2010 Fiscal Year Final Research Report
Automated Generation of Heuristics Using Genetic Programming
| Project/Area Number |
20700131
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Tokyo Institute of Technology |
|---|
Principal Investigator |
福永 Alex Tokyo Institute of Technology, 大学院・総合文化研究科, 准教授 (90452002)
|
|---|
| Project Period (FY) |
2008 – 2010
|
| Keywords | 人工知能 / 進化計算 |
|---|
| Research Abstract |
Developing effective algorithms for constraint satisfaction and optimization, including task allocation and automated planning in robots and autonomous agents, is a difficult problem. We investigated the use of genetic programming for automatically generating heuristics to solve difficult optimization and constraint satisfaction problems. Using a parallel genetic programming system on a large-scale parallel cluster, we generated new, effective heuristics for SAT. We also used genetic programming to generate action selection heuristics for a museum guide robot. In addition, we also developed new exact and heuristic methods for the multiple knapsack problem.
|
