Perception-Based Temporal Logic Planning in Uncertain Semantic Maps
This work addresses the problem of multi-robot planning under semantic uncertainty for robotics applications, representing an incremental advancement in robust task execution.
This paper tackles multi-robot planning in environments with partially unknown semantics, where landmarks have uncertain positions and classes. The authors developed a sampling-based algorithm that generates open-loop control policies, updated online, to adapt to a continuously learned semantic map, enabling robots to accomplish collaborative tasks specified by perception-based co-safe LTL.
This paper addresses a multi-robot planning problem in environments with partially unknown semantics. The environment is assumed to have known geometric structure (e.g., walls) and to be occupied by static labeled landmarks with uncertain positions and classes. This modeling approach gives rise to an uncertain semantic map generated by semantic SLAM algorithms. Our goal is to design control policies for robots equipped with noisy perception systems so that they can accomplish collaborative tasks captured by global temporal logic specifications. To specify missions that account for environmental and perceptual uncertainty, we employ a fragment of Linear Temporal Logic (LTL), called co-safe LTL, defined over perception-based atomic predicates modeling probabilistic satisfaction requirements. The perception-based LTL planning problem gives rise to an optimal control problem, solved by a novel sampling-based algorithm, that generates open-loop control policies that are updated online to adapt to a continuously learned semantic map. We provide extensive experiments to demonstrate the efficiency of the proposed planning architecture.