Robot Grasp Pattern Generation Using Approach Rays and Quality Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for robot grasp planning are computationally expensive and prone to human error, as they require manual programming and struggle with uncertainties in object pose and displacement, leading to inefficient and unreliable grasp patterns.
Innovation Solution
A method that generates a set of grasp patterns by creating approach rays associated with a target object, calculating grasp quality scores, and selecting patterns that meet a quality threshold, while considering object pose and displacement uncertainties through probability distribution models, to reduce on-line computations and improve grasp success.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If grasp patterns are calculated autonomously with full computational testing, then grasp reliability is improved, but computational time and processing cost increase significantly
Solution Approach 1:
The system performs preliminary generation of grasp patterns offline before actual robot operation. Multiple grasp patterns are pre-calculated and stored in a database during system setup or idle periods, so that during online operation, the robot can quickly retrieve and execute pre-validated grasp patterns without performing computationally intensive calculations in real-time.
Solution Approach 2:
The grasp planning process is divided into two distinct phases: offline phase where comprehensive grasp pattern generation and validation is performed, and online phase where only pattern selection and execution occur. This segmentation allows the computationally expensive testing to be done beforehand, while real-time operation remains fast and efficient.
2Ease of manufacture
If manual programming or tele-operation is used to teach grasp patterns, then implementation simplicity is improved, but time consumption and human error increase
Solution Approach 1:
The system enables autonomous self-programming through automated grasp pattern generation algorithms. The robot independently generates, tests, and validates its own grasp patterns using computer simulation and quality assessment metrics, eliminating the need for human operators to manually program or tele-operate the robot through complex manipulation tasks.
Solution Approach 2:
Manual tele-operation and physical teaching are replaced with automated computational algorithms. The system uses computer-based grasp synthesis, simulation, and evaluation to automatically generate grasp patterns, substituting human manual intervention with intelligent software-based solutions.
3Reliability
If comprehensive grasp testing is performed for each candidate, then grasp quality is improved, but processing speed decreases
Solution Approach 1:
Comprehensive grasp pattern testing and quality validation are performed in advance during the offline phase. The system generates multiple candidate grasp patterns, tests them through simulation, evaluates their quality using defined metrics, and selects the best patterns before actual robot operation begins.
Solution Approach 2:
The testing process is segmented into offline comprehensive validation and online quick verification. During offline operation, full computational testing is performed on all candidate patterns. During online operation, only the pre-validated best patterns are used, requiring minimal re-testing and enabling fast execution.
Data Source
AI summary
Methods and computer program products for generating robot grasp patterns are disclosed. In one embodiment, a method for generating robot grasp patterns includes generating a plurality of approach rays associated with a target object. Each approach ray of the plurality of approach rays extends perpendicularly from a surface of the target object. The method further includes generating at least one grasp pattern for each approach ray to generate a grasp pattern set of the target object, calculating a grasp quality score for each individual grasp pattern of the grasp pattern set, and comparing the grasp quality score of each individual grasp pattern with a grasp quality threshold. The method further includes selecting individual grasp patterns of the grasp pattern set having a grasp quality score that is greater than the grasp quality threshold, and providing the selected individual grasp patterns to the robot for on-line manipulation of the target object.