Robotic Grasp Planning for Random Object Sorting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robots face challenges in grasping and sorting objects of varying sizes, orientations, and locations in uncontrolled environments, as existing systems are designed for repetitive tasks with predefined object shapes and orientations.
Innovation Solution
A robotic system that scores objects for grasping likelihood, orients the end effector, checks reachability, and implements crash recovery mechanisms to efficiently pick and place objects in a sorting system, even when objects are randomly sized and oriented.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If robots are used in highly controlled environments with predefined objects, then operational reliability is improved, but adaptability to varied environments deteriorates
Solution Approach 1:
The robotic system employs dynamic algorithms that adapt in real-time to different object geometries, positions, and orientations. The grasp planning software dynamically adjusts grasping strategies based on sensor feedback and object characteristics, enabling the robot to handle varied objects reliably without predefined programming for each object type.
Solution Approach 2:
The system changes operational parameters such as grasp force, approach velocity, and end effector orientation based on detected object properties. By dynamically adjusting these parameters according to object characteristics, the robot maintains high reliability across diverse object types and environmental conditions.
2Productivity
If robots perform repetitive tasks with minimal variation, then productivity is improved, but ease of operation in varied environments deteriorates
Solution Approach 1:
The robotic system performs self-adjustment through autonomous grasp planning and crash recovery algorithms. The system automatically adapts its operation to handle varied objects without human intervention, maintaining high productivity while simplifying operation in diverse environments through self-service capabilities.
Solution Approach 2:
The system uses sensor feedback to continuously monitor object properties and adjust grasping parameters in real-time. This feedback mechanism enables the robot to maintain high productivity across varied tasks by automatically adapting to different object characteristics without requiring complex manual reprogramming.
3Manufacturing precision
If the system scores objects for grasping likelihood and checks reachability, then manufacturing precision of grasping is improved, but device complexity increases
Solution Approach 1:
The system performs preliminary scoring of objects for grasping likelihood and pre-checks reachability before attempting grasping operations. This preliminary analysis enables precise grasping planning while managing complexity by filtering out unreachable or difficult-to-grasp objects before committing to complex manipulation sequences.
Solution Approach 2:
The grasp planning process is segmented into distinct computational stages: object scoring, reachability analysis, grasp site identification, and trajectory planning. This segmentation improves grasping precision by systematically addressing each aspect separately while managing overall system complexity through modular processing.
Data Source
AI summary
A method is provided for grasping randomly sized and randomly located objects. The method may include assigning a score associated with the likelihood of successfully grasping an object. Other features of the method may include orientation of the end effector, a reachability check, and crash recovery.