Mobile robot and method for controlling same
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing moving robots face challenges in autonomously recognizing and avoiding obstacles without user input, particularly in confined spaces, where they may become trapped and require increased escape algorithms to navigate effectively.
Innovation Solution
A moving robot equipped with a sensor unit for detecting obstacles, a storage unit for mapping obstacle locations, and an image acquisition unit for attribute recognition through machine learning, allowing the robot to autonomously detect and escape from confinement by learning obstacle attributes and adjusting its path accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional sensors (infrared or ultrasonic) are used for obstacle detection, then the robot can detect obstacles and avoid them, but the robot may become trapped in confined spaces and require increased escape algorithms
Solution Approach 1:
The robot performs preliminary mapping of the environment by detecting and storing obstacle locations before navigation. By pre-processing the spatial information and creating a map of obstacle areas, the robot prepares advance knowledge that prevents getting trapped, eliminating the need for complex escape algorithms during actual navigation
Solution Approach 2:
The patent introduces an image acquisition unit and machine learning module as intermediaries between the sensor unit and the control unit. These intermediaries process raw sensor data to extract meaningful obstacle attributes and classifications, improving detection reliability while keeping the control logic simpler through automated image analysis
2Extent of automation
If the robot uses machine learning for autonomous obstacle recognition, then user input is not required, but the device complexity increases
Solution Approach 1:
The robot achieves self-service by autonomously acquiring images, processing them through machine learning models, and automatically recognizing obstacle attributes without any user input. The system serves itself by integrating the image acquisition unit, machine learning module, and control unit into a self-sufficient autonomous recognition system
Solution Approach 2:
The patent merges multiple functions into integrated components: the image acquisition unit combines imaging and obstacle detection functions, while the machine learning module integrates attribute recognition and classification. This merging reduces overall system complexity by consolidating separate operations into unified processing pipelines
3Reliability
If the robot stores detailed obstacle location information and attributes, then collision prevention improves, but the storage requirements and processing load increase
Solution Approach 1:
The system extracts only the essential and relevant features from obstacle images and sensor data for storage, such as obstacle location coordinates, basic attributes (size, shape, material), and classification labels. By taking out only the necessary information rather than storing complete raw data, the system achieves reliable collision prevention with minimized storage requirements
Solution Approach 2:
The patent applies local quality by storing different types of information at different levels of detail based on their importance. Critical obstacle locations and attributes receive higher storage priority and more detailed recording, while less critical information is stored with lower fidelity or aggregated, optimizing the balance between collision prevention reliability and storage efficiency
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
The robot effectively prevents collisions by storing obstacle location information and attributes, enabling autonomous navigation and escape from confinement even in the absence of user input, enhancing user convenience and reliability.
Implementation Method 1
The infrared sensor is to determine the presence of the obstacle and the distance from the obstacle based on the quantity of light reflected from the obstacle
Implementation Method 2
The ultrasonic sensor is to determine the distance from the obstacle using the difference between a time point at which an ultrasonic wave is emitted and a time point at which the ultrasonic wave reflected from the obstacle is received
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
A robot cleaner according to one embodiment of the present invention comprises: a travelling unit to move a main body, an image acquisition unit to acquire an image around the main body, a sensor unit including at least one sensor to sense an obstacle during moving, a storage unit to store information on a location of the sensed obstacle and information on a location of the moving robot, to register, into a map, an obstacle area of the obstacle, and to store an image from the image acquisition unit in the obstacle area, an obstacle acquisition module to determine a final attribute of the obstacle using the attributes of the obstacle obtained based on machine learning, and a control unit to detect attributes of obstacles through the obstacle recognition module if detecting a confinement state by the obstacles and to control the traveling unit to move one of the obstacles.