Vehicle Sensor Field Modeling to Exclude Self-Return Signals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in accurately distinguishing between sensor data from the vehicle itself and data from external objects, leading to potential false positives and impacts on driving decisions.
Innovation Solution
A method is developed to generate a refined 3D mesh representation of a vehicle's sensor fields of view, using sensor data from various scenarios to create a model that excludes self-return signals, allowing for more accurate object detection and driving decisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensors are used to detect external objects, then object detection capability is improved, but false positive signals from the vehicle itself increase
Solution Approach 1:
The patent segments the sensor detection space by creating a 3D mesh model that divides the environment into regions occupied by the vehicle and regions available for external object detection. This segmentation allows the system to distinguish between self-return signals and genuine external objects by spatial separation.
Solution Approach 2:
The patent extracts and removes false positive signals by comparing sensor data against the 3D mesh model of the vehicle. Signals that correspond to points within the mesh (self-return signals) are identified and excluded from further processing, leaving only genuine external object detections.
2Device complexity
If a coarse bounding box model is used to represent the vehicle, then model creation is simplified, but accuracy in excluding self-return signals deteriorates
Solution Approach 1:
The patent transitions from a 2D bounding box representation to a 3D mesh model, adding dimensional accuracy to the vehicle representation. This 3D modeling approach captures the complex geometry of the vehicle more precisely, enabling better distinction between self-return signals and external objects while maintaining computational feasibility.
Data Source
AI summary
The technology relates to developing a highly accurate understanding of a vehicle's sensor fields of view in relation to the vehicle itself. A training phase is employed to gather sensor data in various situations and scenarios, and a modeling phase takes such information and identifies self-returns and other signals that should either be excluded from analysis during real-time driving or accounted for to avoid false positives. The result is a sensor field of view model for a particular vehicle, which can be extended to other similar makes and models of that vehicle. This approach enables a vehicle to determine when sensor data is of the vehicle or something else. As a result, the detailed modeling allowing the on-board computing system to make driving decisions and take other actions based on accurate sensor information.