Post-hoc Reconstruction of Plans by Situated Actions
|
Accession number;05A0661028
|
| Title;Post-hoc Reconstruction of Plans by Situated Actions |
| Author;
LEE SERIN
(Univ. Tokyo, Graduate School, JPN)
KUBOTA TAKASHI
(Japan Aerospace Exploration Agency, JPN)
NAKATANI ICHIRO
(Japan Aerospace Exploration Agency, JPN)
|
Journal Title;Proceedings of the Annual Conference on JSAI (CD-ROM)
|
Journal Code:X0580B
|
ISSN:
|
|
VOL.19th;NO.;PAGE.1A1-04(2005)
|
| Figure&Table&Reference;FIG.5, REF.11 |
| Pub. Country;Japan |
| Language;Japanese |
| Abstract;The approaches to make an agent generate intelligent actions in the AI field might be very roughly categorized into two ways-the classical planning and situated action system. However, each system actually has its own application field as well as its strength and weakeness, and, in particular, the application of the situated action system is usually restricted to the field such as the navigation of mobile robots which is not directly related to the logical problem. This paper proposes a novel action generator to situatedly extract a set of actions from the relaxed logical space, which is likely to help to achieve the goal at the current situation. After performing the action set, the agent should recognize the situation for deciding the next likely action set. The empirical result in some planning domains shows that the quality of the resultant path to the goal, post-hoc reconstruction of plans, is mostly acceptable as well as deriving the fast response time. Therefore, this approach could make the agent such as mobile robots and web agents in the dynamic environment respond to the environment fast. (author abst.) |
|
|
|
Related Articles;
|
|
