Cleaning Robot TOF Obstacle Classification for Sofa and Wire Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cleaning robots face difficulties in navigating complex obstacle environments, particularly with movable obstacles like toys and electric wires, and often get stuck under sofas due to inadequate obstacle detection and classification methods.
Innovation Solution
A method using a time-of-flight (TOF) camera to classify obstacles into types like wall, toy, doorsill, sofa, and electric wire, and an infrared sensor for deceleration and obstacle avoidance, allowing the robot to adjust its path to avoid collisions based on obstacle height and type.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If a single-line laser is employed for obstacle detection to save cost, then manufacturing cost is reduced, but obstacle detection capability deteriorates and the robot fails to detect obstacles like sofa-type obstacles
Solution Approach 1:
The patent combines TOF camera depth information with infrared sensor detection to create a multi-modal obstacle detection system. The TOF camera provides depth maps for obstacle classification while the infrared sensor detects thermal signatures, merging multiple detection modalities to overcome the limitations of single-line laser detection.
Solution Approach 2:
The TOF camera serves multiple functions: it generates depth information for obstacle detection, provides depth maps for obstacle classification into different types (sofa-type, toy-type, wall-type), and works in conjunction with the infrared sensor for comprehensive obstacle identification, replacing the need for multiple separate detection systems.
2Device complexity
If a single camera is used as a vision device, then device complexity is reduced, but distance prediction capability deteriorates and the robot fails to detect obstacles in advance
Solution Approach 1:
The patent replaces traditional mechanical/geometric vision systems with a TOF camera that uses time-of-flight measurement principles. Instead of relying on complex multi-camera stereo vision or mechanical scanning systems, the TOF camera directly measures distance by timing light flight, providing accurate depth information with a single sensor.
Solution Approach 2:
The TOF camera changes the detection parameter from 2D image coordinates to 3D depth information by measuring the time of flight of light. This parameter change enables the robot to obtain distance information directly, allowing for early obstacle detection and classification before physical contact occurs.
3Reliability
If the robot enters an infrared obstacle avoidance mode upon collision warning, then collision avoidance reliability is improved, but response time is reduced due to mode switching
Solution Approach 1:
The system performs preliminary obstacle classification using TOF camera depth information before the robot reaches the obstacle. By classifying obstacles into different types (sofa-type, toy-type, wall-type) in advance based on depth maps and longitudinal height calculations, the robot can pre-plan avoidance maneuvers, reducing the need for urgent mode switching during critical moments.
Solution Approach 2:
The obstacle avoidance system dynamically adjusts the robot's behavior based on real-time obstacle classification. Instead of rigid mode switching, the system continuously adapts the robot's trajectory and speed based on the classified obstacle type and position, enabling smooth transitions that maintain both reliability and response time.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Effectively prevents collisions with obstacles by classifying and responding to different types of obstacles, ensuring safe navigation and reducing the risk of getting stuck or entangled.
Implementation Method 1
a depth image of a target obstacle is obtained from a time-of-flight (TOF) camera
Implementation Method 2
an infrared sensor at a front end of a robot body... the robot in the infrared obstacle avoidance mode avoids an obstacle detected in a current traveling direction on a basis of detection information of the infrared sensor
Data Source
AI summary
A method for controlling of obstacle avoidance according to classification of obstacle based on time-of-flight (TOF) camera and cleaning robot are disclosed. The method includes: step 1: a longitudinal height of a target obstacle is calculated and obtained by combining a depth of the target obstacle collected by a TOF camera and intrinsic parameters and extrinsic parameters of the TOF camera, and the target obstacle is identified and classified into a wall-type obstacle, a toy-type obstacle, a doorsill-type obstacle, a sofa-type obstacle or an electric-wire-type obstacle on a basis of a data stability statistical algorithm; and step 2: a deceleration and obstacle avoidance mode or a deceleration and obstacle bypassing mode of a robot is decided according to a classification result, the longitudinal height of the target obstacle of a corresponding type and a trigger situation of a collision warning signal.