Robot Visual Field Adjustment for Continuous Target Following

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Robots with limited visual fields struggle to continuously detect and follow target objects that deviate from their original route quickly, leading to failure in following tasks due to the target object disappearing from the visual field.

Innovation Solution

The robot's visual field range is adjusted in real-time based on the relative pose relationship between the target object and the robot, using visual field parameter information to ensure the target remains within the adjusted field, allowing smooth tracking.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the robot uses a fixed visual field range, then the device structure is simple, but the target object disappears from the visual field when it deviates quickly from the original route

Engineering Contradiction:
Improvecontinuous detection of target objectVSAvoidvisual field adjustment mechanism
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies the dynamics principle by making the visual field range adjustable rather than fixed. The control device dynamically adjusts the visual field parameters (such as field of view angle, focal length) based on the relative pose relationship between the robot and target object, allowing the visual field to adapt to different tracking scenarios and prevent target loss when the object deviates quickly.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent implements parameter changes by modifying visual field parameters (field of view angle, focal length, focus distance) according to the detected relative pose relationship. When the target object deviates from the original route, the system changes these parameters to expand or shift the visual field range, ensuring continuous detection while managing the complexity through software-based parameter adjustment.

Inventive Principle:
Principle #35Parameter changes

2Reliability

If the robot adjusts the visual field range in real-time, then the target object remains in the visual field, but the control system becomes more complex

Engineering Contradiction:
Improvecontinuous detection of target objectVSAvoidreal-time control system
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies feedback by continuously detecting the relative pose relationship between the robot and target object, comparing it with the original route information, and using this feedback to adjust the visual field parameters in real-time. This closed-loop control ensures the target remains in the visual field while managing complexity through systematic feedback processing.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent implements preliminary action by pre-establishing the relationship between relative pose parameters and appropriate visual field adjustments. The system has pre-defined strategies for different deviation scenarios, allowing it to respond quickly to target movements without complex real-time calculations, thus maintaining reliability while controlling system complexity.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4310622A1Following control method and apparatus for robot and storage medium
Publication Date: 2024.01.24 BEIJING XIAOMI ROBOT TECH CO LTD
  • EP4310622A1 patent drawingFigure 1~2
  • EP4310622A1 patent drawingFigure 3~5
  • EP4310622A1 patent drawingFigure 6~7

AI summary

A following control method and apparatus for a robot and a storage medium. The following control method for a robot includes: controlling (S101) the robot to follow a target object; in a process of following the target object, acquiring (S102) a relative pose relationship between the target object and the robot; and adjusting (S103) a visual field range of the robot according to the relative pose relationship and visual field parameter information of the robot, in which the target object is located in the adjusted visual field range.