Anytime motion planning for prehensile manipulation in dense clutter

Anytime motion planning for prehensile manipulation in dense clutter
复制标题

随时进行运动规划,以便在密集的杂乱环境中进行抓握操作

DOI:
10.1080/01691864.2019.1690207
复制
发表时间:
2019
期刊:
影响因子:
2
通讯作者:
Bekris, Kostas
Bekris, Kostas
中科院分区:
计算机科学4区
文献类型:
--
作者:
Kimmel, Andrew;Shome, Rahul;Bekris, Kostas

文献摘要

参考文献

被引文献

相似文献

已经开发了许多方法来规划用于拾取和放置的机器人手臂的运动,范围从局部优化到全局搜索技术,这对于稀疏放置的对象是有效的。然而,在许多现实世界的设置中,密集的杂乱仍然会对成功率、计算时间和解决方案的质量产生不利影响。该方法通过快速返回解并随着时间的推移提高解的质量,实现了在杂波中的高成功率和随时性能。该方法首先通过忽略手臂有效地探索低维末端执行器的任务空间,并建立一个离散近似的导航功能。这是在线执行的,没有场景的先验知识。然后,一个知情的采样为基础的规划器,整个手臂使用雅可比基转向,以达到有前途的终端执行器的任务空间的指导。这个过程也是全面的,如果任务空间指导是误导性的,它允许随着时间的推移探索替代路径。本文评估了所提出的方法对替代品中挑选或放置不同数量的杂波与不同的末端执行器的各种机器人机械手的任务。结果表明,该方法可靠地提供更高质量的解决方案路径更快,具有更高的成功率相对于替代品。
Many methods have been developed for planning the motion of robotic arms for picking and placing, ranging from local optimization to global search techniques, which are effective for sparsely placed objects. Dense clutter, however, still adversely affects the success rate, computation times, and quality of solutions in many real-world setups. The proposed method achieves high success ratio in clutter with anytime performance by returning solutions quickly and improving their quality over time. The method first explores the lower dimensional end effector's task space efficiently by ignoring the arm, and build a discrete approximation of a navigation function. This is performed online, without prior knowledge of the scene. Then, an informed sampling-based planner for the entire arm uses Jacobian-based steering to reach promising end effector poses given the task space guidance. This process is also comprehensive and allows the exploration of alternative paths over time if the task space guidance is misleading. This paper evaluates the proposed method against alternatives in picking or placing tasks among varying amounts of clutter for a variety of robotic manipulators with different end-effectors. The results suggest that the method reliably provides higher quality solution paths quicker, with a higher success rate relative to alternatives.
高效且渐近最优的运动动力学运动规划
DOI: --
发表时间: 2020
期刊:
影响因子: --
作者:
Zakary Littlefield
通讯作者: Zakary Littlefield
DOI: --
发表时间: 2005-11
影响因子: 5.2
作者:
M. Spong;S. Hutchinson;M. Vidyasagar
通讯作者: M. Spong;S. Hutchinson;M. Vidyasagar
DOI: 10.1109/humanoids.2014.7041469
发表时间: 2014-11
期刊: 2014 IEEE-RAS International Conference on Humanoid Robots
影响因子: --
作者:
Joan Fontanals;B. Dang-Vu;O. Porges;J. Rosell;M. Roa
通讯作者: Joan Fontanals;B. Dang-Vu;O. Porges;J. Rosell;M. Roa
使用高斯过程和因子图进行运动规划作为概率推理
DOI: 10.15607/rss.2016.xii.001
发表时间: 2016
期刊: 2nd IEEE International Conference on Space Mission Challenges for Information Technology (SMC-IT'06)
影响因子: --
作者:
Jing Dong;Mustafa Mukadam;F. Dellaert;Byron Boots
通讯作者: Byron Boots
用于组合运动和任务规划器的可扩展软件架构
DOI: --
发表时间: 2014
期刊: Simulation, Modeling, and Programming for Autonomous Robots
影响因子: --
作者:
Zakary Littlefield;A. Krontiris;A. Kimmel;Andrew Dobson;Rahul Shome;Kostas E. Bekris
通讯作者: Kostas E. Bekris