Journals
  Publication Years
  Keywords
Search within results Open Search
Please wait a minute...
For Selected: Toggle Thumbnails
A Review of Robot Learning
QU Weiming, LIU Tianlin, LIN Weikai, LUO Dingsheng
Acta Scientiarum Naturalium Universitatis Pekinensis    2023, 59 (6): 1069-1086.   DOI: 10.13209/j.0479-8023.2023.086
Abstract223)   HTML    PDF(pc) (60672KB)(130)       Save
The basic concepts and core issues related to robot learning are introduced and discussed, and the relevant researches are summarized and analyzed. Through comparing the relevant methods and recent progress, the authors classify the methods of robot learning into four categories based on data types and learning methods, namely reinforcement learning approach, imitation learning approach, transfer learning approach and developmental learning approach. Finally, current challenges and future trends in robot learning are listed.
Related Articles | Metrics | Comments0
Similarities Analysis on Center of Pressure Trajectories for Healthy Volunteers during Walking and Jogging
HUANG Hongshi, QIU Jianwei, YU Yuanyuan, YANG Jie, AO Yingfang, LUO Dingsheng
Acta Scientiarum Naturalium Universitatis Pekinensis    2015, 51 (6): 1035-1039.   DOI: 10.13209/j.0479-8023.2015.128
Abstract1171)      PDF(pc) (459KB)(858)       Save

The aim of this study was to investigate the similarities of Center of Pressure (COP) trajectories during barefoot walking and jogging, based on plantar pressure data collected from 32 healthy volunteers. 32 subjects walk or run on a two-meter footscan® system at a self-selected speed for 5 valid trials respectively. For each trial, a sequence of frames is generated which records the instantaneous pressure value of the reaction between body and the supporting surface. Similarities between COP trajectories are calculated. Results show that similarities between walking and jogging COP trajectories are lower than 0.25, while similarities between left and right COP trajectories during the same motion status (walking or jogging) is higher than 0.91. In addition, intrasubject similarities are significantly higher than those of intersubject. Moreover, similarities between the same sides are significantly higher than those of different sides. COP trajectories similarities between walking and jogging are very low which indicates COP trajectories can distinguish walking from jogging. During the same motion, intersubject similarities are high. In addition, intrasubject similarities are even higher. This study provides a reliable dataset for clinical diagnosis, rehabilitation evaluation, orthosis prescription and sports exercises.

Related Articles | Metrics | Comments0