Mobile robot and control method therefor
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional mobile robots lack accurate object attribute recognition, leading to unreliable object avoidance and inefficient cleaning performance, as they cannot distinguish between objects they can climb over and those that pose a hazard, such as electric wires or human hair.
Innovation Solution
A mobile robot equipped with an image acquisition unit, sensor units, and a controller that performs machine learning-based object recognition, allowing it to extract relevant image data and adjust its travel pattern based on object attributes, enabling reliable object recognition and avoidance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If infrared sensor or ultrasonic sensor is used to sense objects, then the mobile robot can detect object presence and distance, but the robot cannot determine object attributes leading to unreliable avoidance
Solution Approach 1:
The patent combines multiple sensors (infrared sensor, ultrasonic sensor, and camera) into an integrated sensing system. The infrared and ultrasonic sensors detect object presence and distance, while the camera captures images for attribute recognition. This merging of sensing modalities allows the robot to both detect objects accurately and determine their attributes reliably, resolving the contradiction between detection accuracy and attribute recognition reliability.
Solution Approach 2:
The camera acts as an intermediary between the basic object detection sensors and the decision-making system. While infrared and ultrasonic sensors provide object presence and distance information, the camera serves as an intermediate component that captures visual information to determine object attributes (such as whether the object is climbable or hazardous). This intermediary enables the transition from simple detection to reliable attribute recognition.
2Productivity
If the robot climbs over low objects detected by sensors, then the robot maintains forward movement efficiency, but it may be restricted or damaged by hazardous objects like electric wires
Solution Approach 1:
The system performs preliminary action by using the camera to capture images and determine object attributes before the robot attempts to climb or interact with the object. By预先 identifying hazardous objects like electric wires through image analysis, the robot can avoid them before encountering restrictions or damage, while still maintaining efficient movement over safe low obstacles.
Solution Approach 2:
The system implements feedback by continuously monitoring the environment with sensors and camera, determining object attributes, and using this information to adjust movement decisions. The feedback loop allows the robot to learn from previous interactions and improve its ability to distinguish between climbable objects and hazardous objects, thereby maintaining productivity while avoiding harmful factors.
3Device complexity
If the robot uses simple height-based object classification, then the control logic remains simple, but the robot cannot distinguish between safe objects and hazardous objects
Solution Approach 1:
The patent replaces the mechanical/simple height-based classification system with an optical/image-based recognition system. Instead of relying solely on ultrasonic sensor data and simple height thresholds, the system uses camera imaging and image processing to determine object attributes. This substitution maintains relatively simple control logic while dramatically improving the reliability of distinguishing between safe and hazardous objects.
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 mobile robot achieves improved accuracy in object attribute recognition and avoidance, enhancing user convenience and cleaning efficiency by accurately determining object attributes and adjusting its movement accordingly.
Implementation Method 1
the ultrasonic sensor emits an ultrasound wave having a predetermined period and, in response to ultrasonic waves reflected by an object, determines a distance to the object based on a difference between the time to emit the ultrasonic waves and the time for the ultrasonic waves to return to the object
Implementation Method 2
The infrared sensor determines presence of an object and a distance to the object based on an amount of light reflected by the object
Data Source
Figure 1~3
Figure 4~6
Figure 7~9
AI summary
A mobile robot in one general aspect of the present invention includes: a travel drive unit configured to move a main body; an image acquisition unit configured to acquire an image of surroundings of the main body; a storage configured to store the image acquired by the image acquisition unit; a sensor unit having one or more sensors configured to sense an object during the movement of the body; and a controller configured to perform control to extract a part of the image acquired by the image acquisition unit in correspondence to a direction in which the object sensed by the sensor unit is present, and accordingly, it is possible to extract data that is efficient for machine learning and object attribute recognition.