Mobile Robot Obstacle Attribute Recognition for Adaptive Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing moving robots lack the ability to accurately determine the attribute of obstacles, leading to inefficient obstacle recognition and avoidance, which affects their driving and cleaning performance, as they cannot differentiate between movable and immovable objects, resulting in potential collisions and disturbances to users.
Innovation Solution
A moving robot equipped with an image acquisition unit, sensor unit, and controller that recognizes obstacle attributes using machine learning, allowing it to adjust its driving pattern based on the detected attributes and perform efficient obstacle avoidance by extracting partial regions from images for improved recognition and sound output for movable obstacles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the robot uses only height-based obstacle detection, then it can determine whether to go over the obstacle, but it cannot identify the attribute of the obstacle leading to potential collisions with movable objects
Solution Approach 1:
The obstacle detection process is segmented into multiple stages: initial detection by ultrasonic sensor, attribute classification by deep learning model, and differentiated response execution. This segmentation allows the system to process only relevant information at each stage, improving accuracy without requiring all sensors to operate continuously.
Solution Approach 2:
A deep learning-based image recognition module is introduced as an intermediary between the ultrasonic sensor and the driving control system. This intermediary analyzes obstacle attributes and provides classification results that guide the final driving decision, enabling the robot to distinguish between movable and immovable obstacles.
2Reliability
If the robot avoids all detected obstacles, then it prevents collisions with immovable objects, but it may collide with movable obstacles during avoidance driving
Solution Approach 1:
The driving control system dynamically adjusts avoidance behavior based on obstacle attributes. For immovable obstacles, the robot performs standard avoidance driving. For movable obstacles, the system modifies the avoidance pattern to reduce collision risk, demonstrating dynamic adaptation to different obstacle types.
Solution Approach 2:
The system changes driving parameters such as avoidance angle, speed, and timing based on obstacle attributes. When a movable obstacle is detected, the robot adjusts these parameters to perform gentler avoidance maneuvers, reducing the likelihood of collision while still maintaining safety.
3Ease of operation
If the robot follows the user when the user moves, then it maintains proximity to the user, but it disturbs the user and may collide with movable obstacles
Solution Approach 1:
The robot performs preliminary obstacle attribute recognition before executing following behavior. When a movable obstacle (such as a moving user) is detected, the robot proactively adjusts its following strategy to avoid disturbance and potential collision, rather than reacting after the disturbance occurs.
4Measurement precision
If the robot uses deep learning for obstacle attribute recognition, then it achieves high-confidence recognition, but it requires significant computational resources and processing time
Solution Approach 1:
The system applies deep learning processing selectively rather than continuously. It processes images only when obstacles are detected by the ultrasonic sensor, performing partial processing on relevant regions. This approach maintains high recognition accuracy while significantly reducing overall processing time and computational resource consumption.
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 achieves high-confidence obstacle recognition and avoidance, enhancing its stability, user convenience, and cleaning efficiency by accurately identifying and responding to various obstacles, including movable objects, thereby preventing collisions and optimizing its cleaning path.
Implementation Method 1
The ultrasonic sensor emits ultrasonic waves, and, if there is an ultrasonic wave reflected by an obstacle, the ultrasonic sensor determines a distance to the obstacle based on a time difference between when the ultrasonic wave is emitted and when the reflected ultrasonic wave is received
Implementation Method 2
The infrared sensor determines the presence of the obstacle and a distance thereto based on an amount of light reflected from the obstacle and a time taken to receive the reflected light
Data Source
Figure 1
Figure 2~3
Figure 4~5
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.