Carnegie Mellon Robotics Institute
Bin Yu, Paul Scerri, Katia Sycara, Yang Xu, and
Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), 2006.
| Download |
|
| Abstract |
| This paper studies scalable data delivery algorithms in mobile ad hoc sensor networks with node and link failures. Many algorithms have been developed for data delivery and fusion in static microsensor networks, but most of them are not appropriate for mobile sensor networks due to their heavy traffic and long latency. In this paper we propose an efficient and robust data delivery algorithm for distributed data fusion in mobile ad hoc sensor networks, where each node controls its data flows and learns routing decisions solely based on their local knowledge. We analyze the localized algorithm in a formal model and validate our model using simulations. The experiments indicate that controlled data delivery processes significantly increase the probability of relevant data being fused in the network even with limited local knowledge of each node and relatively small hops of data delivery. |
| Keywords |
| sensor data fusion, data delivery, reinforcement learning |
| Notes |
Associated Center(s) / Consortia:
Center for Integrated Manfacturing Decision Systems Associated Lab(s) / Group(s):
Advanced Agent - Robotics Technology Lab Number of pages: 8 |
| Text Reference |
| Bin Yu, Paul Scerri, Katia Sycara, Yang Xu, and , "Scalable and Reliable Data Delivery in Mobile Ad Hoc Sensor Networks," Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), 2006. |
| BibTeX Reference |
|
@inproceedings{Yu_2006_5451, author = "Bin Yu and Paul Scerri and Katia Sycara and Yang Xu and ", title = "Scalable and Reliable Data Delivery in Mobile Ad Hoc Sensor Networks", booktitle = "Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS)", year = "2006", } |
| The Robotics Institute is part of the School of Computer Science, Carnegie Mellon University. Contact Us | Update Instructions |