Vehicle Path Estimation Using Dynamic Territory Probability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle driving assistance systems struggle to accurately predict the most probable path of a vehicle on a road network, especially when faced with dynamic changes in road conditions and territory use, leading to suboptimal performance and reliability in controlling vehicle dynamics.
Innovation Solution
A system that dynamically assigns travel probabilities to road sections based on the designated use of the territory, incorporating real-time updates and specific events, such as shopping centers, tourist destinations, and traffic conditions, to refine path prediction and enhance driving assistance systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If travel probabilities are assigned based on static road class definitions in cartographic reference maps, then the system is simple to implement, but the accuracy of path prediction deteriorates because static definitions cannot reflect real-time traffic conditions and dynamic changes in the road network
Solution Approach 1:
The patent applies the dynamics principle by transitioning from static road class definitions to dynamic travel probability assignments. The system continuously updates travel probabilities based on real-time traffic conditions, vehicle location data, and changing road network states. This allows the path prediction system to adapt to dynamic environmental changes while maintaining computational feasibility through probabilistic models.
Solution Approach 2:
The patent implements feedback by using actual traffic data and vehicle location information to continuously refine and update travel probability assignments. The system collects data on actual vehicle paths taken at intersections and uses this feedback to adjust future probability predictions, creating a closed-loop system that improves accuracy over time while building upon the simple static road class foundation.
2Measurement precision
If travel probabilities are updated dynamically using traffic statistics and real-time data acquisition systems, then the path prediction accuracy is improved, but the system complexity increases due to the need for continuous data collection and processing
Solution Approach 1:
The patent applies universality by designing a modular architecture where the data acquisition system, processing unit, and probability update mechanisms can serve multiple functions. The same infrastructure supports various path prediction scenarios, different types of traffic data integration, and can be adapted to different road network configurations, reducing overall system complexity through shared components.
Solution Approach 2:
The patent uses parameter changes by adjusting travel probability values based on different traffic conditions, time periods, and road characteristics. The system modifies probabilistic parameters dynamically without changing the fundamental system architecture, allowing accurate path prediction through parameter tuning rather than structural complexity.
3Productivity
If the system considers multiple successive road sections and extended path prediction horizons, then the optimization of vehicle performance is enhanced, but the computational complexity increases due to the larger number of possible path combinations
Solution Approach 1:
The patent applies dynamics by implementing adaptive path prediction that adjusts the prediction horizon and number of successive road sections considered based on current driving conditions, vehicle type, and intersection characteristics. The system dynamically extends or reduces the analysis depth to balance computational load with optimization needs, enabling extended path consideration without excessive complexity.
Solution Approach 2:
The patent uses local quality by applying different levels of computational effort to different road sections and path segments. The system focuses detailed probabilistic analysis on critical decision points and intersections while using simplified models for less critical sections, allowing comprehensive multi-section path optimization with localized computational intensity where most beneficial.
Data Source
Figure 1
Figure 2
Figure 3a~3c
AI summary
A system and a method are described for estimating the most probable path followed by a vehicle (V) on a road network including road sections (R, R'), originating from respective intersection or branching nodes (N; D), to which a travel probability is assigned, comprising: - a device (G) for acquiring a data element for locating the vehicle (V) on the road network; - a map (DB1, DB2) of the territory through which the road network passes, comprising data indicative of the corresponding designated use of a plurality of areas of territory (C; T) associated with the sections (R, R') of the road network; and - a processing unit (P) arranged to assign an improved travel probability to a road section (R; R'), originating from a road intersection or branching node (N; D), as a function of the designated use of the area of territory (C; T) associated with the aforesaid road section (R; R'), and to calculate the most probable path for the vehicle according to the improved probabilities assigned to the consecutive road sections, comprising a plurality of consecutive road sections originating in the intersection or branching node (N; D) approached by the vehicle (V) for which the joint travel probability is highest.