We consider the coordinated escort problem, where a decentralised team of supporting robots implicitly assist the mission of higher-value principal robots. The defining challenge is how to evaluate the effect of supporting robots' actions on the principal robots' mission. To capture this effect, we define two novel auxiliary reward functions for supporting robots called satisfaction improvement and satisfaction entropy, which computes the improvement in probability of mission success, or the uncertainty thereof. Given these reward functions, we coordinate the entire team of principal and supporting robots using decentralised cross entropy method (Dec-CEM), a new extension of CEM to multi-agent systems based on the product distribution approximation. In a simulated object avoidance scenario, our planning framework demonstrates up to two-fold improvement in task satisfaction against conventional decoupled information gathering. The significance of our results is to introduce a new family of algorithmic problems that will enable important new practical applications of heterogeneous multi-robot systems.

Mobile robot navigation is an essential problem in robotics. We propose a method for constructing and training fuzzy logic controllers (FLCs) to coordinate a robotic team performing collision-free navigation and arriving simultaneously at a target location in an unknown environment. Our FLCs are organized in a multilayered architecture to reduce the number of tunable parameters and improve the scalability of the solution. In addition, in contrast to simple traditional switching mechanisms between target seeking and obstacle avoidance, we develop a novel rule-embedded FLC to improve the navigation performance. Moreover, we design a grouping and merging mechanism to obtain transparent fuzzy sets and integrate this mechanism into the training process for all FLCs, thus increasing the interpretability of the fuzzy models. We train the proposed FLCs using a novel multiobjective hybrid approach combining a genetic algorithm and particle swarm optimization. Simulation results demonstrate the effectiveness of our algorithms in reliably solving the proposed navigation problem.

We present a hierarchical neural-fuzzy system for precision coordination of multiple mobile agents for simultaneous arrival at their destination positions in a cluttered urban environment. We assume that each agent is equipped with a 2D scanning LiDAR to make movement decisions based on local distance and bearing information. Two solution approaches are considered and compared. Both of them are structured around a hierarchical arrangement of controller modules to enable synchronisation of the agents arrival times while avoiding collision with obstacles. The first approach is based on cascading SONFIN (Self-Organizing Neural Fuzzy Inference Network) controllers, and the second approach considers the use of an LSTM (Long ShortTerm Memory) recurrent neural network module alongside SONFIN modules. Parameters of all the controllers are optimised using the Particle Swarm optimization algorithm. A physics-based simulator, Webots, is used as a training and testing environment for the two learning models to facilitate the deployment of codes to hardware which will follow in the next phase of our research.