Control method, apparatus and system for robot, and applicable robot

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing intelligent robots face challenges in automatically adjusting their pose to move along a principal direction, such as a direction formed by a wall, to optimize cleaning efficiency and coverage rate.

Innovation Solution

A control method that acquires images during movement, identifies characteristic line segments, determines the relative orientation relationship between the robot and room dividers, and adjusts the robot's pose to align with the principal direction constructed based on these dividers, using techniques like vanishing point grouping and angle counting to ensure accurate alignment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the robot uses traditional localization methods without vanishing point grouping, then the processing speed is faster, but the accuracy of determining the principal direction is lower

Engineering Contradiction:
Improveaccuracy of principal direction determinationVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent segments the image processing task by dividing lines into different groups based on vanishing points. This segmentation allows the system to focus processing on relevant line groups that converge at specific vanishing points, improving both accuracy in determining the principal direction and efficiency by avoiding unnecessary processing of all lines uniformly.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary grouping of lines by vanishing points before determining the principal direction. This preliminary action organizes the data structure in advance, making subsequent processing more efficient and accurate by having lines already categorized by their convergence points, thus reducing overall processing time while maintaining high precision.

Inventive Principle:
Principle #10Preliminary action

2Productivity

If the robot moves without automatic pose adjustment, then the operational complexity is lower, but the cleaning coverage rate is reduced

Engineering Contradiction:
Improvecleaning coverage rateVSAvoidcontrol system complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent implements self-service through automatic pose adjustment where the robot autonomously determines its orientation relative to the principal direction using vanishing point analysis and automatically adjusts its pose without external intervention. This self-service capability increases cleaning coverage by optimizing movement patterns while the complexity is managed through automated algorithms rather than manual control.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent changes the operational parameters by dynamically adjusting the robot's pose based on calculated orientation angles derived from vanishing points. By continuously modifying position and orientation parameters according to the determined principal direction, the system achieves better cleaning coverage while the complexity is handled through automated parameter adjustment rather than complex mechanical structures.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If the robot uses simple line detection without vanishing point analysis, then the device complexity is lower, but the accuracy of orientation determination is reduced

Engineering Contradiction:
Improveorientation determination accuracyVSAvoidimage processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces vanishing points as an intermediary concept in the image processing pipeline. Instead of directly determining orientation from raw line detections, the system uses vanishing points as intermediate representations that encode directional information. This intermediary approach improves orientation determination accuracy while managing complexity by providing a structured intermediate representation that simplifies subsequent calculations.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3686703B1Control method, apparatus and system for robot, and applicable robot
Publication Date: 2022.12.14 ANKOBOT (SHENZHEN) SMART TECH CO LTD
  • EP3686703B1 patent drawingFigure 1
  • EP3686703B1 patent drawingFigure 2~3
  • EP3686703B1 patent drawingFigure 4

AI summary

A control method, apparatus and system for a robot, and an applicable robot. The control method comprises: acquiring an image photographed during the movement of a robot and recognizing a characteristic line segment in the image (S 110); according to the recognised characteristic line segment, determining an orientation relation between the robot and a room spacer in a physical space (S120); and adjusting a stance of the robot according to the orientation relation, so that the robot moves in the physical space along a main direction in which the room spacer is constructed (S130). In the method, by acquiring a characteristic line segment in an image, an orientation relation between a robot and a room spacer is determined, so that the robot can adjust, based on the orientation relation, its own stance to move along a main direction in which the room spacer is constructed, improving the coverage rate of movement.