Autonomous Vehicle Lane Guidelines for Scenario-Based Path Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current path planning for autonomous driving vehicles relies on standard reference lines, which may not be optimal and require time-consuming real-time calculations, limiting efficiency and safety.
Innovation Solution
A computer-implemented method using behavior-based driving guidelines and predefined driving scenarios to determine optimal path segments based on historical driving statistics, allowing for efficient path planning by referencing preconfigured path segments rather than dynamically calculating each segment in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a standard reference line centered on the road is used for path planning, then the path planning can be performed with simple calculations, but the reference line may not be optimal for safety and comfort
Solution Approach 1:
The patent pre-calculates and stores optimal path segments for various driving scenarios (straight driving, turning, lane changing) based on historical driving behavior data before real-time operation. During actual path planning, the system only needs to retrieve and combine these pre-computed segments according to the current driving scenario, avoiding time-consuming real-time optimization calculations while ensuring optimal safety and comfort.
2Reliability
If real-time dynamic calculation of path segments is performed, then the most optimal path can be determined, but the calculation is time-consuming and limits real-time performance
Solution Approach 1:
The system performs path optimization calculations in advance during offline training phases, storing the results as pre-configured path segments for different driving scenarios. During real-time operation, the system retrieves these pre-optimized segments based on the current driving scenario and vehicle state, achieving both optimality and real-time performance without sacrificing either.
Solution Approach 2:
The patent divides the continuous path planning problem into discrete driving scenarios (straight driving, turning, lane changing) with corresponding pre-configured path segments. This segmentation allows the system to handle complex path planning by combining simpler, pre-optimized segments rather than calculating the entire path dynamically, significantly reducing real-time computational burden while maintaining optimality.
3Reliability
If behavior-based driving guidelines are used to determine optimal path segments, then the driving route becomes more comfortable and safe, but the system complexity increases
Solution Approach 1:
The patent pre-computes and stores behavior-based optimal path segments for various driving scenarios during an offline training phase using historical driving behavior data. During real-time operation, the system only needs to retrieve the appropriate pre-configured segments based on the current driving scenario and vehicle state, avoiding the need for complex real-time behavior analysis while still achieving comfortable and safe driving routes.
Solution Approach 2:
The system creates simplified representations (copies) of complex driving behaviors by storing pre-configured path segments that capture the essence of optimal driving patterns for different scenarios. Instead of performing complex behavior analysis in real-time, the system uses these copied behavioral patterns to determine the driving route, maintaining safety and comfort while reducing system complexity.
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
In one embodiment, in response to a route from a source location to a target location, the route is analyzed to identify a list of one or more driving scenarios along the route that match one or more predetermined driving scenarios. The route is segmented into a list of route segments based on the driving scenarios. At least one of the route segments corresponds to one of the identified driving scenarios. A path is generated based on the route segments for driving an autonomous driving vehicle from the source location to the target location. The path includes a number of path segments corresponding to the route segments. At least one of the path segments of the path is determined based on a preconfigured path segment of a predetermined driving scenario associated with the path segment, without having to calculating the same at real time.