Moving robot and control method thereof
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing moving robots lack the ability to accurately determine the attribute of obstacles, which affects their driving and cleaning performance, as they rely on infrared and ultrasonic sensors that cannot differentiate between types of obstacles.
Innovation Solution
The implementation of an obstacle recognition system using machine learning, specifically deep learning techniques, such as Convolutional Neural Networks (CNNs), that processes images from cameras to identify and classify obstacles based on pre-learned attributes, allowing the robot to adjust its movement patterns accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If infrared and ultrasonic sensors are used to detect obstacles, then the robot can detect the presence and distance of obstacles, but it cannot determine the attribute or type of the obstacle
Solution Approach 1:
The patent introduces an image processing unit as an intermediary component that captures images of obstacles using a camera, processes these images to extract feature information, and combines this visual data with sensor data from infrared and ultrasonic sensors. This intermediary image processing system enables the robot to determine obstacle attributes (such as whether an obstacle is a pet, person, or object) while maintaining the distance detection capabilities of the original sensors.
2Device complexity
If the robot uses simple sensor-based obstacle detection, then the device complexity is low, but the obstacle recognition confidence and cleaning performance are insufficient
Solution Approach 1:
The patent merges multiple detection systems into a unified obstacle recognition system. It combines the distance detection capabilities of infrared and ultrasonic sensors with the visual recognition capabilities of a camera and image processing unit. The controller integrates data from all these sources to make comprehensive obstacle identification and classification, thereby significantly improving recognition confidence and cleaning performance without requiring a complete system redesign.
Solution Approach 2:
The patent creates a multi-functional detection system where the camera and image processing unit serve multiple purposes: identifying obstacle types (pets, persons, objects), determining obstacle attributes, and providing visual confirmation for the controller's decision-making process. This universal image processing component enhances the reliability of the entire obstacle detection system while maintaining reasonable device complexity.
3Object-affected harmful factors
If the robot performs avoidance driving for all detected obstacles, then collision avoidance is achieved, but cleaning efficiency decreases due to unnecessary path adjustments
Solution Approach 1:
The patent applies different avoidance strategies based on the local characteristics of each obstacle type. The controller analyzes image processing results to determine obstacle attributes and applies customized avoidance behaviors: for example, pets may receive gentle avoidance with continued cleaning in the area, persons trigger immediate avoidance and area re-cleaning, and stationary objects receive standard avoidance. This localized, attribute-based approach maintains collision avoidance while preserving cleaning efficiency by avoiding unnecessary path adjustments for certain obstacle types.
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
This approach significantly improves the robot's ability to recognize and avoid obstacles with high accuracy, enhancing its navigation and cleaning efficiency by enabling it to differentiate between movable and immovable objects, and adjusting its path accordingly.
Implementation Method 1
an image acquisition unit (120, 120a, 120b) for acquiring a surrounding image of the body (110)
Data Source
AI summary
Disclosed is a moving robot including: a travel unit configured to move a body; an image acquisition unit configured to acquire a surrounding image of the body; a sensor unit having one or more sensors configured to detect an obstacle while the body moves; a controller configured to: upon detection of an obstacle by the sensor unit, recognize an attribute of the obstacle based on an image acquired by the image acquisition unit, and control driving of the travel unit based on the attribute of the obstacle; and a sound output unit configured to: output preset sound when the recognized attribute of the obstacle indicates a movable obstacle. Accordingly, the moving robot improves stability, user convenience, driving efficiency, and cleaning efficiency.