Evolution of Solitary and Group Transport Behaviors for Autonomous Robots Capable of Self-Assembling
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Strengths and synergies of evolved and designed controllers: A study within collective robotics
Artificial Intelligence
Teamwork in self-organized robot colonies
IEEE Transactions on Evolutionary Computation
Decentralized cooperative manipulation with a swarm of mobile robots
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
A path planning method for dynamic object closure by using random caging formation testing
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Cooperative caging and transport using autonomous aquatic surface vehicles
Intelligent Service Robotics
Dynamics model abstraction scheme using radial basis functions
Journal of Control Science and Engineering - Special issue on Dynamic Neural Networks for Model-Free Control and Identification
Hi-index | 0.00 |
This paper addresses the function distribution and behavior design problem for a multirobot system which incorporates a behavior-based dynamic cooperation strategy for object handling. The proposed multiple robot system is composed of a managing robot and homogeneous behavior-based robots. The cooperation strategy in this system is realized in two steps: designing the distributed robot's cooperative behavioral attributes according to the robot's abilities, and organizing these behavioral attributes so that team cooperation is realized. For indicating an incremental style of local behavior construction, an advanced design of cooperative behavior for coping with unknown disturbance is addressed. Additionally, two extended cooperation strategies designed for a path tracking task are described. These three strategies are based on the same concept on performing manipulation in coordination. Therefore, by considering the function distribution among the managing robot and worker robots, and considering behavior design of each worker robot, the proposed system is able to achieve the object handling task with different performances according to the task requirement, such as with or without path tracking and with or without contact with the environment. Experimental results demonstrate the applicability of the proposed system.