Distributed Multi-Robot Coordination Combining Semantics and Real-Time Scheduling

Abstract

In this paper, we study a distributed intelligent multi-robot system (MRS) in assembly setting where robots have partially overlapping capabilities. We treat the problem of the system’s real-time self-(re)configurability and self-optimization. In this light, we propose an optimized distributed coordination system ORCAS that integrates the MRS configuration based on semantic descriptions and process scheduling. In more detail, initially, robots and the corresponding devices get matched semantically to respond to the assembly requests. Then, the best configurations are chosen by dynamically minimizing total assembly costs and off-line times. During the execution, the performance is controlled for contingencies in case of which the robots, if necessary, self-reconfigure or reschedule the tasks.