Automated Design of Simple and Robust Manipulators for Dexterous In-Hand Manipulation Tasks using Evolutionary Strategies

Automated Design of Simple and Robust Manipulators for Dexterous In-Hand Manipulation Tasks using Evolutionary Strategies
复制标题

DOI:
10.1109/humanoids43949.2019.9035055
复制
发表时间:
2019-10
期刊:
2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids)
影响因子:
--
通讯作者:
Andre Meixner;Christopher Hazard;N. Pollard
Andre Meixner;Christopher Hazard;N. Pollard
中科院分区:
其他
文献类型:
--
作者:
Andre Meixner;Christopher Hazard;N. Pollard

文献摘要

被引文献

相似文献

尽管取得了实质性进展,但稳健而灵巧的手动操作仍然是机器人技术的一大挑战。最近的研究表明,针对特定任务优化机器人手形态可以实现低成本、易于维护且功能强大的定制手设计。然而,在现实情况下,由此产生的操纵策略可能不是非常稳健或通用。本文表明,通过优化控制而不是接触力/轨迹,并在优化过程中明确考虑不确定性,可以显着提高鲁棒性。我们提出了一种基于进化算法的管道,用于共同优化手部形态和针对一系列问题和初始状态的控制策略,以实现鲁棒的手部操作。我们证明,这种方法可以利用手的所有表面和令人惊讶的动态运动产生可靠的结果。我们展示了优化联合极限值以创建稳健设计的优势。此外,我们证明我们的方法是基于轨迹优化的方法的补充,可用于提高此类结果的稳健性以及从头开始创建自定义手部设计。显示了相对于手掌重新定位和重新定向不同对象的结果。
In spite of substantial progress, robust and dexterous in-hand manipulation remains a robotics grand challenge. Recent research has shown that optimization of robot hand morphology for specific tasks can result in custom hand designs that are low-cost, easy to maintain, and highly capable. However, the resulting manipulation strategies may not be very robust or generalizable in real-world situations. This paper shows that robustness can be improved dramatically by optimizing controls instead of contact force / trajectories and by considering uncertainty explicitly during the optimization process. We present a evolutionary algorithm based pipeline for co-optimizing hand morphology and control strategy over families of problems and initial states in order to achieve robust in-hand manipulation. We demonstrate that this approach produces robust results which utilize all surfaces of the hand and surprising dynamic motions. We showcase the advantage of optimizing joint limit values to create robust designs. Furthermore, we demonstrate that our approach is complementary to trajectory optimization based approaches and can be utilized to improve robustness of such results as well as to create custom hand designs from scratch. Results are shown for repositioning and reorienting diverse objects relative to the palm of the hand.