Autonomous Vehicle Lane Change Routing With Dynamic Cost Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in determining the optimal location for lane changes while navigating, often getting stuck in infinite loops due to inability to execute lane changes, which affects route efficiency and safety.
Innovation Solution
The method involves using a cost analysis based on factors like duration, traffic conditions, previous lane change history, solid white line crossings, intersection involvement, and time of day to assess the best node pairs for lane changes, with processors iterating through possible transitions to select the lowest-cost option and adjust costs dynamically to avoid infinite loops.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If the autonomous vehicle uses a simple lane change decision system, then the system complexity is reduced, but the vehicle may get stuck in infinite loops and fail to execute lane changes properly
Solution Approach 1:
The system dynamically changes the cost parameter associated with lane changes based on multiple factors including time of day, traffic conditions, and historical data. By adjusting these cost parameters, the system guides the vehicle to make appropriate lane change decisions without requiring complex hard-coded logic, thus maintaining reliability while managing complexity
Solution Approach 2:
The system incorporates feedback loops where lane change outcomes are recorded and used to update future decision-making. Historical lane change data is fed back into the cost assessment mechanism, allowing the system to learn from past experiences and improve lane change execution reliability without increasing structural complexity
2Productivity
If the autonomous vehicle assesses multiple factors for lane change decisions, then the route efficiency is improved, but the computational cost and processing time increase
Solution Approach 1:
The decision-making process is segmented into discrete cost factors (time of day, traffic conditions, historical data, etc.), each evaluated independently. This segmentation allows the system to process multiple factors efficiently by breaking down the complex assessment into manageable, modular components that can be computed separately and aggregated
3Adaptability or versatility
If the autonomous vehicle dynamically adjusts lane change costs based on historical data, then the adaptability to traffic patterns is improved, but the data processing requirements increase
Solution Approach 1:
The system performs preliminary processing of historical lane change data during off-peak periods or in advance, pre-computing cost adjustments based on historical patterns. This preliminary action reduces the real-time data processing burden while maintaining high adaptability to traffic patterns during actual lane change decisions
Data Source
AI summary
Aspects of the disclosure relate to routing an autonomous vehicle. For instance, the vehicle may be maneuvered along a route in a first lane using map information identifying a first plurality of nodes representing locations within the first lane and a second plurality of nodes representing locations within a second lane different from the first lane. While maneuvering, when the vehicle should make a lane change may be determined by assessing a cost of connecting a first node of the first plurality of nodes with a second node of a second plurality of nodes. The assessment may be used to make the lane change from the first lane to the second lane.