Enhancing Consistent Ground Maneuverability by Robot Adaptation to Complex Off-Road Terrains

Sriram Siva, Maggie Wigness, John Rogers, Hao Zhang
Proceedings of the 5th Conference on Robot Learning, PMLR 164:1200-1210, 2022.

Abstract

Terrain adaptation is a critical ability for a ground robot to effectively traverse unstructured off-road terrain in real-world field environments such as forests. However, the expected or planned maneuvering behaviors cannot always be accurately executed due to setbacks such as reduced tire pressure. This inconsistency negatively affects the robot’s ground maneuverability and can cause slower traversal time or errors in localization. To address this shortcoming, we propose a novel method for consistent behavior generation that enables a ground robot’s actual behaviors to more accurately match expected behaviors while adapting to a variety of complex off-road terrains. Our method learns offset behaviors in a self-supervised fashion to compensate for the inconsistency between the actual and expected behaviors without requiring the explicit modeling of various setbacks. To evaluate the method, we perform extensive experiments using a physical ground robot over diverse complex off-road terrain in real-world field environments. Experimental results show that our method enables a robot to improve its ground maneuverability on complex unstructured off-road terrain with more navigational behavior consistency, and outperforms previous and baseline methods, particularly so on challenging terrain such as that which is seen in forests.

Cite this Paper

BibTeX
@InProceedings{pmlr-v164-siva22a, title = {Enhancing Consistent Ground Maneuverability by Robot Adaptation to Complex Off-Road Terrains}, author = {Siva, Sriram and Wigness, Maggie and Rogers, John and Zhang, Hao}, booktitle = {Proceedings of the 5th Conference on Robot Learning}, pages = {1200--1210}, year = {2022}, editor = {Faust, Aleksandra and Hsu, David and Neumann, Gerhard}, volume = {164}, series = {Proceedings of Machine Learning Research}, month = {08--11 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v164/siva22a/siva22a.pdf}, url = {https://proceedings.mlr.press/v164/siva22a.html}, abstract = {Terrain adaptation is a critical ability for a ground robot to effectively traverse unstructured off-road terrain in real-world field environments such as forests. However, the expected or planned maneuvering behaviors cannot always be accurately executed due to setbacks such as reduced tire pressure. This inconsistency negatively affects the robot’s ground maneuverability and can cause slower traversal time or errors in localization. To address this shortcoming, we propose a novel method for consistent behavior generation that enables a ground robot’s actual behaviors to more accurately match expected behaviors while adapting to a variety of complex off-road terrains. Our method learns offset behaviors in a self-supervised fashion to compensate for the inconsistency between the actual and expected behaviors without requiring the explicit modeling of various setbacks. To evaluate the method, we perform extensive experiments using a physical ground robot over diverse complex off-road terrain in real-world field environments. Experimental results show that our method enables a robot to improve its ground maneuverability on complex unstructured off-road terrain with more navigational behavior consistency, and outperforms previous and baseline methods, particularly so on challenging terrain such as that which is seen in forests.} }
Endnote
%0 Conference Paper %T Enhancing Consistent Ground Maneuverability by Robot Adaptation to Complex Off-Road Terrains %A Sriram Siva %A Maggie Wigness %A John Rogers %A Hao Zhang %B Proceedings of the 5th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2022 %E Aleksandra Faust %E David Hsu %E Gerhard Neumann %F pmlr-v164-siva22a %I PMLR %P 1200--1210 %U https://proceedings.mlr.press/v164/siva22a.html %V 164 %X Terrain adaptation is a critical ability for a ground robot to effectively traverse unstructured off-road terrain in real-world field environments such as forests. However, the expected or planned maneuvering behaviors cannot always be accurately executed due to setbacks such as reduced tire pressure. This inconsistency negatively affects the robot’s ground maneuverability and can cause slower traversal time or errors in localization. To address this shortcoming, we propose a novel method for consistent behavior generation that enables a ground robot’s actual behaviors to more accurately match expected behaviors while adapting to a variety of complex off-road terrains. Our method learns offset behaviors in a self-supervised fashion to compensate for the inconsistency between the actual and expected behaviors without requiring the explicit modeling of various setbacks. To evaluate the method, we perform extensive experiments using a physical ground robot over diverse complex off-road terrain in real-world field environments. Experimental results show that our method enables a robot to improve its ground maneuverability on complex unstructured off-road terrain with more navigational behavior consistency, and outperforms previous and baseline methods, particularly so on challenging terrain such as that which is seen in forests.
APA
Siva, S., Wigness, M., Rogers, J. & Zhang, H.. (2022). Enhancing Consistent Ground Maneuverability by Robot Adaptation to Complex Off-Road Terrains. Proceedings of the 5th Conference on Robot Learning, in Proceedings of Machine Learning Research 164:1200-1210 Available from https://proceedings.mlr.press/v164/siva22a.html.

Related Material