Mobile Robot Image Filtering for Fast Obstacle Identification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional moving robots face challenges in accurately detecting and responding to obstacles during cleaning due to time-consuming image data processing and difficulties in low-light conditions, leading to inefficient path changes and potential collisions.

Innovation Solution

A moving robot equipped with a sensor unit, camera, and controller that analyzes image data for brightness and sharpness to filter and transmit only recognizable data to a server for obstacle identification, allowing the robot to adjust its path accordingly based on obstacle type and danger level.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the moving robot transmits all photographed image data to the server for obstacle identification, then the obstacle recognition accuracy is improved, but the data transmission time and network bandwidth consumption increase

Engineering Contradiction:
Improveobstacle recognition accuracyVSAvoiddata transmission time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies partial action by selectively transmitting only necessary image data to the server. The controller analyzes image data and transmits only when obstacles are detected or when transmission is necessary, rather than continuously transmitting all image data. This reduces data transmission time and network bandwidth consumption while maintaining obstacle recognition accuracy.

Inventive Principle:
Principle #16Partial or excessive action

2Reliability

If the moving robot changes the traveling path immediately when an obstacle is detected, then the collision avoidance is improved, but the cleaning coverage is reduced

Engineering Contradiction:
Improvecollision avoidanceVSAvoidcleaning coverage
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent applies preliminary action by analyzing image data to identify obstacles before the robot collides with them. The controller receives image data from the server, identifies obstacles in advance, and then determines whether to change the traveling path. This allows the robot to avoid collisions while maintaining cleaning coverage by making informed decisions about path changes.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements feedback by continuously receiving image data from the server and using this information to adjust the traveling path. The controller monitors the environment through transmitted image data and makes real-time decisions about whether to change direction, ensuring both collision avoidance and optimal cleaning coverage.

Inventive Principle:
Principle #23Feedback

3Speed

If the moving robot processes image data locally to quickly identify obstacles, then the response speed is improved, but the device complexity increases

Engineering Contradiction:
Improveobstacle identification speedVSAvoidimage processing capability
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

The patent uses the server as an intermediary for image data processing. The controller transmits image data to the server, which performs the complex obstacle identification using its image processing unit. This externalizes the processing complexity from the robot itself, maintaining fast response times while reducing the device complexity of the robot.

Inventive Principle:
Principle #24Intermediary (Mediator)

4Measurement precision

If the moving robot photographs and transmits all image data, then the obstacle detection accuracy is improved, but the energy consumption increases

Engineering Contradiction:
Improveobstacle detection accuracyVSAvoidenergy consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent applies partial action by selectively photographing and transmitting only necessary image data. The controller determines whether to photograph and transmit image data based on obstacle detection needs, rather than continuously capturing and transmitting all images. This reduces energy consumption while maintaining obstacle detection accuracy.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP3590665B1Mobile robot and control method therefor
Publication Date: 2022.06.15 LG ELECTRONICS INC
  • EP3590665B1 patent drawingFigure 1~2
  • EP3590665B1 patent drawingFigure 3~4
  • EP3590665B1 patent drawingFigure 5~6(d)

AI summary

The present invention relates to a moving robot and a control method thereof, and includes a sensor unit configured to detect an obstacle located in a traveling direction; a camera configured to photograph the obstacle, when the obstacle is detected by the sensor unit; a controller configured to control a certain operation to be performed in accordance with the obstacle. The controller analyzes a plurality of image data of the obstacle inputted from the camera to determine whether the obstacle can be identified and filters the image data, transmits the filtered image data among the plurality of image data to the server through the communication unit, and controls the traveling unit in accordance with obstacle information received from the server. Hence, by transmitting only recognizable image, unnecessary data transmission is reduced, and accordingly, transmission traffic is reduced and the load of image processing of the server is reduced. As the load of the server decreases, the obstacle can be quickly determined, and accordingly, the moving robot can recognize the obstacle in a short time and determine the type of the obstacle to cope with, thereby performing the operation suitable for the feature of the obstacle, the cleaning area, or the surrounding environment.