Autonomous Vehicle Route Viability Assessment for Hazardous Road Segments
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in safely navigating certain road segments and geographic regions due to limitations in sensor capabilities and software processes, which can degrade under specific environmental conditions or times, leading to unsafe or unreliable route planning.
Innovation Solution
A viability assessment system determines the safety and robustness of routes for autonomous vehicles by evaluating sensor and software performance characteristics, road features, and environmental conditions, allowing for the exclusion of non-navigable road segments and the identification of validated autonomous driving routes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If routing algorithms determine routes based on road network information without considering sensor and software performance, then route planning is simple and fast, but the autonomous vehicle cannot safely navigate certain road segments under specific environmental conditions
Solution Approach 1:
The patent segments the route planning process into multiple independent modules: a routing algorithm that generates candidate routes based on road network information, and a viability assessment system that evaluates sensor and software performance for each road segment. This segmentation allows each module to specialize in specific tasks, improving overall reliability without overwhelming complexity.
Solution Approach 2:
The patent implements preliminary action by pre-assessing the viability of road segments before the autonomous vehicle encounters them. The system evaluates sensor performance characteristics and software process performance for each road segment in advance, storing this viability information for rapid route planning decisions. This preliminary assessment ensures safety-critical evaluations are completed before navigation decisions are made.
2Reliability
If the autonomous vehicle avoids road segments with poor sensor or software performance, then navigation safety is improved, but the number of available routes decreases
Solution Approach 1:
The patent applies dynamics by making route viability assessment conditional on environmental factors and vehicle operating conditions. The system dynamically evaluates whether road segments are navigable based on current sensor performance characteristics, software process performance, and environmental conditions. This dynamic assessment allows the vehicle to adapt to changing conditions while maintaining safety, rather than permanently excluding road segments.
Solution Approach 2:
The patent changes parameters by introducing viability thresholds for sensor and software performance. Instead of binary inclusion/exclusion of road segments, the system evaluates continuous performance parameters and compares them against safety thresholds. This parameter-based approach allows flexible route planning that maintains safety while maximizing the number of available routes when performance criteria are met.
3Measurement precision
If the system evaluates sensor and software performance for each road segment, then route viability assessment is accurate, but the computational time and resources increase
Solution Approach 1:
The patent implements preliminary action by pre-evaluating and storing viability information for road segments before they are needed for route planning. The system assesses sensor performance characteristics and software process performance in advance, creating a database of pre-computed viability data. When route planning is needed, the system rapidly queries this pre-computed data rather than performing full evaluations in real-time, significantly reducing computational time.
Solution Approach 2:
The patent uses copying by creating and storing simplified representations of road segment viability characteristics. Instead of re-evaluating complex sensor and software performance parameters for each route planning query, the system creates copies of pre-assessed viability information that can be rapidly retrieved and used for multiple route planning decisions. This copying approach maintains measurement precision while reducing computational overhead.
Data Source
AI summary
Among other things, a viability of a route is determined. The route includes a sequence of connected road segments to be traveled by an autonomous vehicle from a starting position to a goal position. The route conforms to stored road network information.