Risk Routing for Human Drivers in Autonomous Fleets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The widespread adoption of autonomous vehicles on public roads is hindered by the need for extensive real-world testing and a convincing safety record, as well as limitations in monetizing autonomy features, which require proven safety and efficient risk assessment across varying conditions.
Innovation Solution
An on-demand transportation management system that utilizes risk regression and trip classification techniques to dynamically assess and manage risk, allowing for the deployment of autonomous vehicles by selecting the most optimal vehicle type (human-driven, safety-driven autonomous, or fully autonomous) based on route-specific risk analysis and software verification, ensuring safety and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If autonomous vehicles are deployed extensively on public roads, then productivity and transportation efficiency are improved, but safety risks and harmful factors increase due to the need for extensive real-world testing
Solution Approach 1:
The system performs preliminary risk assessment and route classification before autonomous vehicle deployment. By pre-evaluating road segments and categorizing them by risk level, the system prepares safety protocols in advance, allowing extensive deployment without proportionally increasing safety risks.
Solution Approach 2:
The patent introduces a centralized server as an intermediary that coordinates between autonomous vehicles, road conditions, and safety protocols. This mediator processes route information, classifies risks, and manages vehicle assignments, thereby decoupling the direct relationship between deployment scale and safety risks.
2Reliability
If risk assessment and vehicle selection processes are made more comprehensive, then safety is improved, but device complexity and operational time increase
Solution Approach 1:
The risk assessment system divides the road network into discrete path segments and classifies each segment by risk level. This segmentation allows comprehensive safety evaluation without requiring complex holistic analysis, as each segment can be independently assessed and managed.
Solution Approach 2:
The system transforms qualitative safety assessments into quantitative risk scores and classifications. By converting complex safety evaluations into measurable parameters (risk levels, route categories), the system maintains comprehensive safety analysis while reducing operational complexity through standardized metrics.
3Reliability
If dynamic risk assessment and route optimization are implemented, then safety and efficiency are improved, but loss of time for data processing and decision-making increases
Solution Approach 1:
The system pre-calculates and stores risk assessments for various road segments before vehicles need them. By performing risk evaluations in advance and caching route classifications, the system reduces real-time processing requirements, maintaining safety without excessive time loss during actual vehicle operations.
4Adaptability or versatility
If autonomous vehicle operations are expanded to diverse conditions, then adaptability and productivity are improved, but reliability decreases due to varying and untested conditions
Solution Approach 1:
The patent segments the operational environment into classified route categories based on risk levels and conditions. This allows the system to manage diverse operating conditions systematically, matching vehicles to appropriate route types based on their verification status, thereby maintaining reliability across varied conditions.
Solution Approach 2:
The system dynamically adjusts vehicle assignments and route classifications based on current conditions, vehicle performance data, and accumulated experience. This dynamic adaptation allows expansion into diverse conditions while maintaining reliability through continuous optimization and learning from operational data.
Data Source
AI summary
An on-demand transportation management system can collect historical data of harmful events of human-driven vehicles (HDVs) operating throughout a given region. For each road segment of the given region, the system can determine a fractional risk value for the HDVs, and based on the fractional risk value for each road segment, the system can route drivers within the given region along lowest risk route options.