Efficient Humanoid Contact Planning using Learned Centroidal Dynamics Prediction

Efficient Humanoid Contact Planning using Learned Centroidal Dynamics Prediction
复制标题

使用学习质心动力学预测进行高效的人形接触规划

DOI:
10.1109/icra.2019.8794032
复制
发表时间:
2019
期刊:
2019 IEEE International Conference on Robotics and Automation (ICRA
影响因子:
--
通讯作者:
Berenson, Dmitry
Berenson, Dmitry
中科院分区:
--
文献类型:
--
作者:
Lin, Yu-Chi;Ponton, Brahayam;Righetti, Ludovic;Berenson, Dmitry

文献摘要

参考文献

被引文献

相似文献

类人机器人动态导航的环境,通过与它互动,通过接触扳手施加在间歇性的接触姿势。因此,在规划接触序列时考虑动力学是很重要的。传统的接触规划方法假设一个准静态的平衡标准,以减少计算的挑战,选择一个接触序列在粗糙的地形。然而,当需要动态运动时,例如当走下陡坡或穿过宽间隙时,这限制了该方法的适用性。最近的方法克服了这一限制的帮助下,有效的混合整数凸规划求解器能够合成动态接触序列。然而,它的指数时间复杂度限制了它的适用性,在小环境中的短时间范围内的接触序列。在本文中,我们超越了目前的方法,通过学习预测的机器人质心动量的动态演变,然后可以用于快速生成动态鲁棒的接触序列的机器人与手臂和腿使用基于搜索的接触规划。我们证明了所提出的方法的结果在一组动态的挑战性的情况下的效率和质量。
Humanoid robots dynamically navigate an environment by interacting with it via contact wrenches exerted at intermittent contact poses. Therefore, it is important to consider dynamics when planning a contact sequence. Traditional contact planning approaches assume a quasi-static balance criterion to reduce the computational challenges of selecting a contact sequence over a rough terrain. This however limits the applicability of the approach when dynamic motions are required, such as when walking down a steep slope or crossing a wide gap. Recent methods overcome this limitation with the help of efficient mixed integer convex programming solvers capable of synthesizing dynamic contact sequences. Nevertheless, its exponential-time complexity limits its applicability to short time horizon contact sequences within small environments. In this paper, we go beyond current approaches by learning a prediction of the dynamic evolution of the robot centroidal momenta, which can then be used for quickly generating dynamically robust contact sequences for robots with arms and legs using a search-based contact planner. We demonstrate the efficiency and quality of the results of the proposed approach in a set of dynamically challenging scenarios.
使用学习的可通行性估计在不平坦的地形中进行人形导航
DOI: 10.1109/humanoids.2017.8239531
发表时间: 2017
期刊: 2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids)
影响因子: --
作者:
Yu;D. Berenson
通讯作者: D. Berenson
DOI: --
发表时间: 2009
期刊: Proceedings of 9th IEEE-RAS International Conference on Humanoid Robots
影响因子: --
作者:
Oussama Kanoun;吉田英一、Jean-Paul Laumond
通讯作者: 吉田英一、Jean-Paul Laumond
水平行走时腿部的受力和力矩
DOI: --
发表时间: 1950
期刊: Journal of Fluids Engineering
影响因子: --
作者:
B. Bresler
通讯作者: B. Bresler
利用以往的经验进行人形导航规划
DOI: 10.1109/humanoids.2016.7803364
发表时间: 2016
期刊: 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids)
影响因子: --
作者:
Yu;D. Berenson
通讯作者: D. Berenson
优化人形行走的二次编码
DOI: --
发表时间: 2013
期刊: IEEE-RAS International Conference on Humanoid Robots
影响因子: --
作者:
Junggon Kim;N. Pollard;C. Atkeson
通讯作者: C. Atkeson