Dual execution of optimized contact interaction trajectories
Dual execution of optimized contact interaction trajectories
复制标题
优化接触交互轨迹的双重执行
DOI：
10.1109/iros.2014.6942539
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
S. Schaal
中科院分区：
文献类型：
--
作者：
Marc Toussaint;Nathan D. Ratliff;J. Bohg;L. Righetti;Péter Englert;S. Schaal
有效的操作需要接触，以减少不确定性。操纵文献将其称为funerals：一种通过利用触觉反馈和控制环境交互来提高可靠性和鲁棒性的方法。然而，在传统的轨迹优化方法和函数的鲁棒性概念之间存在根本性的差距：传统的轨迹优化器没有发现力反馈策略。从POMDP的角度来看，这些行为可以被视为明确的观察行动计划，以充分减少不确定性，从而使任务。虽然我们赞同完整的POMDP观点，但在高维中解决完整的连续空间POMDP是困难的。在本文中，我们提出了一种替代方法，其中轨迹优化目标增加了新的条款，奖励通过接触减少不确定性，明确促进有趣。这种增强将鲁棒性的责任转移到优化轨迹的实际执行上。直接跟踪轨迹通过配置空间将失去所有的鲁棒性对偶执行通过设计力控制器来再现编码在优化问题的对偶解中的时间交互配置文件来实现鲁棒性。这项工作深入介绍了双重执行，并通过模拟和真实世界机器人平台上的鲁棒性实验分析了其性能。
Efficient manipulation requires contact to reduce uncertainty. The manipulation literature refers to this as funneling: a methodology for increasing reliability and robustness by leveraging haptic feedback and control of environmental interaction. However, there is a fundamental gap between traditional approaches to trajectory optimization and this concept of robustness by funneling: traditional trajectory optimizers do not discover force feedback strategies. From a POMDP perspective, these behaviors could be regarded as explicit observation actions planned to sufficiently reduce uncertainty thereby enabling a task. While we are sympathetic to the full POMDP view, solving full continuous-space POMDPs in high-dimensions is hard. In this paper, we propose an alternative approach in which trajectory optimization objectives are augmented with new terms that reward uncertainty reduction through contacts, explicitly promoting funneling. This augmentation shifts the responsibility of robustness toward the actual execution of the optimized trajectories. Directly tracing trajectories through configuration space would lose all robustness-dual execution achieves robustness by devising force controllers to reproduce the temporal interaction profile encoded in the dual solution of the optimization problem. This work introduces dual execution in depth and analyze its performance through robustness experiments in both simulation and on a real-world robotic platform.
影响因子：
9.2
作者：
Eppner, Clemens;Deimel, Raphael;Brock, Oliver
通讯作者：
Brock, Oliver