Motion planning efficient trajectories for industrial bin-picking

Abstract

This paper presents an algorithm for planning efficient trajectories in a bin-picking scenario. The presented algorithm is designed to provide paths, which are applicable for typical industrial manipulators, and does not require customized research interfaces to the robot controller. The method provides paths (almost) instantaneously, which is important for running efficiently in production. To achieve this, the method utilizes that all motions start and end within sub-volumes of the work envelope. A database of paths can thus be pre-computed, such that all paths are optimized with respect to a specified cost function, thereby ensuring close to optimal solutions. When queried, the method searches the database for a feasible path candidate and adapts it to the specific query. To achieve an efficient execution on the robot, blends are added to ensure a smooth transition between segments. Two algorithms for calculating feasible blends based on the clearance between robot and obstacles are therefore provided. Finally, the method is tested in a real bin-picking application where it solves queries efficiently and provides paths, which are significantly faster than those currently used for bin-picking in the industry.

Detecting and Solving Tube Entanglement in Bin Picking Operations

“…Motion planning is used to determine a trajectory for the gripper, namely after grasping an object. Most of the research focuses on the particular case of finding a trajectory that avoids the gripper and the grasped object from colliding with the environment [10][11][12]. Planning algorithms include exploring the gripper configuration space (or one of its sub-spaces) with random sampling or using optimization techniques to minimize an objective function subject to equality and inequality constraints (such as keeping the gripper horizontal or preventing each of the robot arm's joints from exceeding a certain velocity).…”

Visual Repetition Sampling for Robot Manipulation Planning

“…Ellekilde et al [10] blend several segments of solution retrieved from database into a smooth one. Jetchev et al [11] proposed to penalize differences from the retrieved solutions in its inverse kinematic.…”

Identification of probabilistic approaches and map-based navigation in motion planning for mobile robots

“…PP and TP are shown in figures 10 and 11, respectively. Generally, welding robots with many DOF [111], industrial robots [112], domestic robots [113,114], and urban selfdriving vehicles have used developed with TC [115,116].…”