Autonomous Vehicle Route Viability Screening for Unsafe Road Segments
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in safely navigating certain road segments and conditions due to limitations in sensor capabilities and software processes, which can lead to degraded performance or failure in perceiving the environment, performing motion planning, and making decisions, especially under varying weather conditions and complex scenarios.
Innovation Solution
A route planning system that analyzes the performance of autonomous vehicles on road features, considering prior driving and simulation data, to determine which routes can be safely navigated by eliminating unsuitable road segments based on sensor and software capabilities, and providing a viability status assessment for road features and routes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous vehicle uses standard routing algorithms that assume human-driven vehicle capabilities, then the route planning process is simple and fast, but the vehicle cannot safely navigate certain road segments due to sensor and software limitations
Solution Approach 1:
The system performs preliminary analysis of road segment safety by evaluating sensor performance and software capabilities before route planning. Road segments are pre-assessed and categorized as safe or unsafe for autonomous navigation, allowing the routing algorithm to exclude unsafe segments without adding complexity to the core routing logic.
Solution Approach 2:
The route planning system is segmented into independent modules: a safety assessment module that evaluates individual road segments based on sensor and software capabilities, and a routing module that uses these assessments to plan routes. This segmentation allows each module to be optimized independently.
2Reliability
If the autonomous vehicle excludes road segments where performance may be degraded, then navigation safety is improved, but the number of available routes decreases
Solution Approach 1:
The system dynamically adjusts the set of available road segments based on current weather conditions, sensor performance, and software capabilities. Road segments are not permanently excluded but are conditionally included or excluded based on real-time assessments, allowing the system to maximize route options when conditions permit while maintaining safety when conditions are adverse.
Solution Approach 2:
The safety assessment of road segments is based on variable parameters such as weather conditions, sensor performance metrics, and software capability levels. By changing these parameters dynamically, the system can adjust which road segments are available without permanently limiting route options.
3Productivity
If the autonomous vehicle includes all road segments in route planning without performance assessment, then the routing algorithm is simple and provides more route options, but the vehicle may attempt to navigate unsafe road segments
Solution Approach 1:
The system performs preliminary safety assessments of road segments before they are considered by the routing algorithm. This pre-filtering removes unsafe segments from the candidate set, allowing the routing algorithm to operate efficiently on a reduced, pre-validated set of road segments without needing to evaluate safety during route planning.
Solution Approach 2:
A safety assessment layer acts as an intermediary between the road network data and the routing algorithm. This intermediary layer pre-evaluates road segments based on sensor and software capabilities, translating complex safety considerations into simple inclusion/exclusion criteria that the routing algorithm can efficiently process.
Data Source
AI summary
Among other things, a determination is made of and ability of an autonomous vehicle to safely or robustly travel a road feature or a road segment or a route that is being considered for the autonomous vehicle as of a time or range of times. The route conforms to properties of stored road network information. The road feature or road segment or route is eliminated from consideration if the computer has determined that the road feature or road segment or route cannot be safely or robustly traveled by the autonomous vehicle. The determination is based on analysis of performance of the autonomous vehicle.