MAPF is an NP-hard problem. We are given a large pre-calculated set of paths. The aim is to select paths from this set such that they do not collide with static obstacles nor with each other. This selection should be calculated in near real-time, i.e., extremely faster than classic MAPF algorithms.
We investigate how Deep-Learning methods may speed up the search process. We train the NN to recognize patterns in the training examples and apply them to previously unseen settings of the problem.
The challenge of mapping indoor environments is addressed. Frontier-based methods calculation time may increase substantially as more areas are exposed. To overcome this limitation, we apply deep reinforcement learning to train the motion planner, and pre-trained generative deep neural network, acting as a map predictor. Hence, we improve the decision making through use of the learned structural statistics of the environment and ensure a constant calculation time. We show that combining the two methods can shorten the duration of the mapping process substantially.
This report, written under the supervision of Professor Alfred M. Bruckstein as part of a doctoral dissertation, surveys results on distributed systems comprising mobile agents that are identical and anonymous, oblivious and interact solely by adjusting their motion according to the relative location of their neighbours. The agents are assumed capable of sensing the presence of other agents within a given sensing range and able to implement rules of motion based on partial information on the geometric constellation of their neighbours.
