Design of the peer agent for multi-robot communication in an agent-based robot control architecture
The role of communication among mobile robots remains one of the most important issues in multi-agent robotics system design. There are many research groups currently working on communication and cooperation among robots. Cooperation requires communication whenever one’s actions depend critically on the knowledge that is accessible only from others. In the Intelligent Robotics Laboratory at Vanderbilt University, we are currently developing a method for robots to communicate and share knowledge with each other. We have developed the concept of the Peer Agent that will enable robots to exchange information between one another. The research experiment, described in this thesis, involved two mobile robots; Skeeter, a Pioneer 2-AT robot and Scooter, an ATRV-Jr robot. We will show that knowledge sharing through Peer Agents can lead to a more stable, robust and efficient cooperation between robots.
This item appears in the following collection(s):
Showing items related by title, author, creator and subject.
Rojas, Juan Luis (2009-04-07)Department: Electrical EngineeringRecent goals in space missions require innovative technologies to develop and to build infrastructure for space exploration. NASA plans to have robots construct modular systems and habitats and prepare them for life support ...
Sidek, Shahrul Naim (2008-11-12)Department: Electrical EngineeringDYNAMIC MODELING AND CONTROL OF NONHOLONOMIC WHEELED MOBILE ROBOT SUBJECTED TO WHEEL SLIP<P> SHAHRUL NAIM SIDEK<P> Improving navigation performance of autonomous wheeled mobile robot (WMR) in a dynamic unstructured ...
Investigating the cognitive processing of experience for decision making in robots: accounting for internal states and appraisals Gordon, Stephen Michael (2009-04-09)Department: Electrical EngineeringReal-time search techniques have been used extensively in the areas of task planning and decision making. In order to be effective, however, these techniques require task-specific domain knowledge in the form of heuristic ...