Aligning Human and Robot Representations
Name
3610977.3634987.pdf
Size
1.56 MB
Format
Adobe PDF
Checksum (MD5)
16999af80dfd6d398bbf53b65deebe23
Author(s)
Bobu, Andreea
Peng, Andi
Agrawal, Pulkit
Shah, Julie A
Dragan, Anca D.
Date Issued
March 11, 2024
Publisher
ACM
Citation
Bobu, Andreea, Peng, Andi, Agrawal, Pulkit, Shah, Julie A and Dragan, Anca D. 2024. "Aligning Human and Robot Representations."
Version
Final published version
Abstract
To act in the world, robots rely on a representation of salient task aspects: for example, to carry a coffee mug, a robot may consider movement efficiency or mug orientation in its behavior. However, if we want robots to act for and with people, their representations must not be just functional but also reflective of what humans care about, i.e. they must be aligned. We observe that current learning approaches suffer from representation misalignment, where the robot's learned representation does not capture the human's representation. We suggest that because humans are the ultimate evaluator of robot performance, we must explicitly focus our efforts on aligning learned representations with humans, in addition to learning the downstream task. We advocate that current representation learning approaches in robotics should be studied from the perspective of how well they accomplish the objective of representation alignment. We mathematically define the problem, identify its key desiderata, and situate current methods within this formalism. We conclude by suggesting future directions for exploring open challenges.
Description
HRI ’24, March 11–14, 2024, Boulder, CO, USA
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3610977.3634987
