Vision-Guided Mobile Robot Picking for Random Object Grasping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current robots rely on 'blind grasping' and struggle to adapt to changes in object shape, texture, or location, making them ineffective for picking and placing objects randomly among others.
Innovation Solution
A vision-guided mobile robot with a manipulator and camera system that builds a database of grasping points and visual features for objects, allowing it to identify and grasp objects autonomously, perform collision-free path planning, and verify targets using barcode recognition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If robots perform blind grasping from the same location, then the operation is simple and reliable, but the robot cannot adapt to changes in object shape, texture, or location
Solution Approach 1:
The system performs preliminary actions by capturing images of objects in advance, extracting visual features, and building a database of object characteristics before the actual grasping operation. This allows the robot to plan its grasping strategy based on pre-analyzed object properties, enabling adaptation to different objects without increasing real-time system complexity
Solution Approach 2:
The patent replaces traditional mechanical sensing and trial-and-error grasping approaches with vision-based systems. The camera and image processing algorithms substitute for complex mechanical sensors, allowing the robot to perceive and adapt to object variations through visual information rather than physical interaction
2Reliability
If robots use vision-guided grasping to identify target objects, then the robot can adapt to random object positions and variations, but the system complexity increases due to database building and visual feature extraction
Solution Approach 1:
The system performs preliminary actions by capturing images of objects in advance, extracting visual features, and building a database of object characteristics before the actual grasping operation. This allows the robot to plan its grasping strategy based on pre-analyzed object properties, enabling adaptation to different objects without increasing real-time system complexity
Solution Approach 2:
The system implements feedback mechanisms where the vision system continuously monitors object characteristics, compares them with the database, and adjusts grasping parameters accordingly. This closed-loop control ensures high grasping accuracy by constantly verifying object identification and adjusting the grasping plan based on visual feedback
3Measurement precision
If the robot performs closed-loop optimization of looking while approaching, then the grasping precision is improved, but the time required for detection and path planning increases
Solution Approach 1:
The system performs preliminary actions by capturing images of objects in advance, extracting visual features, and building a database of object characteristics before the actual grasping operation. This allows the robot to plan its grasping strategy based on pre-analyzed object properties, enabling adaptation to different objects without increasing real-time system complexity
Solution Approach 2:
The system implements continuous useful action by performing closed-loop optimization during the approach phase. The robot continuously captures images, updates object detection, and refines the grasping plan while moving toward the target, ensuring that useful detection and planning actions continue throughout the approach rather than being performed as separate discrete steps
Data Source
AI summary
A vision-guided picking and placing method for a mobile robot that has a manipulator having a hand and a camera, includes: receiving a command instruction that instructs the mobile robot to grasp a target item among at least one object; controlling the mobile robot to move to a determined location, controlling the manipulator to reach for the at least one object, and capturing one or more images of the at least one object using the camera; extracting visual feature data from the one or more images, matching the extracted visual feature data to preset feature data of the target item to identify the target item, and determining a grasping position and a grasping vector of the target item; and controlling the manipulator and the hand to grasp the target item according to the grasping position and the grasping vector, and placing the target item to a target position.