A particle swarm optimization approach using adaptive entropy-based fitness quantification of expert knowledge for high-level, real-time cognitive robotic control

Abstract: High-level, real-time mission control of semi-autonomous robots, deployed in remote and dynamic environments, remains a challenge. Control models, learnt from a knowledgebase, quickly become obsolete when the environment or the knowledgebase changes. This research study introduces a cognitive reasoning process, to select the optimal action, using the most relevant knowledge from the knowledgebase, subject to observed evidence. The approach in this study introduces an adaptive entropy-based set-based particle swarm algorithm (AE-SPSO) and a novel, adaptive entropy-based fitness quantification (AEFQ) algorithm for evidence-based optimization of the knowledge. The performance of the AE-SPSO and AEFQ algorithms are experimentally evaluated with two unmanned aerial vehicle (UAV) benchmark missions: (1) relocating the UAV to a charging station and (2) collecting and delivering a package. Performance is measured by inspecting the success and completeness of the mission and the accuracy of autonomous flight control. The results show that the AE-SPSO/AEFQ approach successfully finds the optimal state-transition for each mission task and that autonomous flight control is successfully achieved.