Automated Driving Control Level Adjustment for Dense Road Events
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional automated driving systems face high processing loads and may fail to perform appropriate driving when large amounts of map information are involved, leading to inefficiencies.
Innovation Solution
A vehicle control system that includes a recognizer, determiner, and driving controller to adjust the control level of automated driving based on the number of events within a predetermined range, lowering the control level when the number of events exceeds an upper limit.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If automated driving control is performed based on large amounts of map information, then the accuracy of automated driving is improved, but the processing load becomes high
Solution Approach 1:
The patent segments the map information into discrete events (e.g., intersections, merges, lane changes) within a predetermined range ahead of the vehicle. Instead of processing all map information uniformly, the system identifies and processes only relevant event segments, reducing the overall processing load while maintaining accuracy for critical driving decisions.
Solution Approach 2:
The patent extracts only the necessary event information from the large amount of map data. The determiner identifies specific events that affect automated driving control (such as branching points, merging points, traffic lights) and extracts only these relevant elements for processing, leaving out unnecessary map information to reduce computational burden.
2Extent of automation
If the control level of automated driving is maintained high in complex environments, then the automation performance is improved, but the system reliability deteriorates due to high processing load
Solution Approach 1:
The patent implements dynamic adjustment of the control level based on the number of events detected in the predetermined range. When the number of events exceeds an upper limit, the system automatically lowers the control level from fully automated to partially automated or manual control. This dynamic adaptation ensures system reliability is maintained by preventing overload while preserving high automation performance in less complex environments.
3Loss of information
If all events on the map are processed for automated driving control, then the completeness of driving information is improved, but the processing time increases
Solution Approach 1:
The patent applies local quality by focusing processing resources on events within a predetermined range ahead of the vehicle's current position. Instead of uniformly processing all map information, the system concentrates computational effort on locally relevant events that will impact near-term driving decisions, reducing processing time while maintaining completeness of critical driving information.
Data Source
AI summary
A vehicle control device according to an embodiment includes: a recognizer that recognizes a situation around a vehicle; a determiner that determines events that define a traveling state of the vehicle based on the situation recognized by the recognizer, a route to a destination of the vehicle, and a position of the vehicle; and a driving controller that performs automated driving that controls at least one of acceleration/deceleration and steering of the vehicle based on the events determined by the determiner, wherein the driving controller changes the control level of the automated driving according to the number of events within a predetermined range in a traveling direction of the vehicle.