Based on soccer robotsimulation as its research platform, this paper studies the learning of high level strategy of multi-agent adversarial system.
本文以足球仿真机器人系统为研究平台,研究多智能体对抗系统的高层策略学习问题。
2
In this paper, the design methods and implementation of a 3d graphic robotsimulation module are researched as a general component of the open architecture robot controller.
In the computer simulation experiment, this method can efficiently implement robot path searching in the dynamic environment with both moving obstacles and moving targets.