ROAILGMar 10, 2022

Context is Everything: Implicit Identification for Dynamics Adaptation

arXiv:2203.05549v137 citationsh-index: 41
Originality Incremental advance
AI Analysis

This addresses the challenge of safe and optimal robot operation in changing environments, representing an incremental improvement over existing methods.

The paper tackles the problem of robots adapting to non-stationary environment dynamics without access to true causal variables, proposing IIDA to implicitly infer environment properties from contextual data, which reduces model error and improves task performance in simulated and real robot experiments.

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 and robot videos are at https://bennevans.github.io/iida/

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes