Self-Driving Car Lane Path Scoring for Fewer Lane Changes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current self-driving car technologies face challenges in planning and executing routes efficiently, particularly in minimizing lane-changing maneuvers, which can be complex due to numerous lane-level alternatives and dynamic traffic conditions.
Innovation Solution
A system and method that utilize a combination of global and local scoring models to evaluate and adjust lane transitions, incorporating traffic rules and real-time data from sensors to determine the most desirable lane paths, thereby reducing the number of lane changes and optimizing route planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the system evaluates all lane-level alternatives to find the optimal route, then route planning accuracy is improved, but computational complexity and processing time increase significantly
Solution Approach 1:
The patent divides the route planning process into two distinct stages: global route planning that identifies the overall path from origin to destination, and local lane-level planning that optimizes specific lane transitions along that path. This segmentation allows the system to evaluate lane-level alternatives only where necessary, reducing overall computational complexity while maintaining routing accuracy.
Solution Approach 2:
The system performs preliminary global route planning to establish the overall path before conducting detailed local lane-level evaluation. By pre-determining the general route and identifying only those segments requiring lane changes, the system reduces the scope of complex evaluations to specific critical areas, thereby managing computational load effectively.
2Productivity
If the system performs frequent lane-changing maneuvers to optimize route efficiency, then travel time is reduced, but safety and operational complexity increase
Solution Approach 1:
The patent implements a dynamic lane change evaluation system that continuously assesses current traffic conditions, sensor data, and environmental factors before recommending lane transitions. The system adapts its lane-changing strategy in real-time, performing maneuvers only when conditions are favorable and safe, thus balancing route efficiency with operational safety.
Solution Approach 2:
The system incorporates real-time feedback from sensors and traffic conditions to evaluate the safety and desirability of potential lane changes. By continuously monitoring the environment and adjusting lane transition decisions based on current conditions, the system ensures that lane changes are performed only when they improve efficiency without compromising safety.
3Stability of the object's composition
If the system uses a single comprehensive scoring model to evaluate all lane transitions, then evaluation consistency is improved, but adaptability to local conditions deteriorates
Solution Approach 1:
The patent employs different scoring models for different stages of route planning: a global scoring model that applies consistent criteria across the entire route, and local scoring models that adapt to specific local conditions at each lane transition point. This allows the system to maintain overall evaluation consistency while adapting to local traffic patterns, road geometry, and environmental factors.
Solution Approach 2:
The evaluation system is segmented into global and local components. The global scoring model provides consistent baseline evaluation across the entire route, while local scoring models are applied specifically to lane transition segments, allowing adaptability to local conditions without compromising overall evaluation consistency.
Data Source
AI summary
Method and device for controlling operation of a Self-Driving Car. The method includes determining route-level and lane-level information for generating a graph-structure, applying a first model for assigning costs to respective edges, determining scores for vertices based on the costs, storing the edges with the costs and the vertices with the scores. The method also includes at a given moment in time during operation: acquiring a lane path indicative of a lane segment extending from the current location without a lane-changing manoeuvre. The method includes, for the lane path: identifying a series of vertices covered by the lane segment, applying a second model for assigning additional costs to lane-path-departing edges of the series of vertices thereby determining locally-increased costs, determining a locally-adjusted scores for vertices in the series of vertices based on the locally-increased costs, and identifying a lane path score for the lane path based on the locally-adjusted scores.