Adaptive 3D Bulk Picking Robot for Moving Conveyor Throughput
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing pick and place robot systems struggle to efficiently pick up objects from a bulk, especially 3D bulk, with random sizes, shapes, and textures, and place them at a high rate of success and high throughput, especially in environments with continuously moving conveyors.
Innovation Solution
A robot system comprising a controllable gripper with multiple gripping members, a controllable robotic actuator, a sensor system providing 3D images of objects upstream, and a control system executing algorithms to identify objects, select which object to grip, adjust the gripper configuration, move the gripper to grip the object, and place it at a target position.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a robot system picks objects from a continuously moving bulk conveyor, then throughput is improved, but the difficulty of detecting and measuring object properties increases due to random sizes, shapes, and textures
Solution Approach 1:
The sensor system captures images of objects in the bulk conveyor before the robot attempts to pick them. The control system processes these images in advance to identify object properties such as size, shape, and position. This preliminary detection allows the robot to plan its picking trajectory and adjust gripper configuration before actually attempting to grasp the object, thereby maintaining high throughput while overcoming the difficulty of detecting random object properties.
Solution Approach 2:
The control system continuously receives image data from the sensor system, processes this feedback information to update its understanding of object properties in the bulk, and adjusts the robot's picking strategy accordingly. This closed-loop feedback mechanism enables the system to adapt to the random sizes, shapes, and textures of objects while maintaining consistent high-speed operation.
2Adaptability or versatility
If the robot system handles objects with random sizes and shapes, then adaptability is improved, but the device complexity increases due to the need for controllable gripper configuration
Solution Approach 1:
The gripper is designed with controllable configuration, allowing its gripping members to be dynamically adjusted based on the detected properties of each object. The control system calculates the optimal gripper configuration for each object's size and shape, and actuates the gripper accordingly. This dynamic adaptability enables the robot to handle objects with random sizes and shapes without requiring multiple specialized grippers, thus managing device complexity while maximizing versatility.
Solution Approach 2:
The system changes the operational parameters of the gripper (such as opening width, gripping force, and finger position) based on the detected object properties. By dynamically adjusting these parameters according to each object's characteristics, the system achieves high adaptability to random object sizes and shapes while using a single standardized gripper mechanism, avoiding the complexity of multiple specialized devices.
3Productivity
If the robot picks objects at high speed from a moving bulk, then productivity is improved, but the reliability of successful picking decreases due to the complexity of the task
Solution Approach 1:
The control system performs preliminary calculations of the picking trajectory, gripper configuration, and release timing based on pre-captured images of the objects in the bulk. This advance planning allows the robot to execute picks at high speed with high reliability, as all critical parameters are determined before the actual picking action occurs, eliminating delays and reducing errors during the high-speed operation.
Solution Approach 2:
The system maintains continuous operation by constantly capturing images, processing object properties, planning trajectories, and executing picks without interruption. The sensor system continuously monitors the bulk conveyor, and the control system continuously updates its understanding of object positions and properties. This continuous cycle of detection, planning, and execution enables the robot to maintain both high picking speed and high success rate by never stopping to reassess the situation.
Data Source
AI summary
A robot system for picking randomly shaped and sized object from a continuously moving stream of objects in bulk, e.g. a 3D bulk, and placing the object singulated and aligned on an induction or directly on a sorter. A pick and place robot has a robotic actuator for moving a gripper with a controllable gripping configuration of its gripping members, e.g. four suction cups, to adapt the gripper for various objects. A control system processes a 3D image of objects upstream of a position of the pick and place robot, identifies separate objects in the 3D image, and selects which object to grip, based on parameters of the identified separate objects determined from the 3D image. Based on e.g. size and shape of the selected object to grip, the gripping configuration of the gripper is adjusted to match the surface of the object to grip for optimal gripping. The robotic actuator, e.g. a gantry type robotic actuator, is then controlled to move the gripper to a position for gripping the object, and afterwards move the gripper with the gripped object to a target position and with a target orientation to release grip of the object and thus place the object on an induction or directly on a sorter. An image after placing the object along with properties of the object determined from the 3D image can be used as input to a machine learning for online improving pick and place performance of the robot system, e.g. for online improving the algorithm for selection of which object to pick, and also for selection of the appropriate gripping configuration to match the object.