Chang, Alexander H. and Hubicki, Christian and Ames, Aaron and Vela, Patricio A. (2019) Every Hop is an Opportunity: Quickly Classifying and Adapting to Terrain During Targeted Hopping. In: 2019 International Conference on Robotics and Automation (ICRA). IEEE , Piscataway, NJ, pp. 3188-3194. ISBN 978-1-5386-6027-0. https://resolver.caltech.edu/CaltechAUTHORS:20190815-131048956
Full text is not posted in this repository. Consult Related URLs below.
Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20190815-131048956
Abstract
Practical use of robots in diverse domains requires programming for, or adapting to, each domain and its unique characteristics. Failure to do so compromises the ability of the robot to achieve task-relevant objectives. Here we describe how the learned terrain reaction force profiles of a hopping robot serve the additional objectives of classifying terrain and quickly learning control strategies to accomplish a jumping task on novel terrain. We show that the reaction forces experienced during closed-loop jumping are sufficient to discriminate between three different terrain types (granular, trampoline, and rigid) when using the learned models as discriminators. Building on this, we show that applying the classification to unknown terrain types leads to faster task completion, where the task objective is to meet a specific jump height. The classification experiments, utilizing real-world jumping data, achieve 95% prediction accuracy. The online learning experiments leverage simulation as there is more control over the terrain properties. Terrain-informed learning achieves the target hop heights more than 2x faster than without terrain knowledge when the prediction is correct, and 1.5x faster when the prediction is incorrect. Thus, applying the closest approximately known terrain knowledge facilitates low shot learning when hopping on unknown terrain.
Item Type: | Book Section | ||||||
---|---|---|---|---|---|---|---|
Related URLs: |
| ||||||
ORCID: |
| ||||||
Additional Information: | © 2019 IEEE. This work was supported by NSF Award #1544857. | ||||||
Funders: |
| ||||||
DOI: | 10.1109/ICRA.2019.8793757 | ||||||
Record Number: | CaltechAUTHORS:20190815-131048956 | ||||||
Persistent URL: | https://resolver.caltech.edu/CaltechAUTHORS:20190815-131048956 | ||||||
Official Citation: | A. H. Chang, C. Hubicki, A. Ames and P. A. Vela, "Every Hop is an Opportunity: Quickly Classifying and Adapting to Terrain During Targeted Hopping," 2019 International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada, 2019, pp. 3188-3194. doi: 10.1109/ICRA.2019.8793757 | ||||||
Usage Policy: | No commercial reproduction, distribution, display or performance rights in this work are provided. | ||||||
ID Code: | 97925 | ||||||
Collection: | CaltechAUTHORS | ||||||
Deposited By: | Tony Diaz | ||||||
Deposited On: | 15 Aug 2019 20:20 | ||||||
Last Modified: | 16 Nov 2021 17:35 |
Repository Staff Only: item control page