MATLAB® package that provides, through a user-friendly API, methods to model multi-robot coordination problems as generalized stochastic Petri nets with rewards (GSPNR). This formalism provides a compact way of capturing: action selection, uncertainty on the duration of action execution, and team goals. This package also implements algorithms that obtain optimal policies for the GSPNR model, while reasoning over uncertainty and optimizing team-level objectives. Furthermore, it is also integrated with ROS middleware and thus managing the execution in real multi-robot systems.
Clone the repo:
git clone https://github.com/cazevedo/multi-robot-gspnr-toolbox.gitRun the install.m script on MATLAB and you will be directed to the GettingStarted.mlx live script.
Follow the GettingStarted.mlx live script.