3D Workpiece Removal Path Planning for Robot Interference Avoidance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing robot systems struggle to accurately determine interference between workpieces and a robot hand when removing workpieces with complex shapes and arrangements, as they rely solely on distance images and cannot account for insertions or hidden back sides.

Innovation Solution

A robot system equipped with a three-dimensional sensor and a control device that generates a removal path for workpieces by modeling their three-dimensional shapes and simulating their positions in a virtual space to avoid interference with other workpieces and obstacles.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If distance image-based overlap determination is used, then the system can determine interference between workpieces, but it cannot accurately detect insertions or hidden back sides of workpieces

Engineering Contradiction:
Improveinterference detection accuracyVSAvoidhidden surface information
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The patent transitions from two-dimensional distance image analysis to three-dimensional point cloud data processing. By constructing a 3D model of the workpiece and the robot hand, the system can accurately detect insertions and hidden back sides that are invisible in 2D distance images, thereby resolving the contradiction between measurement precision and information loss.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Reliability

If three-dimensional point cloud data and modeling are used, then the system can accurately determine interference in complex arrangements, but the computational complexity and processing time increase

Engineering Contradiction:
Improveinterference determination reliabilityVSAvoidprocessing system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent creates simplified 3D models (copies) of workpieces and the robot hand from point cloud data. These models are used for virtual overlap determination instead of processing raw point cloud data directly, reducing computational complexity while maintaining accuracy in interference detection.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The system performs preliminary 3D modeling and virtual overlap determination before actual robot operation. By pre-calculating interference scenarios using simplified models, the system reduces real-time processing requirements and computational complexity during actual execution.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS20250196351A1Robot system
Publication Date: 2025.06.19 FANUC LTD
  • US20250196351A1 patent drawing
  • US20250196351A1 patent drawing

AI summary

A robot system according to one aspect of the present disclosure comprises: a model storing unit that stores a workpiece model; a workpiece detecting unit that detects the position and orientation of a workpiece by comparing features of a surface shape measured by a three-dimensional sensor to features of the workpiece model; a workpiece model positioning unit that positions the workpiece model in a virtual space; and a path setting unit that, in the virtual space, sets a removal path so as to move and withdraw the workpiece model that is an object to be removed without interfering with another workpiece model.