From Bayesian Decision-Makers to Bayesian Agents
Proceedings of the 2005 conference on Self-Organization and Autonomic Informatics (I)
A multiagent system for helping urban traffic management
IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 2
| Hi-index | 0.00 |
This paper puts forward a method for calculating the optimum duration for every group of intersection controllers working on the same cycle. It uses a process of deep reasoning to deal with problems related to uncertainty and unavailability of sensor data. Furthermore, this process is constrained by soft temporal deadlines. Its execution can be disturbed by interactions of other agents or by external control actions performed by the human operator. The method is implemented as the primary task of an agent which collaborates with other agents to deal with various open problems concerning urban traffic. This paper shows that its execution, in isolation or together with other agents, is stable and provides suitable results.