Depth-Based Empty Bin Detection for Robotic Grasp Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current robotic bin picking systems lack efficiency and accuracy in determining whether a bin is empty or contains an object, leading to unnecessary grasp computations and potential damage to robots.
Innovation Solution
An autonomous system equipped with a depth camera and a processor that performs k-means clustering on depth images to determine the location of the bin's bottom end and classify whether the bin is empty or contains an object before performing grasp computations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the robot performs grasp computations for every detected bin, then the robot can potentially grasp objects in the bin, but the robot wastes processing time and may attempt grasps on empty bins
Solution Approach 1:
The system performs a preliminary check using depth image clustering to detect whether a bin contains objects before initiating grasp computations. This preliminary action filters out empty bins, preventing wasted grasp attempts and saving processing time while maintaining reliability.
2Measurement precision
If the robot uses simple detection methods to identify bins, then the system is faster and simpler, but the robot cannot accurately determine whether bins are empty or contain objects
Solution Approach 1:
The system replaces complex mechanical inspection methods with an optical-based depth camera and computational clustering algorithm. This substitution achieves high measurement precision in determining bin emptiness while keeping the physical hardware relatively simple.
Solution Approach 2:
The system creates a depth map representation (copy) of the bin contents and applies clustering algorithms to this digital model to determine emptiness. This allows accurate detection without physically inspecting each bin, balancing precision and complexity.
3Productivity
If the robot attempts grasps on all detected bins, then no objects are missed, but the robot may damage itself by attempting grasps on empty bins
Solution Approach 1:
The system performs a preliminary depth-based analysis to identify bins containing objects before attempting grasps. This preliminary filtering protects the robot from damaging empty bins while maintaining productivity by quickly identifying valid targets.
Solution Approach 2:
The depth image clustering analysis serves as an intermediary step between bin detection and grasp execution. This intermediary layer provides safety verification, allowing the system to maintain high productivity while filtering out harmful grasp attempts on empty bins.
Data Source
AI summary
It is recognized herein that robots or autonomous systems can lose time when computing grasp scores for empty bins. Further, when grasps are attempted on empty bins, for instance due to the related grasp score computations, the robot can lose additional time through being used unnecessarily to attempt the grasp. Such usage can wear on the robot, or damage the robot, in some cases. An autonomous system can classify or determine whether a bin contains an object or is empty, for example, such that a grasp computation is not performed when the bin is empty. In some examples, a system classifies a given bin at runtime before each grasp computation is performed. Thus, systems described herein can avoid performing unnecessary grasp computations, thereby conserving processing time and overheard, among addressing other technical problems.