基于多重几何约束的未知物体抓取位姿估计

针对机器人在非结构化环境下面临的未知物体难以快速稳定抓取的问题,提出一种基于多重几何约束的未知物体抓取位姿估计方法.通过深度相机获取场景的几何点云信息,对点云进行预处理得到目标物体,利用简化的夹持器几何形状约束生成抓取位姿样本.然后,利用简化的力封闭约束对样本进行快速粗筛选.对抓取位姿的抓取几何轮廓进行力平衡约束分析,将稳定的位姿传送至机器人执行抓取.采用深度相机与6自由度机械臂组成实验平台,对不同姿态形状的物体进行抓取实验.实验结果表明,本文方法能够有效应对物体种类繁多、缺乏3维模型的情况,在单目标和多目标场景均具有良好的适用性.

Estimation of the Grasping Pose of Unknown Objects Based onMultiple Geometric Constraints

Aiming at the problem of grasping unknown objects quickly and stably by robots in unstructured environment, a method based on multiple geometric constraints is proposed to estimate the pose of unknown objects. Firstly, the geometric point cloud information of the scene is acquired by depth camera. Target object can be obtained after point cloud preprocessing, and the sample of the grasping pose is generated by simplified geometric constraint of the grasper. With the constraint of simplified force-closure, a quick and coarse screening of samples is performed. After the force balance constraint on the geometric profile of the grasping pose is analyzed, a stable pose is transmitted to the robot to perform grasping. Using a 6 degree of freedom (6-DoF) robotic manipulator with a depth camera, experiments are conducted to grasp objects with different postures and shapes. Results show that the proposed method can effectively deal with the situation that various objects exist and their three-dimensional models are unknown. It also has good applicability in both single-target and multi-target scenarios.