Robotic Pick-and-Place Pose Correction for Precision Chassis Insertion

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing robotic assembly systems face challenges in achieving high precision and accuracy during pick and place operations, particularly when handling expensive components like GPUs and CPUs, leading to potential damage and scrap.

Innovation Solution

A multi-sensor system with structured light sensors and machine learning algorithms for continuous detection and validation, combined with iterative closest point (ICP) algorithms and force sensors, ensures accurate alignment and insertion of components by calculating and correcting pose estimations using pre- and run-time template generation and validation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If traditional robotic arm systems are used for pick and place operations, then the operation speed and simplicity are maintained, but the precision and accuracy are insufficient leading to potential damage to expensive components

Engineering Contradiction:
Improveplacement precisionVSAvoidsystem complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system segments the pick and place operation into multiple phases: initial pickup, transport to approach point, final position correction, and insertion. Each phase uses specialized sensors and algorithms optimized for that specific task, allowing high precision where needed while maintaining overall system manageability

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary detection and pose estimation before the actual placement operation. Structured light sensors capture component geometry and position in advance, and ICP algorithms pre-calculate alignment transformations, enabling precise placement without requiring the entire system to be overly complex

Inventive Principle:
Principle #10Preliminary action

2Reliability

If multiple sensors and algorithms are used for continuous detection and validation, then the accuracy and reliability are improved, but the processing time and computational load increase

Engineering Contradiction:
Improveoperation reliabilityVSAvoidprocessing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs detection and validation at specific periodic intervals: initial component detection at pickup point, validation at approach point, and final correction verification before insertion. This periodic approach ensures reliability through multiple checks while avoiding continuous processing that would waste time

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The system performs preliminary pose estimation and alignment calculations before the critical insertion phase. By pre-processing detection data and calculating transformations in advance, the system reduces real-time processing demands during the actual placement operation

Inventive Principle:
Principle #10Preliminary action

3Measurement precision

If iterative closest point algorithms are used for pose estimation correction, then the alignment precision is improved, but the computational complexity and processing time increase

Engineering Contradiction:
Improvepose estimation precisionVSAvoidalgorithm complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The ICP algorithm implementation is segmented into discrete phases: initial pose estimation from structured light data, iterative refinement at approach point, and final correction at insertion point. Each phase processes only the necessary data subset, reducing overall computational complexity while maintaining precision

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system uses ICP algorithms to continuously refine pose estimates based on feedback from structured light sensor measurements. The algorithm compares expected component geometry with actual sensor data, calculates transformation corrections, and applies them iteratively to achieve precise alignment without excessive computational burden

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS20250214243A1High Precision Pick and Place Operation
Publication Date: 2025.07.03 BRIGHT MACHINES INC
  • US20250214243A1 patent drawing
  • US20250214243A1 patent drawing
  • US20250214243A1 patent drawing

AI summary

An assembly operation and a robotic cell for inserting a part into a chassis comprising calculating a first part pose estimation for the part in the pick area, picking up the part, and moving the part above the chassis, calculating a second part pose estimation for the part being held by the robot arm above the chassis, and correcting the second part pose estimation using a chassis pose estimation. The operation further comprising inserting the part into the chassis, wherein the multi-stage verification ensures that a high value part is not damaged in the assembly.