Local Real-Time Motion Planning Using Evolutionary Optimization

In order to allow for flexible realization of diverse navigation tasks of mobile robots, objective-based motion planner proved to be very successful. The quality of a selected control command for a certain time step is inherently connected to the considered diversity of future trajectories. Therefore, we propose an evolutionary motion planning (EMP) method to solve this high-dimensional search problem without restricting the search space. The algorithm optimizes sequences of acceleration commands with respect to objective functions for evaluating the resulting movement trajectories. The method has been successfully deployed on two robots with differential drive, and experiments showed that it outperforms the Dynamic Window Approach [1] with its restricted discretized search space. Furthermore, car-like and holonomic robots could be controlled successfully in simulations.