Vehicle Control Unified Object Boundary for Interference Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle control systems fail to provide a fine-granularity prediction of interference potential between multiple objects and a vehicle, as they rely on representative evaluation values without considering positional relationships between objects.
Innovation Solution
A vehicle control apparatus that forms unified objects based on positional relationships between detected objects within a predetermined distance range, using geometric shapes like polygons to predict interference potential, thereby accounting for the geometry of the vehicle and detection performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If representative evaluation values (TTC) are used for grouped objects, then the frequency of alarm activation is decreased and driver annoyance is reduced, but the granularity of prediction regarding interference potential is insufficient
Solution Approach 1:
The patent segments the interference potential prediction by introducing a unified object boundary that divides the spatial relationship between grouped objects and the vehicle. Instead of treating all grouped objects uniformly, the boundary creates distinct regions (inside/outside the boundary) that enable differentiated prediction of interference potential for each object relative to the vehicle's geometry.
Solution Approach 2:
The patent adds a spatial dimension to the prediction by introducing the unified object boundary concept. This boundary creates a new spatial reference frame that allows the system to evaluate not just the representative TTC value, but also the positional relationship of each object to the vehicle through the boundary structure, thereby enhancing prediction granularity.
2Measurement precision
If fine-granularity prediction is performed for each object, then the accuracy of interference potential prediction is improved, but the computation time increases
Solution Approach 1:
The patent merges the evaluation of multiple grouped objects into a unified prediction framework. By introducing the unified object boundary, the system can evaluate the interference potential of multiple objects simultaneously through a single boundary-based assessment, rather than performing separate detailed evaluations for each object, thus reducing overall computation time while maintaining fine-granularity prediction.
Solution Approach 2:
The patent uses the unified object boundary as a simplified geometric representation that copies the essential spatial relationship information without requiring complex individual object models. This boundary acts as a computational proxy that preserves the necessary positional relationship data while significantly reducing the computational complexity of interference potential prediction.
3Device complexity
If the boundary is determined without considering vehicle geometry, then the computation is simpler, but the accuracy of determining whether the vehicle can pass through clearances between objects is reduced
Solution Approach 1:
The patent applies local quality by adapting the unified object boundary determination to the specific geometry of the vehicle. The boundary is not a generic geometric shape but is determined based on the vehicle's actual dimensions and shape characteristics, allowing the prediction system to account for local geometric features that affect clearance determination while maintaining computational efficiency.
Data Source
AI summary
An integrated object formation unit of a vehicle control device forms integrated objects, which are integral objects, the boundaries of the integrated objects being determined from the positional relationship between two or ore objects in a prescribed distance range. An interference prediction unit of the vehicle control device predicts the probability of the integrated objects, instead of each of the objects, coming into contact with, or near, a vehicle.