Robot navigation with predictive capabilities using graph learning and Monte Carlo tree search
Robot navigation with predictive capabilities using graph learning and Monte Carlo tree search
复制标题
DOI：
10.1177/09596518221140934
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Yifan Wang;Yanling Wei;Xueliang Huang;Shan Gao;Hongyan Zou
中科院分区：
文献类型：
--
作者：
Yifan Wang;Yanling Wei;Xueliang Huang;Shan Gao;Hongyan Zou
针对机器人在复杂动态环境中的导航问题，提出了一种基于图神经网络的预测和路径规划系统。特别是，这种方法的核心是预测那些与规划直接相关的未来方面，包括它们的价值、状态和政策。介绍了一种基于图神经网络的方法来编码机器人与周围环境之间的相互作用。然后，通过基于模型的强化学习来学习环境的动态模型，并根据学习到的模型使用蒙特卡洛树搜索方法来规划路径。最后，通过仿真研究，与现有方法相比，验证了该算法的有效性和优越性。结果表明，该方法在更短的时间内实现了更高的成功率。同时，避免了机器人因近视而引起的摆动和冻结问题。
This article develops a prediction and path planning system based on the graph neural network to navigate a robot in a complex dynamic environment. In particular, the core of this method is to predict those aspects of the future that are directly relevant for planning, including their value, state, and policy. A graph neural network-based method is introduced to encode the interaction between the robot and the surrounding environment. Then, the dynamic model of the environment is learned through the model-based reinforcement learning, and the path is planned using the Monte Carlo tree search method according to the learned model. Finally, simulation studies are given to evaluate the validity and advantage of the obtained algorithm compared with the most recent methods. It has been shown that the proposed method achieves a higher success rate within a less time. Meantime, the oscillatory and freezing problems caused by the short-sightedness of the robot are avoided.