Learning to Jump from Pixels
Gabriel B Margolis, Tao Chen, Kartik Paigwar, Xiang Fu, Donghyun Kim, Sang bae Kim, Pulkit Agrawal
Abstract
Today's robotic quadruped systems can robustly walk over a diverse range of rough but continuous terrains, where the terrain elevation varies gradually. Locomotion on discontinuous terrains, such as those with gaps or obstacles, presents a complementary set of challenges. In discontinuous settings, it becomes necessary to plan ahead using visual inputs and to execute agile behaviors beyond robust walking, such as jumps. Such dynamic motion results in significant motion of onboard sensors, which introduces a new set of challenges for real-time visual processing. The requirements of agility and terrain awareness in this setting reinforce the need for robust control. We present Depth-based Impulse Control (DIC), a method for synthesizing highly agile visually-guided locomotion behaviors. DIC affords the flexibility of model-free learning but regularizes behavior through explicit model-based optimization of ground reaction forces. We evaluate performance both in simulation and in the real world.
BibTeX
@inproceedings{
margolis2021learning,
title={Learning to Jump from Pixels},
author={Gabriel B Margolis and Tao Chen and Kartik Paigwar and Xiang Fu and Donghyun Kim and Sang bae Kim and Pulkit Agrawal},
booktitle={5th Annual Conference on Robot Learning },
year={2021},
url={https://openreview.net/forum?id=R4E8wTUtxdl}
}