| Presentation | 2004/1/22 A Study on a Route Search Method Using Experience in Disastar Environment SHINGO YONEDA, Yoshinobu KAJIKAWA, Yasuo NOMURA, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper, we describes shortest route search on rescue activities in the RoboCup rescue. The shortest route search is one of the basic and important functions in disaster relief activities. However, rescue agents can not know change of the environment by calamity. That is, this environment is Partially Observable Markov Decision Processes (POMDPs), and dose not guarantee existence of routes to a target. In such environment, the shortest route search is very difficult. Hence, it is important to bypass blocades and to arrive at a target. We have proposed a route search method using Bayesian Learning. This method can bypass blockades effectively by judging a safe road statistically from experience obtained by Bayesian Learning to this problem. However this method needs to execute Bayesian Learning in the environment which agents conducted rescue effort in advance. We therefore propose a new technique that predicts blocades from surrourding information of objective roads so as to adapt it to unknown environments using Neural Network(NN). Although this technique can adapt all route search methods, we use A (A-Star) method for the route search in this paper. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Route Search / Bayesian Learning / A-Star / RoboCup-Rescue |
| Paper # | AI2003-66 |
| Date of Issue |
| Conference Information | |
| Committee | AI |
|---|---|
| Conference Date | 2004/1/22(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Artificial Intelligence and Knowledge-Based Processing (AI) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Study on a Route Search Method Using Experience in Disastar Environment |
| Sub Title (in English) | |
| Keyword(1) | Route Search |
| Keyword(2) | Bayesian Learning |
| Keyword(3) | A-Star |
| Keyword(4) | RoboCup-Rescue |
| 1st Author's Name | SHINGO YONEDA |
| 1st Author's Affiliation | Faculty of Engineering, Kansai University() |
| 2nd Author's Name | Yoshinobu KAJIKAWA |
| 2nd Author's Affiliation | Faculty of Engineering, Kansai University:Frontier Science Center, Kansai University |
| 3rd Author's Name | Yasuo NOMURA |
| 3rd Author's Affiliation | Faculty of Engineering, Kansai University |
| Date | 2004/1/22 |
| Paper # | AI2003-66 |
| Volume (vol) | vol.103 |
| Number (no) | 623 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |