Vehicle Collision Detection Using Virtual Boundaries
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle collision avoidance systems require extensive data and complex computations to predict the intent and motion of target vehicles, making them inefficient and prone to errors in predicting potential collisions.
Innovation Solution
The system identifies virtual boundaries between host and target vehicle lanes based on predicted paths, determines constraint values from boundary approach velocities and accelerations, and performs threat assessments to actuate vehicle components for collision avoidance, using fewer data inputs and computations compared to neural networks or machine learning methods.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If neural networks or machine learning methods are used to predict target vehicle intent and motion, then prediction accuracy may be improved, but data requirements and computational complexity increase significantly
Solution Approach 1:
The patent extracts only the essential motion parameters (position, velocity, acceleration) needed for collision prediction from the target vehicle's movement, rather than using comprehensive machine learning models that process extensive data. This selective extraction reduces computational complexity while maintaining prediction effectiveness for collision avoidance scenarios.
Solution Approach 2:
The system performs preliminary calculations by establishing virtual boundaries and constraint values in advance based on current motion states. By pre-defining safety margins and constraint thresholds before collisions occur, the system enables rapid threat assessment without requiring complex real-time computations, thus reducing computational complexity while preserving prediction accuracy.
2Reliability
If more data inputs and computations are used to predict target vehicle intent, then prediction reliability may improve, but system efficiency decreases
Solution Approach 1:
The patent changes the parameters used for prediction from extensive historical and environmental data to focused real-time motion parameters (position, velocity, acceleration) relative to virtual boundaries. This parameter transformation maintains prediction reliability by capturing essential collision risk information while dramatically improving system efficiency through reduced computational load.
Solution Approach 2:
The system replaces complex machine learning computational systems with a physics-based mechanical model that uses virtual boundaries and constraint values. This substitution maintains prediction reliability through physically grounded collision mechanics while improving efficiency by using straightforward mathematical calculations instead of resource-intensive neural network computations.
3Speed
If virtual boundaries and constraint values are used for threat assessment, then collision prediction speed improves, but system complexity increases
Solution Approach 1:
The patent segments the prediction space into virtual boundaries that divide the roadway into safe and unsafe zones. By segmenting the continuous motion space into discrete regions with defined constraint values, the system enables rapid threat assessment through simple boundary crossing detection, improving prediction speed while keeping system complexity manageable through structured spatial organization.
Data Source
AI summary
A computer includes a processor and a memory storing instructions executable by the processor to identify a virtual boundary between a host roadway lane of a host vehicle and a target roadway lane of a target vehicle, the virtual boundary based on a predicted path of the target vehicle, determine a first constraint value based on a boundary approach velocity of the target vehicle, determine a second constraint value based on (1) a boundary approach velocity of the host vehicle and (2) a boundary approach acceleration of the host vehicle and perform a threat assessment of a collision between the host vehicle and the target vehicle upon determining that the first constraint value violates a first threshold or the second constraint value violates a second threshold.