arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.00563cs.RO
收藏

运动学关节约束下的机器人轨迹学习

Learning Robot Trajectories subject to Kinematic Joint Constraints

Karlsruhe Institute of Technology (KIT)(卡尔斯鲁厄理工学院)

Jonas C. Kiemel, Torsten Kröger

摘要:

我们提出了一种方法来学习快速和动态的机器人运动,而不超过限制的位置$θ$,速度$\dotθ$,加速度$\ddotθ$和加加速度$\dddotθ$的每个机器人关节。通过将神经网络的预测映射到安全可执行的关节加速度来生成运动。神经网络被周期性地调用并通过强化学习进行训练。我们的主要贡献是计算安全关节加速度的分析程序,它认为预测频率$f_N$的神经网络。结果,频率$f_N$可以被自由选择并被视为超参数。我们表明,我们的方法是最好的惩罚违反约束,因为它提供了明确的保证,并没有扭曲所需的优化目标。此外,所选择的预测频率对学习性能和计算工作量的影响是突出的各种实验。

英文摘要:

We present an approach to learn fast and dynamic robot motions without exceeding limits on the position $θ$, velocity $\dotθ$, acceleration $\ddotθ$ and jerk $\dddotθ$ of each robot joint. Movements are generated by mapping the predictions of a neural network to safely executable joint accelerations. The neural network is invoked periodically and trained via reinforcement learning. Our main contribution is an analytical procedure for calculating safe joint accelerations, which considers the prediction frequency $f_N$ of the neural network. As a result, the frequency $f_N$ can be freely chosen and treated as a hyperparameter. We show that our approach is preferable to penalizing constraint violations as it provides explicit guarantees and does not distort the desired optimization target. In addition, the influence of the selected prediction frequency on the learning performance and on the computing effort is highlighted by various experiments.

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。

↑