Improving Robot Controller Transparency Through Autonomous Policy Explanation
Shared expectations and mutual understanding are critical facets of teamwork. Achieving these in human-robot collaborative contexts can be especially challenging, as humans and robots are unlikely to share a common language to convey intentions, plans, or justifications. Even in cases where human co...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Association for Computing Machinery (ACM)
2018
|
| Online Access: | http://hdl.handle.net/1721.1/116013 https://orcid.org/0000-0003-1338-8107 |
| _version_ | 1826211883328208896 |
|---|---|
| author | Hayes, Bradley H Shah, Julie A |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Hayes, Bradley H Shah, Julie A |
| author_sort | Hayes, Bradley H |
| collection | MIT |
| description | Shared expectations and mutual understanding are critical facets of teamwork. Achieving these in human-robot collaborative contexts can be especially challenging, as humans and robots are unlikely to share a common language to convey intentions, plans, or justifications. Even in cases where human co-workers can inspect a robot's control code, and particularly when statistical methods are used to encode control policies, there is no guarantee that meaningful insights into a robot's behavior can be derived or that a human will be able to efficiently isolate the behaviors relevant to the interaction. We present a series of algorithms and an accompanying system that enables robots to autonomously synthesize policy descriptions and respond to both general and targeted queries by human collaborators. We demonstrate applicability to a variety of robot controller types including those that utilize conditional logic, tabular reinforcement learning, and deep reinforcement learning, synthesizing informative policy descriptions for collaborators and facilitating fault diagnosis by non-experts. |
| first_indexed | 2024-09-23T15:12:56Z |
| format | Article |
| id | mit-1721.1/116013 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T15:12:56Z |
| publishDate | 2018 |
| publisher | Association for Computing Machinery (ACM) |
| record_format | dspace |
| spelling | mit-1721.1/1160132022-10-02T01:24:34Z Improving Robot Controller Transparency Through Autonomous Policy Explanation Hayes, Bradley H Shah, Julie A Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Hayes, Bradley H Shah, Julie A Shared expectations and mutual understanding are critical facets of teamwork. Achieving these in human-robot collaborative contexts can be especially challenging, as humans and robots are unlikely to share a common language to convey intentions, plans, or justifications. Even in cases where human co-workers can inspect a robot's control code, and particularly when statistical methods are used to encode control policies, there is no guarantee that meaningful insights into a robot's behavior can be derived or that a human will be able to efficiently isolate the behaviors relevant to the interaction. We present a series of algorithms and an accompanying system that enables robots to autonomously synthesize policy descriptions and respond to both general and targeted queries by human collaborators. We demonstrate applicability to a variety of robot controller types including those that utilize conditional logic, tabular reinforcement learning, and deep reinforcement learning, synthesizing informative policy descriptions for collaborators and facilitating fault diagnosis by non-experts. 2018-05-31T13:48:22Z 2018-05-31T13:48:22Z 2017-03 2018-04-10T16:44:38Z Article http://purl.org/eprint/type/ConferencePaper 9781450343367 http://hdl.handle.net/1721.1/116013 Hayes, Bradley, and Julie A. Shah. “Improving Robot Controller Transparency Through Autonomous Policy Explanation.” Proceedings of the 2017 ACM/IEEE International Conference on Human-Robot Interaction - HRI ’17 (2017). https://orcid.org/0000-0003-1338-8107 http://dx.doi.org/10.1145/2909824.3020233 Proceedings of the 2017 ACM/IEEE International Conference on Human-Robot Interaction - HRI '17 Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Association for Computing Machinery (ACM) MIT Web Domain |
| spellingShingle | Hayes, Bradley H Shah, Julie A Improving Robot Controller Transparency Through Autonomous Policy Explanation |
| title | Improving Robot Controller Transparency Through Autonomous Policy Explanation |
| title_full | Improving Robot Controller Transparency Through Autonomous Policy Explanation |
| title_fullStr | Improving Robot Controller Transparency Through Autonomous Policy Explanation |
| title_full_unstemmed | Improving Robot Controller Transparency Through Autonomous Policy Explanation |
| title_short | Improving Robot Controller Transparency Through Autonomous Policy Explanation |
| title_sort | improving robot controller transparency through autonomous policy explanation |
| url | http://hdl.handle.net/1721.1/116013 https://orcid.org/0000-0003-1338-8107 |
| work_keys_str_mv | AT hayesbradleyh improvingrobotcontrollertransparencythroughautonomouspolicyexplanation AT shahjuliea improvingrobotcontrollertransparencythroughautonomouspolicyexplanation |