Multi-Task Agent Hybrid Control in Sparse Maps and Complex Environmental Conditions

Abstract With the rapid development of space exploration technology, the detection of extraterrestrial bodies has become increasingly important. Among these, path planning and target recognition and positioning technologies are particularly critical for applications in intelligent agents with low computational power operating in complex environments. This paper introduces an A* path planning algorithm with an adaptive heuristic function, which demonstrates improved robustness in low-resolution maps and can plan paths that stay as far away from obstacles as possible, even when the accuracy of the prior map is limited. Additionally, this study proposes a Dynamic Environment Target Identification and Localization (DETIL) algorithm, which includes the identification of unknown obstacles and the spatio-temporal dimension clustering to locate points of interest. Simulation results of the mixed control scheme using both algorithms indicate that the improved A* algorithm reduces the maximum elevation difference by 55% and the maximum cumulative elevation difference by 68% compared to the traditional A* algorithm. The unknown obstacle identification component of the DETIL algorithm can recognize all obstacles along the path, while the spatio-temporal dimension clustering section improves the average number of target discoveries by 152% over the conventional DBSCAN clustering approach.