Learning for Robot Decision Making under Distribution Shift: A Survey

TL;DR

This survey reviews techniques for improving robotic decision making under distribution shift, categorizing existing approaches, and highlighting open challenges for future research in the field.

Contribution

It provides a comprehensive taxonomy and survey of current methods addressing distribution shift in robotic learning, and identifies open problems for future work.

Findings

Taxonomy of existing approaches to distribution shift in robotics

Summary of techniques improving decision making under distribution shift

Identification of open research challenges

Abstract

With the recent advances in the field of deep learning, learning-based methods are widely being implemented in various robotic systems that help robots understand their environment and make informed decisions to achieve a wide variety of tasks or goals. However, learning-based methods have repeatedly been shown to have poor generalization when they are presented with inputs that are different from those during training leading to the problem of distribution shift. Any robotic system that employs learning-based methods is prone to distribution shift which might lead the agents to make decisions that lead to degraded performance or even catastrophic failure. In this paper, we discuss various techniques that have been proposed in the literature to aid or improve decision making under distribution shift for robotic systems. We present a taxonomy of existing literature and present a survey of existing approaches in the area based on this taxonomy. Finally, we also identify a few open problems in the area that could serve as future directions for research.