Autonomous Vehicle Routing Using Human Takeover Risk Scores
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional autonomous vehicle routing systems primarily focus on minimizing travel time and distance, neglecting the risk of human operator takeover, which can lead to suboptimal routes in scenarios where avoiding challenging driving conditions is crucial.
Innovation Solution
A computer-implemented model that generates a score indicative of the likelihood of autonomous vehicle takeover based on predefined maneuvers, allowing the system to identify and select routes that balance travel efficiency with the risk of human intervention, using labeled data and machine learning algorithms to predict transitions from autonomous to human-operated modes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If routing is based solely on travel time and distance minimization, then operational efficiency is improved, but safety and operational reliability deteriorate due to increased risk of autonomous vehicle takeover
Solution Approach 1:
The routing system changes the parameters considered for route selection by incorporating takeover risk scores alongside travel time and distance. The computer-implemented model generates risk scores for different maneuvers and routes, allowing the system to evaluate and select routes based on multiple parameters including safety considerations, thereby resolving the contradiction between operational efficiency and safety.
2Reliability
If routing avoids challenging driving scenarios to reduce takeover risk, then safety is improved, but travel time and distance increase
Solution Approach 1:
The system dynamically adjusts routing decisions by evaluating takeover risk scores for different maneuvers and routes in real-time. Rather than statically avoiding all challenging scenarios, the system uses the computer-implemented model to assess risk levels and make dynamic routing choices that balance safety with travel efficiency, selecting routes that minimize takeover risk while maintaining reasonable travel times.
3Reliability
If the system incorporates takeover risk assessment into routing decisions, then operational reliability is improved, but system complexity increases
Solution Approach 1:
The patent introduces a computer-implemented model as an intermediary component that generates takeover risk scores for different maneuvers and routes. This model acts as a mediator between the routing system and the autonomous vehicle control system, providing quantitative risk assessments that simplify the decision-making process. By using this intermediary model, the system incorporates safety considerations without requiring complex integration across all system components.
Data Source
AI summary
Various technologies described herein pertain to routing an autonomous vehicle based upon risk of takeover of the autonomous vehicle by a human operator. A computing system receives an origin location and a destination location of the autonomous vehicle. The computing system identifies a route for the autonomous vehicle to follow from the origin location to the destination location based upon output of a computer-implemented model. The computer-implemented model is generated based upon labeled data indicative of instances in which autonomous vehicles are observed to transition from operating autonomously to operating based upon conduction by human operators while the autonomous vehicles are executing predefined maneuvers. The computer-implemented model takes, as input, an indication of a maneuver in the predefined maneuvers that is performed by the autonomous vehicle when the autonomous vehicle follows a candidate route. The autonomous vehicle then follows the route from the origin location to the destination location.