Mobile Robot Obstacle Sensing With 3D-to-2D Depth Projection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional obstacle avoidance sensors for mobile robots cannot perform full stereo sensing and obstacle avoidance, particularly failing to sense obstacles in a large range and at multiple levels, due to limitations in ultrasound, infrared, and two-dimensional laser systems which lack depth perception and multi-level detection capabilities.
Innovation Solution
A method and device that acquire depth image data, convert it into a coordinate system of the mobile robot, project it into a moving plane to obtain two-dimensional data, and detect obstacles within the robot's travel route, allowing for stereoscopic sensing and obstacle information acquisition similar to two-dimensional laser systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If two-dimensional laser sensing is used, then detailed obstacle information in the surrounding environment can be sensed, but obstacles outside the installation plane (low or high obstacles) cannot be detected
Solution Approach 1:
The patent transitions from two-dimensional laser sensing to three-dimensional depth image sensing, adding the depth dimension (Z-axis) to the detection capability. This allows the system to sense obstacles at multiple height levels and distances, not just in the installation plane, by capturing spatial information in three dimensions and then projecting or analyzing it according to different plane orientations.
2Loss of information
If three-dimensional depth image data is processed, then comprehensive obstacle information can be obtained, but processing complexity increases
Solution Approach 1:
The patent extracts only the relevant obstacle information from the complete three-dimensional depth image data by projecting the 3D point cloud onto two-dimensional planes (horizontal and vertical). This extraction process removes unnecessary spatial dimensions while preserving the essential obstacle detection information needed for navigation, thereby reducing processing complexity while maintaining information completeness.
3Reliability
If conventional obstacle avoidance sensors are used, then simple obstacle detection is possible, but full stereo sensing and multi-level obstacle avoidance cannot be achieved
Solution Approach 1:
The patent makes the depth image sensor serve multiple functions: it simultaneously provides horizontal plane obstacle detection, vertical plane obstacle detection, and three-dimensional spatial mapping. This multi-functionality replaces what would traditionally require multiple separate sensors (ultrasound, infrared, 2D laser), achieving comprehensive stereo sensing and multi-level obstacle avoidance while managing system complexity through a single versatile sensing device.
Data Source
Figure 1
Figure 2~3
Figure 4~5
AI summary
The present application discloses a method and device for sensing obstacle information for a mobile robot. The method includes: obtaining depth image data, converting the depth image data into data in a coordinate system of the mobile robot; converting the data in the coordinate system of the mobile robot into a projection in a moving plane of the mobile robot to obtain two-dimensional data; detecting the two-dimensional data in a range of a travel route of the mobile robot; obtaining obstacle information based on the detected two-dimensional data. The present application solves the defects that conventional obstacle avoidance sensors cannot perform full stereo sensing and obstacle avoidance, and can sense obstacles in a large range and multi-levels.