https://scholars.lib.ntu.edu.tw/handle/123456789/598970
Title: | Legged robot running using a physics-data hybrid motion template | Authors: | Yang W.-S Lu W.-C Lin P.-C. PEI-CHUN LIN |
Keywords: | Gaussian process (GP) regression;Inverted pendulum;Legged robot;Rolling;Running;Spring-loaded;Template;Trajectory optimization;Agricultural robots;Iterative methods;Machine design;Data-driven model;Design and control;Gaussian process;Model complexes;Motion templates;Power efficient;Unmodeled dynamics;Robots | Issue Date: | 2021 | Journal Volume: | 37 | Journal Issue: | 5 | Start page/Pages: | 1680-1695 | Source: | IEEE Transactions on Robotics | Abstract: | We report on the methodology of developing a hybrid model and utilizing it as a template to initiate running behavior in a legged robot. The hybrid model is comprised of a physics-based, rolling, spring-loaded, inverted pendulum (R-SLIP) model, and a data-driven model that compensates for unmodeled dynamics using Gaussian process (GP) regression. The hybrid R-SLIP-GP model retains the R-SLIP's intrinsic running dynamics, as well as improves the template's accuracy without intensive data training and iteration efforts. The proposed hybrid model was evaluated via simulation and in empirical robot running experiments. The results confirm that the added GP-based model greatly improved the model's accuracy, especially discrepancies resulting from the originally difficult-to-model complex leg-ground interactions. In addition, the R-SLIP-GP model was utilized as a complete motion template to design and control the robot's running motion. The experimental results demonstrate that the hybrid template can initiate more stable and power-efficient running motion in the robot than using the R-SLIP template. ? 2021 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85104662764&doi=10.1109%2fTRO.2021.3065241&partnerID=40&md5=4c2248774f72e8eb99e6810e5ff68786 https://scholars.lib.ntu.edu.tw/handle/123456789/598970 |
ISSN: | 15523098 | DOI: | 10.1109/TRO.2021.3065241 |
Appears in Collections: | 機械工程學系 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.