In distributed mobile robot systems, autonomous robots accomplish complicated tasks through intelligent cooperation with each other. This paper presents behavior learning and online distributed evolution for cooperati...
详细信息
In distributed mobile robot systems, autonomous robots accomplish complicated tasks through intelligent cooperation with each other. This paper presents behavior learning and online distributed evolution for cooperative behavior of a group of autonomous robots. Learning and evolution capabilities are essential for a group of autonomous robots to adapt to unstructured environments. Behavior learning finds an optimal state-action mapping of a robot for a given operating condition. In behavior learning, a Q-learning algorithm is modified to handle delayed rewards in the distributedrobot systems. A group of robots implements cooperative behaviors through communication with other robots. Individual robots improve the state-action mapping through online evolution with the crossover operator based on the Q-values and their update frequencies. A cooperative material search problem demonstrated the effectiveness of the proposed behavior learning and online distributed evolution method for implementing cooperative behavior of a group of autonomous mobilerobots.
Reaching consensus is fundamental in distributed computing. For each execution of a consensus algorithm, there is no difference between the proposed values by different nodes with respect to their proposed times. By p...
详细信息
ISBN:
(纸本)9783030483401;9783030483395
Reaching consensus is fundamental in distributed computing. For each execution of a consensus algorithm, there is no difference between the proposed values by different nodes with respect to their proposed times. By presenting a realistic application scenario related to distributed asynchronous mobilerobots in dynamic environments, we argue some safety-critical, real-time systems require reaching consensus on the newest proposed values when the old proposed values may not be valid anymore. Afterward, we formulate a new type of consensus problem called time-based consensus, which requires to take into account the times of proposed values. Finally, to tackle such a consensus problem, we determine an essential characteristic which should be considered.
暂无评论