Free Space Estimation Using Sensor-Fused Virtual Polygons
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies for estimating free space around a moving vehicle are computationally intensive, inefficient, and unable to provide real-time data, especially in dynamically changing environments, leading to delayed and inaccurate representations of obstacle-free areas.
Innovation Solution
A system that uses a combination of ultrasonic sensors and cameras to generate virtual polygons representing the boundary of free space, employing AI and machine learning models to combine and adjust measurements from different sensors, reducing noise and providing a lightweight, efficient estimation of free space.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If occupancy grid generation is used to estimate free space, then high-detail understanding is achieved, but computational complexity and memory consumption increase significantly
Solution Approach 1:
The patent extracts only the essential information needed for free space estimation from the environment, rather than generating a complete occupancy grid. It uses sensor data to directly compute distance measurements and generate simplified polygon representations of free space boundaries, eliminating the need for full grid generation while maintaining estimation accuracy
Solution Approach 2:
The patent creates simplified polygon copies that represent the essential boundaries of free space, rather than maintaining the complete detailed occupancy grid. These polygon representations capture the critical free space information needed for autonomous navigation with much lower computational overhead
2Measurement precision
If occupancy grid generation is used, then detailed free space mapping is achieved, but real-time performance is lost due to processing time
Solution Approach 1:
The system extracts only the critical distance measurements and boundary information from sensor data, skipping the time-consuming full grid generation process. This extraction approach maintains sufficient mapping detail for autonomous navigation while achieving real-time processing speeds
Solution Approach 2:
The patent performs partial occupancy grid generation by computing only the necessary polygon representations of free space boundaries rather than generating the complete grid. This partial action provides sufficient information for real-time autonomous movement decisions without the full computational burden
3Loss of information
If large data storage volumes are used for occupancy grid, then comprehensive environment understanding is achieved, but efficiency decreases
Solution Approach 1:
The patent extracts and retains only the essential environmental information needed for free space estimation, storing compact polygon representations and distance measurements rather than complete occupancy grids. This extraction maintains sufficient environmental understanding while dramatically improving processing efficiency
Solution Approach 2:
The patent changes the data representation parameters from detailed occupancy grid cells to simplified polygon boundaries and key distance measurements. This parameter transformation reduces data storage requirements while preserving the critical free space information needed for autonomous navigation
Data Source
Figure 1
Figure 2
Figure 3
AI summary
One or more embodiments herein can enable identification of an obstacle free area about an object. An exemplary system can comprise a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory, wherein the computer executable components can comprise an obtaining component that obtains raw data defining a physical state of an environment around an object from a vantage of the object, and a generation component that, based on the raw data, generates a dimension of a portion or more of a virtual polygon representing a boundary about the object, wherein the boundary bounds free space about the object. A sensing sub-system can comprise both an ultrasonic sensor and a camera that can separately sense the environment about the object from the vantage of the object to thereby generate separate polygon measurement sets.