AV Routing Maps for Prioritizing High-Impact Avoidance Areas
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles (AVs) face challenges in navigating avoidance areas due to road conditions, software limitations, and real-world changes not reflected in their maps, which can impact service quality and efficiency.
Innovation Solution
A mapping system that assesses and prioritizes avoidance areas by determining their impact on service coverage, allowing for targeted updates to restore access and improve routing efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If AVs avoid certain roads due to map inaccuracies or real-world changes, then routing reliability is improved, but service coverage area is reduced
Solution Approach 1:
The system proactively identifies avoidance areas by analyzing real-world changes before they significantly impact service coverage. By detecting changes such as new stop signs, speed bumps, or road conditions through sensor data from AVs and external sources, the system creates avoidance areas in advance, allowing for planned route adjustments rather than reactive service denials, thus maintaining reliability while minimizing coverage loss
Solution Approach 2:
The system dynamically adjusts routing parameters by computing alternative routes that circumvent avoidance areas while optimizing for service coverage. By changing route parameters such as preferred roads, travel time thresholds, and coverage priorities, the system can restore access to high-value service areas while maintaining avoidance of problematic regions, effectively balancing reliability and coverage area
2Reliability
If AVs avoid roads due to software limitations or training gaps, then operational safety is improved, but navigational versatility is reduced
Solution Approach 1:
The system enables AVs to self-identify navigational challenges through sensor data collection and automated avoidance area creation. When AVs encounter difficult-to-navigate intersections or road types, they autonomously flag these areas, contributing to fleet-wide knowledge. This self-service mechanism allows the system to progressively expand navigational versatility by identifying and addressing software limitations without requiring constant external intervention, while maintaining safety through automated avoidance
Solution Approach 2:
The system implements feedback loops where AVs report navigational difficulties and real-world changes back to the central system, which then updates avoidance areas and routing algorithms. This continuous feedback enables the fleet to collectively learn from encountered challenges, progressively improving navigational versatility while maintaining operational safety through data-driven route adjustments
3Reliability
If the system creates avoidance areas for all identified issues, then routing reliability is improved, but system complexity increases
Solution Approach 1:
The system applies local quality by creating avoidance areas with specific spatial and contextual characteristics rather than blanket restrictions. Each avoidance area is defined with precise geometric boundaries, associated reasons (e.g., new stop sign, construction), and priority levels. This localized approach allows the routing system to process only relevant avoidance information for each specific route planning scenario, maintaining reliability while managing complexity through targeted, context-aware avoidance area management
4Area of stationary object
If the system prioritizes restoring access to high-impact avoidance areas, then service coverage is improved, but data processing requirements increase
Solution Approach 1:
The system implements partial action by focusing computational resources on assessing and restoring only the most high-impact avoidance areas rather than processing all avoidance areas uniformly. By calculating service coverage impact metrics and prioritizing restoration based on thresholds and demand data, the system restores access to critical areas first, achieving significant coverage improvement with moderate data processing requirements, rather than exhaustively processing every avoidance area
Data Source
AI summary
A map database stores data describing a set of connected roads each having one or more lanes, each having one or more lanes. The map database further stores data describing at an avoidance area comprising an area in the map database that an autonomous vehicle (AV) avoids traversing. A routability system determines at least one lane that can be accessed by the AV if the AV traverses the avoidance area, and generates a restored coverage area corresponding to the at least one lane. The restored coverage area corresponds to an area of restored coverage provided by the AV traversing the avoidance area. The routability system computes a score based on the restored coverage area, the score indicating an impact of restoring access by the AV to the avoidance area.