Vision-Guided Pickup Robot for Accurate Slot Item Retrieval

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The existing logistics systems face high failure rates in accurately picking up goods due to defects in positioning, which reduces overall logistics efficiency.

Innovation Solution

A pickup robot equipped with a camera, processor, and pickup component, utilizing an image processing module and position determining module to identify and accurately determine the position of goods based on slot and goods identifiers, enabling precise pickup.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual pickup is replaced by robot pickup to improve logistics efficiency, then productivity increases, but positioning accuracy deteriorates leading to high failure rate

Engineering Contradiction:
Improvelogistics efficiencyVSAvoidpositioning accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent replaces manual mechanical positioning with an automated vision-based positioning system. The camera captures images of slot identifiers and goods identifiers, and the processor automatically determines the target slot position and goods position within the slot, eliminating reliance on manual positioning skills and achieving consistent, accurate results.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an intermediary vision system consisting of a camera and image processing module. This intermediary captures visual information about slot identifiers and goods identifiers, processes the images to extract position information, and provides accurate positioning data to the pickup robot, bridging the gap between automated operation and precise positioning.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If robot travels to each slot to acquire target image for accurate identification, then positioning accuracy improves, but time consumption increases

Engineering Contradiction:
Improvepositioning accuracyVSAvoidtime consumption
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary image acquisition by capturing the target image containing slot identifier and goods identifier before the pickup operation. The processor analyzes these identifiers in advance to determine the target slot position and goods position within the slot, so that when the robot arrives at the target slot, the positioning is already complete, reducing on-site time consumption.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent creates a visual copy of the slot and goods information through image capture. The camera captures the slot identifier and goods identifier, creating a digital representation that the processor analyzes to determine position information. This copying approach allows accurate positioning without requiring complex physical measurement or trial-and-error searching.

Inventive Principle:
Principle #26Copying

3Manufacturing precision

If image processing is performed to filter goods identifier from target image, then pickup accuracy improves, but device complexity increases

Engineering Contradiction:
Improvepickup accuracyVSAvoidsystem complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent segments the image processing task into distinct functional modules: the image processing module filters and extracts the goods identifier from the target image, while the position determining module calculates the position information based on the extracted identifier. This segmentation allows each module to focus on a specific function, improving pickup accuracy while keeping the overall system manageable through modular design.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS12403608B2Pickup robot, pickup method, and computer-readable storage medium
Publication Date: 2025.09.02 BEIJING GEEKPLUS TECH CO LTD
  • US12403608B2 patent drawing
  • US12403608B2 patent drawing
  • US12403608B2 patent drawing

AI summary

The present disclosure provides a pickup robot, a pickup method, and a computer-readable storage medium. First, obtain a target image captured when a pickup component moves to each slot where a commodity is stored; then, when it is determined, on the basis of the slot identifier in the target image, that the current slot is a target slot which stores a commodity to be picked, screen a commodity identifier from the target image; when the commodity identifier is obtained by means of screening, determine, on the basis of the commodity identifier, the position information of the commodity to be picked up in the target slot; finally, pick up, on the basis of the position information, said commodity from the target slot. In the technical solution above, the target slot where the commodity to be picked up is stored, and the position information of said commodity in the target slot can be accurately determined by using the slot identifier and the commodity identifier, and said commodity can be accurately picked up on the basis of the determined position information, thereby effectively improving the pickup success rate, and also helping to improve the logistics efficiency of logistics industry.