arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.00568cs.LGstat.ML
收藏

基于全卷积神经网络的多智能体一次性路径规划

One-shot path planning for multi-agent systems using fully convolutional neural network

University of Göttingen(哥廷根大学);Vytautas Magnus University(维陶塔斯·马格努斯大学)

Tomas Kulvicius, Sebastian Herzog, Timo Lüddecke, Minija Tamosiunaite, Florentin Wörgötter

摘要:

路径规划在机器人动作执行中起着至关重要的作用,因为在执行动作之前必须首先定义特定动作的路径或运动轨迹。大多数当前方法是迭代法,其中通过基于当前状态预测下一状态来迭代地生成轨迹。此外,在多代理系统的情况下,路径分别为每个代理计划。与此相反,我们提出了一种新的方法,通过充分利用卷积神经网络,它允许生成完整的路径,甚至为一个以上的代理,在一个镜头,即,一步预测。我们证明,我们的方法是能够成功地产生最佳或接近最佳路径的情况下,超过98%的单路径预测。此外,我们表明,虽然网络从未受过多路径规划的训练,但在生成两条和三条路径时,它也能够分别在85.7%和65.4%的情况下生成最优或接近最优的路径。

英文摘要:

Path planning plays a crucial role in robot action execution, since a path or a motion trajectory for a particular action has to be defined first before the action can be executed. Most of the current approaches are iterative methods where the trajectory is generated iteratively by predicting the next state based on the current state. Moreover, in case of multi-agent systems, paths are planned for each agent separately. In contrast to that, we propose a novel method by utilising fully convolutional neural network, which allows generation of complete paths, even for more than one agent, in one-shot, i.e., with a single prediction step. We demonstrate that our method is able to successfully generate optimal or close to optimal paths in more than 98\% of the cases for single path predictions. Moreover, we show that although the network has never been trained on multi-path planning it is also able to generate optimal or close to optimal paths in 85.7\% and 65.4\% of the cases when generating two and three paths, respectively.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑