Abstract
Goal recognition is the problem of inferring the (unobserved) goal of an agent, based on a sequence of its observed actions. Inspired by mirroring processes in human brains, we advocate goal mirroring, an online recognition approach that uses a black-box planner to generate recognition hypotheses. This approach avoids the prevalent assumption in current approaches, which rely on a dedicated plan library, representing all known plans to achieve known goals. Such methods are inherently limited to the knowledge represented in the library. In this paper, we (i) describe a novel online goal mirroring algorithm for continuous spaces; (ii) evaluate a novel heuristic for choosing between competing recognition hypotheses; (iii) contrast machine and human recognition in two challenging domains, revealing insights as to human capabilities; and (iv) compare mirroring to library-based methods.
| Original language | English |
|---|---|
| Title of host publication | Fourth Annual Conference on Advances in Cognitive Systems |
| Subtitle of host publication | June 23-26, 2016, Evanston, Illinois |
| Editors | Kenneth Forbus, Tom Hinrichs, Carrie Ost |
| Place of Publication | Kirkland WA USA |
| Publisher | Cognitive Systems Foundation |
| Number of pages | 13 |
| Publication status | Published - 2016 |
| Externally published | Yes |
| Event | Annual Conference on Advances in Cognitive Systems 2016 - Evanston, United States of America Duration: 23 Jun 2016 → 26 Jun 2016 Conference number: 4th http://www.cogsys.org/2016 |
Publication series
| Name | Advances in Cognitive Systems |
|---|---|
| ISSN (Print) | 2324-8416 |
Conference
| Conference | Annual Conference on Advances in Cognitive Systems 2016 |
|---|---|
| Country/Territory | United States of America |
| City | Evanston |
| Period | 23/06/16 → 26/06/16 |
| Internet address |