Robotic Picking Control Using Point Clouds for Fast Trajectory Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing picking systems face challenges in calculating trajectories efficiently, especially when considering obstacles, leading to difficulties in practical time calculations for arranging works between containers.
Innovation Solution
A control device that includes a point cloud information acquiring unit, an abnormality detection unit, and an instruction sending unit to manage the picking apparatus, utilizing image data and sensor measurements to detect abnormalities and adjust operations, and a program that generates trajectory information for the picking hand to navigate between containers while avoiding interference.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If trajectory calculation considers interference with obstacles, then trajectory accuracy is improved, but calculation time increases significantly
Solution Approach 1:
The system performs preliminary trajectory calculations during the planning phase, generating multiple candidate trajectories before execution. This allows the picking apparatus to have pre-computed paths ready, reducing real-time calculation requirements while maintaining accuracy through pre-planned obstacle avoidance
Solution Approach 2:
The trajectory calculation system dynamically adjusts its approach by switching between detailed interference-checking calculations for critical segments and simplified calculations for safe zones. This dynamic calculation strategy maintains accuracy where needed while reducing overall computation time
2Measurement precision
If point cloud information is acquired at multiple stages, then abnormality detection accuracy is improved, but system complexity increases
Solution Approach 1:
The abnormality detection process is segmented into distinct stages: pre-picking detection, during-picking detection, and post-picking detection. Each stage uses point cloud information acquisition targeted at specific detection needs, reducing overall system complexity while maintaining high detection accuracy through stage-specific optimization
Solution Approach 2:
The point cloud information acquisition unit serves multiple functions: it detects abnormalities, verifies work position, monitors picking hand status, and validates trajectory execution. This multi-functionality reduces the need for separate detection systems, thereby reducing system complexity while maintaining comprehensive detection accuracy
Data Source
AI summary
A point cloud information acquiring unit for acquiring point cloud information of a region including at least one of the picking hand and the work at a time which is at least one of (i) when the picking hand picks the work at the first position, (ii) when the picking hand moves the work out of the first container, (iii) when the picking hand moves the work in the second container and (iv) when the picking hand arranges the work at the second position; and an abnormality detection unit for detecting an abnormality based on the point cloud information acquired by the point cloud information acquiring unit are included.