion status (walking or jogging), SSCOP were higher than 0.885. However, SSCOP between walking and jogging were lower than 0.25 in both the healthy and ACLD group. SSCOP between the intrasubjects were statistically higher than those between the intersubjects (p<0.01). (2) SSCOP in the ACLD group were statistically significantly reduced to 0.885±0.074 compared to 0.912±0.057 in healthy volunteers during walking, and 0.903±0.066 in the ACLD group compared to 0.919±0.050 in the healthy group during jogging (p<0.01). CONCLUSIONS: SSCOP can distinguish walking from jogging, and SSCOP of ACLD patients would be different from that of healthy controls. The study protocol was approved by the Institutional Research Board of Peking University Third Hospital (IRB00006761-2012010).