arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.09914cs.ROcs.LG
收藏

比较SONN类型在位形空间中的有效机器人运动规划

Comparing SONN Types for Efficient Robot Motion Planning in the Configuration Space

FZI Research Center for Information Technology(FZI信息技术研究中心)

Lea Steffen, Tobias Weyer, Katharina Glueck, Stefan Ulbrich, Arne Roennau, Rüdiger Dillmann

摘要:

配置空间(C空间)中的运动规划带来了诸如平滑轨迹的益处。随着自由度(DOF)的增加,它变得更加复杂。这是由于搜索空间的维数和DOF之间的直接关系。自组织神经网络(SONN)及其著名的候选者自组织映射(Self-Organizing Map)已被证明是C空间约简的有用工具,同时保留其底层拓扑结构,如[29]所示。在这项工作中,我们扩展了我们以前的研究与额外的模型,并适应从人类运动数据的方法对机器人的运动学。评估包括来自[29]的最佳性能模型和三个额外的SONN架构,代表了先前工作的后续延续。生成的轨迹,计划与不同的SONN模型,成功地在机器人模拟测试。

英文摘要:

Motion planning in the configuration space (C-space) induces benefits, such as smooth trajectories. It becomes more complex as the degrees of freedom (DOF) increase. This is due to the direct relation between the dimensionality of the search space and the DOF. Self-organizing neural networks (SONN) and their famous candidate, the Self-Organizing Map, have been proven to be useful tools for C-space reduction while preserving its underlying topology, as presented in [29]. In this work, we extend our previous study with additional models and adapt the approach from human motion data towards robots' kinematics. The evaluation includes the best performant models from [29] and three additional SONN architectures, representing the consequent continuation of this previous work. Generated Trajectories, planned with the different SONN models, were successfully tested in a robot simulation.

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。

↑