An unmanned ship cluster distributed cooperative path planning method and system

Abstract

The application discloses an unmanned ship cluster distributed cooperative path planning method and system, and the core of the application is that each unmanned ship intelligent agent firstly constructs a future space-time risk map through probabilistic prediction; when a potential collision conflict is detected, the relevant unmanned ship will not need intervention of a central node, but through a distributed negotiation mechanism, through bidding of a multi-objective comprehensive cost required for avoiding the conflict by each unmanned ship, finally, the party with a lower cost initiatively assumes the responsibility of avoiding the conflict, so that the cooperative path optimal for the whole cluster is achieved. Through probabilistic prediction, distributed negotiation and dynamic multi-objective optimization, the safety, self-adaptability and scalability of the unmanned ship cluster path planning are remarkably improved, the communication cost is greatly reduced, and efficient, safe and intelligent autonomous cooperation in a complex environment is realized.

Images