Robot Ground Obstacle Detection Using Calibrated Depth Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robots operating in busy spaces with diverse flooring and obstacles face challenges in identifying the driving surface and obstacles, leading to potential stops or falls due to inadequate sensing of varying factors on the floor.
Innovation Solution
A method and apparatus that utilize depth-sensing technology to generate and calibrate depth information, allowing robots to identify obstacles by distinguishing between floor surface and obstacles, and store this information in a temporary map for real-time navigation and obstacle avoidance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the robot uses depth-sensing to identify obstacles on the driving surface, then the measurement precision of obstacles is improved, but the device complexity increases
Solution Approach 1:
The patent segments the driving surface into multiple regions (first driving surface region and second driving surface region) with different height thresholds. The controller selectively applies different height threshold values to different regions, allowing precise obstacle detection while simplifying the overall sensing system through regional differentiation rather than requiring complex global analysis.
Solution Approach 2:
The patent applies local quality by setting different height threshold values for different driving surface regions. The first height threshold value applies to the first driving surface region and the second height threshold value applies to the second driving surface region, enabling the system to adapt to local variations in the driving surface without increasing overall device complexity.
2Measurement precision
If the robot stores depth information and calibrates it using floor surface information, then the measurement precision is improved, but the loss of time increases
Solution Approach 1:
The patent performs preliminary action by storing depth information and floor surface information in advance before obstacle detection is needed. The controller calibrates the depth information using the pre-stored floor surface information, which reduces processing time during actual operation since the reference data is already available without requiring real-time acquisition.
Solution Approach 2:
The patent implements feedback by using stored floor surface information as a reference to calibrate real-time depth information. The controller compares the depth-sensed object information against the pre-stored floor surface characteristics and adjusts the interpretation accordingly, improving accuracy while maintaining efficient processing through iterative refinement rather than complete re-analysis.
3Measurement precision
If the robot depth-senses objects in the advancing direction, then the measurement precision of obstacles is improved, but the loss of energy increases
Solution Approach 1:
The patent applies local quality by focusing depth-sensing resources on the advancing direction where obstacles are most critical. The sensing module concentrates measurement efforts in the forward path rather than uniformly scanning all directions, improving obstacle detection precision while reducing overall energy consumption by limiting intensive sensing to the most necessary area.
4Measurement precision
If the robot identifies obstacles by calibrating depth information with floor surface information, then the measurement precision is improved, but the device complexity increases
Solution Approach 1:
The patent segments the data processing into distinct modules: the sensing module captures depth information, the controller calibrates it using pre-stored floor surface information, and the system generates calibrated depth information for obstacle identification. This segmentation of processing functions improves obstacle identification accuracy while managing complexity through modular organization of processing tasks.
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
Enables precise detection and avoidance of obstacles within several meters, allowing robots to move safely in broad spaces by processing 3D data in real-time and distinguishing between floor surface and obstacles, reducing the risk of collisions.
Implementation Method 1
depth-sensing objects in an advancing direction to thereby generate first depth information, by a sensing module of a robot
Data Source
AI summary
The present disclosure relates to a method for identifying an obstacle on a driving ground and a robot for implementing the same, and according to one embodiment of the present disclosure, the method for identifying an obstacle on a driving ground comprises the steps of allowing: a sensing module of the robot to sense the depths of objects in a driving direction so as to generate first depth information; a plane analysis unit of the sensing module to calibrate second depth information by using ground information stored by a map storage of the robot so as to generate the first depth information; a control unit to identify an obstacle from the second depth information; and the control unit to store position information of the identified obstacle in a temporary map of the map storage.