Integrated grasp and motion planning using independent contact regions
Integrated grasp and motion planning using independent contact regions
复制标题
DOI：
10.1109/humanoids.2014.7041469
复制
发表时间：
2014-11
期刊：
影响因子：
--
通讯作者：
Joan Fontanals;B. Dang-Vu;O. Porges;J. Rosell;M. Roa
中科院分区：
文献类型：
--
作者：
Joan Fontanals;B. Dang-Vu;O. Porges;J. Rosell;M. Roa
传统上，抓取和手臂运动规划被认为是单独的任务。本文提出了一种集成的方法，只需要初始配置的机器人手臂和目标对象的姿态，同时规划一个良好的手的姿势和手臂轨迹，以抓住对象。规划者利用独立接触区域的概念来寻找最佳可能的把握。使用两种不同的方法来获得末端执行器的目标姿势：一种是使用主成分分析将采样方法偏向有利区域，另一种是考虑机器人手臂的能力来决定最有希望的手姿势。所提出的方法进行评估，使用不同的情况下的人形机器人Spacejustin。
Traditionally, grasp and arm motion planning are considered as separate tasks. This paper presents an integrated approach that only requires the initial configuration of the robotic arm and the pose of the target object to simultaneously plan a good hand pose and arm trajectory to grasp the object. The planner exploits the concept of independent contact regions to look for the best possible grasp. The goal poses for the end effector are obtained using two different methods: one that biases a sampling approach towards favorable regions using principal component analysis, and another one that considers the capabilities of the robotic arm to decide the most promising hand poses. The proposed method is evaluated using different scenarios for the humanoid robot Spacejustin.