Tal Regev, M.Sc. Thesis Seminar
Wednesday, 20.7.2016, 13:00
Collaboration between multiple robots (or agents) pursuing common or individual tasks is important in numerous problem domains, including cooperative autonomous navigation, mapping and 3D reconstruction, tracking and active sensing. A key required capability is to autonomously determine robot actions while taking into account different sources of uncertainty. The corresponding approaches, known as belief space planning, represent the states of interest (e.g. robot or camera pose, objects) via a probability distribution function and reason how the latter changes as a result of different actions.
In this research we develop a new approach for decentralized multi-robot belief space planning in high dimensional state spaces while operating in unknown environments. State of the art approaches often address related problems within a sampling based motion planning paradigm, where robots generate candidate paths and choose the best paths according to a given objective function. As exhaustive evaluation of all candidate path combinations from different robots is computationally intractable, a commonly used (sub-optimal) framework is for each robot, at each time epoch, to evaluate its own candidate paths while only considering the best paths announced by other robots. Yet, even this approach can become computationally expensive, especially for high dimensional state spaces and for numerous candidate paths that need to be evaluated. In particular, upon an update in the announced path from one of the robots, state of the art approaches re-evaluate belief evolution for all candidate paths and do so from scratch. In this work we develop a framework to identify and efficiently update only those paths that are actually impacted as a result of an update in the announced path. Our approach is based on appropriately propagating belief evolution along impacted paths while employing insights from factor graph and incremental smoothing for efficient inference that is required for evaluating the utility of each impacted path. We demonstrate our approach in a synthetic simulation.