Risk-bounded coordination of human-robot teams through concurrent intent recognition and adaptation
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | eng |
| Published: |
Massachusetts Institute of Technology
2019
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/1721.1/121652 |
| _version_ | 1811089124272111616 |
|---|---|
| author | Levine, Steven James. |
| author2 | Brian C. Williams. |
| author_facet | Brian C. Williams. Levine, Steven James. |
| author_sort | Levine, Steven James. |
| collection | MIT |
| description | This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. |
| first_indexed | 2024-09-23T14:14:04Z |
| format | Thesis |
| id | mit-1721.1/121652 |
| institution | Massachusetts Institute of Technology |
| language | eng |
| last_indexed | 2024-09-23T14:14:04Z |
| publishDate | 2019 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1216522019-09-14T03:07:20Z Risk-bounded coordination of human-robot teams through concurrent intent recognition and adaptation Levine, Steven James. Brian C. Williams. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Electrical Engineering and Computer Science. This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019 Cataloged from student-submitted PDF version of thesis. Includes bibliographical references (pages 369-378). There is an ever-growing demand for humans and robots to work fluidly together in a number of important domains, such as home care, manufacturing, and medical robotics. In order to achieve this fluidity, robots must be able to (1) recognize their human teammate's intentions, and (2) automatically adapt to those intentions in an intelligent manner. This thesis makes progress in these areas by proposing a framework that solves these two problems (task-level intent recognition and robotic adaptation) concurrently and holistically, using a single model and set of algorithms for both. The result is a mixed-initiative human-robot interaction that achieves the team's goals. The robot is able to reason about the action requirements, timing constraints, and unexpected disturbances in order to adapt intelligently to the human. We extend this framework by additionally maintaining a probabilistic belief over the human's intentions. We develop a risk-aware executive that performs concurrent intent recognition and adaptation. Our executive continuously assesses the risk associated with plan execution, selects adaptations that are safe enough, asks uncertainty-reducing questions when appropriate, and provides a proactive early warning of likely failure. Finally, we present an extension to this work which enables the robot to save time by ignoring potentially many, vanishingly-unlikely scenarios. To achieve this behavior, we frame concurrent intent recognition and adaptation as a constraint satisfaction problem, and compactly represent their associated solutions and policies using compiled structures that are updated online as new observations arise. Through the use of these compiled structures, the robot efficiently reasons about which actions to perform, as well as when to perform them - thereby ensuring decision making consistent with the team's goals. by Steven James Levine. Ph. D. Ph.D. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science 2019-07-15T20:31:07Z 2019-07-15T20:31:07Z 2019 2019 Thesis https://hdl.handle.net/1721.1/121652 1102048633 eng MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission. http://dspace.mit.edu/handle/1721.1/7582 378 pages application/pdf Massachusetts Institute of Technology |
| spellingShingle | Electrical Engineering and Computer Science. Levine, Steven James. Risk-bounded coordination of human-robot teams through concurrent intent recognition and adaptation |
| title | Risk-bounded coordination of human-robot teams through concurrent intent recognition and adaptation |
| title_full | Risk-bounded coordination of human-robot teams through concurrent intent recognition and adaptation |
| title_fullStr | Risk-bounded coordination of human-robot teams through concurrent intent recognition and adaptation |
| title_full_unstemmed | Risk-bounded coordination of human-robot teams through concurrent intent recognition and adaptation |
| title_short | Risk-bounded coordination of human-robot teams through concurrent intent recognition and adaptation |
| title_sort | risk bounded coordination of human robot teams through concurrent intent recognition and adaptation |
| topic | Electrical Engineering and Computer Science. |
| url | https://hdl.handle.net/1721.1/121652 |
| work_keys_str_mv | AT levinestevenjames riskboundedcoordinationofhumanrobotteamsthroughconcurrentintentrecognitionandadaptation |