Integrated Sensor System for Warehouse Robot Payload Centering

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing autonomous robots in warehouses often require multiple cameras for obstacle detection and payload centering, increasing costs and complexity, while existing solutions do not efficiently utilize a single camera for both functions.

Innovation Solution

The use of an integrated sensor system with a single camera for both obstacle detection and payload centering, employing advanced image processing techniques and camera technology to perform these functions simultaneously.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If multiple cameras are used for obstacle detection and payload centering, then the reliability and precision of these functions are improved, but the device complexity and cost increase

Engineering Contradiction:
Improveobstacle detection reliabilityVSAvoidcamera system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies multi-functionality by enabling a single camera to perform both obstacle detection and payload centering tasks. The camera captures images that are processed to detect obstacles in the robot's path while simultaneously determining the position of payloads relative to the robot's center, replacing what would traditionally require multiple separate cameras or sensors

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent merges the obstacle detection function and payload centering function into a single integrated camera system. By combining these functions into one sensor, the system reduces component count and complexity while maintaining the reliability of both functions through unified image processing algorithms

Inventive Principle:
Principle #5Merging (Combining)

2Measurement precision

If multiple cameras are used for obstacle detection and payload centering, then the measurement precision of both functions is improved, but the manufacturing cost increases

Engineering Contradiction:
Improvepayload centering precisionVSAvoidmanufacturing cost
Core Design Contradiction:
Measurement precisionVSEase of manufacture

Solution Approach 1:

The single camera is designed to provide sufficient measurement precision for both obstacle detection and payload centering applications. Advanced image processing techniques extract multiple types of spatial information from the same image data, achieving the required precision without requiring multiple specialized cameras

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

By merging the detection and centering functions into one camera system, the patent reduces manufacturing costs associated with purchasing, installing, and calibrating multiple cameras. The unified approach simplifies the manufacturing process while maintaining measurement precision through sophisticated algorithms

Inventive Principle:
Principle #5Merging (Combining)

3Device complexity

If a single camera is used for both obstacle detection and payload centering, then the device complexity is reduced, but the difficulty of detecting and measuring increases

Engineering Contradiction:
Improvecamera system complexityVSAvoidimage processing complexity
Core Design Contradiction:
Device complexityVSDifficulty of detecting and measuring

Solution Approach 1:

The image processing system segments the single camera's output into separate analysis streams for obstacle detection and payload centering. By dividing the processing tasks into distinct algorithmic modules, the system manages the complexity of analyzing a single image for multiple purposes without overwhelming computational burden

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent develops universal image processing algorithms that can extract both obstacle information and payload position information from the same image data. These multi-functional algorithms are designed to handle the increased detection difficulty by efficiently processing multiple measurement objectives simultaneously

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP3512785B1Integrated obstacle detection and payload centering sensor system
Publication Date: 2020.08.12 AMAZON TECH INC
  • EP3512785B1 patent drawingFigure 1
  • EP3512785B1 patent drawingFigure 2
  • EP3512785B1 patent drawingFigure 3

AI summary

Disclosed are various embodiments for an integrated obstacle detection and payload centering sensor system. A robotic drive unit (RDU) captures, with a downward facing camera mounted to itself, an image of fiducial located on the ground. The RDU then positions itself over the fiducial and subsequently rotates. As it rotates, the RDU captures a point cloud of the surround vicinity a forwardfacing three-dimensional camera mounted to itself. The RDU then identifies in the point cloud at least two legs of a storage unit positioned over the robotic drive unit. Subsequently, the RDU determines a location for each of the at least two legs relative to the fiducial and triangulates a center of the storage unit based at least in part on the location of each of the at least two legs. The RDU then centers itself underneath the storage unit.