TY - GEN
T1 - Context is Everything
T2 - 39th IEEE International Conference on Robotics and Automation, ICRA 2022
AU - Evans, Ben
AU - Thankaraj, Abitha
AU - Pinto, Lerrel
N1 - Funding Information:
VII. ACKNOWLEDGEMENTS We thank Kendall Lowrey, Denis Yarats, and David Brand-fonbrener for their feedback on early versions of the paper. This work was supported by grants from Honda, Amazon, and ONR award numbers N00014-21-1-2404 and N00014-21-1-2758.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Understanding environment dynamics is necessary for robots to act safely and optimally in the world. In realistic scenarios, dynamics are non-stationary and the causal variables such as environment parameters cannot necessarily be precisely measured or inferred, even during training. We propose Implicit Identification for Dynamics Adaptation (IIDA), a simple method to allow predictive models to adapt to changing environment dynamics. IIDA assumes no access to the true variations in the world and instead implicitly infers properties of the environment from a small amount of contextual data. We demonstrate IIDA's ability to perform well in unseen environments through a suite of simulated experiments on MuJoCo environments and a real robot dynamic sliding task. In general, IIDA significantly reduces model error and results in higher task performance over commonly used methods. Our code, video of the method, and latest paper is available here https://bennevans.github.io/icra-iida/
AB - Understanding environment dynamics is necessary for robots to act safely and optimally in the world. In realistic scenarios, dynamics are non-stationary and the causal variables such as environment parameters cannot necessarily be precisely measured or inferred, even during training. We propose Implicit Identification for Dynamics Adaptation (IIDA), a simple method to allow predictive models to adapt to changing environment dynamics. IIDA assumes no access to the true variations in the world and instead implicitly infers properties of the environment from a small amount of contextual data. We demonstrate IIDA's ability to perform well in unseen environments through a suite of simulated experiments on MuJoCo environments and a real robot dynamic sliding task. In general, IIDA significantly reduces model error and results in higher task performance over commonly used methods. Our code, video of the method, and latest paper is available here https://bennevans.github.io/icra-iida/
UR - http://www.scopus.com/inward/record.url?scp=85136322876&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85136322876&partnerID=8YFLogxK
U2 - 10.1109/ICRA46639.2022.9812119
DO - 10.1109/ICRA46639.2022.9812119
M3 - Conference contribution
AN - SCOPUS:85136322876
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 2642
EP - 2648
BT - 2022 IEEE International Conference on Robotics and Automation, ICRA 2022
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 23 May 2022 through 27 May 2022
ER -