Swarm Intelligence Motion Planning

Multi-agent motion planning has recently attracted much interest in the research community and has many applications including robot navigation among pedestrians, self-driving cars, and drone shows. This problem: 1) concerns finding a one-to-one assignment between a set of given agents’ initial locations and the corresponding destination locations and 2) finding the continuous trajectories connecting each agent’s initial position to its goal location.

Using motion functions, the agents should be able to reach their goal destinations without colliding with each other or environmental obstacles. Also, the motion planning algorithm should be able to satisfy constraints, such as the maximum velocity of the agents, and the minimum required separation distance between them. In this project we try to balance between robustness, scalability, optimality, low computational and communication overhead, being fast, real-time and flexible goals using swarm intelligence, deep learning, and other approaches.