A Real-Time Negotiation Model and A Multi-Agent Sensor Network Implementation
Autonomous Agents and Multi-Agent Systems
| Hi-index | 0.00 |
The DRESUN testbed for research on distributed situation assessment (DSA) was developed to explore the implications of having agents with more sophisticated evidential representations and control capabilities than the agents that were used in our earlier research with the Distributed Vehicle Monitoring Testbed (DVMT). In DRESUN, communication among the agents is driven by the goal of determining the global consistency of local agent solutions, with unresolved global consistency questions viewed as sources of uncertainty about the correctness of local agent solutions. This paper reports on issues that have arisen in modeling the beliefs of other agents when dealing with inter-agent communication of incomplete and conflicting evidence, and evidence at multiple levels of abstraction. Experimentation showed that extensions to the DRESUN model of external evidence were necessary to better represent the uncertainties that occur when DRESUN agents exchange such information. These are important issues since DSA agents typically must exchange much information in order to meet their goals. Furthermore, because DSA agents require evidential representations, this work is different from DAI work that has used justification-based representations of belief and has focused on methods for automatically maintaining (some level of) global consistency. Initial experimentation has been done with a variety of simulated distributed aircraft monitoring scenarios involving local solutions that are globally inconsistent and local solution uncertainty that can be resolved only through agent interactions. These experiments suggest that DRESUN agents have the flexibility to support the complex communication protocols and highly directed information exchanges that we believe are necessary to resolve global inconsistencies in DSA applications.