据mil-embedded网2020年1月12日报道,美国人工智能系统解决方案研发企业查尔斯河分析公司获得DARPR“攻击群使能战术” (OFFSET) 计划经费,开发“强健群策略元强化学习创新”(MERLIN-RST)项目,通过运用元强化学习方法探索新的群体智能策略。通过生物启发算法和深度机器学习,OFFSET计划旨在促使蜂群实现任务目标。为实现OFFSET计划的“第四次蜂群冲刺”目标,MERLIN研究人员将增加OFFSET模拟样机,以模拟各种城市环境的蜂群战能力。

Autonomous learning applied to robotic swarm tactics

CAMBRIDGE, Mass. Charles River Analytics Inc., developer of intelligent systems solutions, received funding from the Defense Advanced Research Projects Agency (DARPA) under the OFFensive Swarm-Enabled Tactics (OFFSET) program to develop Meta-Reinforcement Learning Innovation for Robust Swarm Tactics (MERLIN-RST). MERLIN applies a meta-reinforcement learning approach to discover and learn novel swarm tactics.

Through biology-inspired algorithms and deep machine learning, tactics in the OFFSET program are intended to help swarms achieve and adapt to mission objectives.

According to the company, human programmers cannot support the evolution of these tactics quickly or accurately enough due to numerous variants in adversary strategy and evolving environments that make manual development a challenge.

Under the MERLIN effort, researchers will augment OFFSET simulators to model swarm performance in a wide range of challenging urban environments as part of the OFFSET Program’s Fourth Swarm Sprint.