Autonomous Vehicle Routing Using Stranding Risk Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in routing due to factors like likelihood of becoming stranded, disengagement, lane changes, and unprotected turns, which existing routing systems do not adequately address.
Innovation Solution
A method and system that use models trained with log data to assess the likelihood of these events, determining costs for each route based on time of day, map information, and route details, and selecting routes to minimize these risks, thereby controlling the vehicle in autonomous mode effectively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If typical routing approaches are used (shortest distance or shortest time), then routing efficiency is improved, but the vehicle may become stranded or require disengagement from autonomous mode
Solution Approach 1:
The patent uses multiple pre-computed routes as disposable alternatives. Instead of relying on a single optimal route that may fail, the system generates multiple candidate routes and can switch between them when problems arise, treating each route as a temporary, replaceable option rather than a permanent solution
Solution Approach 2:
The system performs preliminary assessment of potential routes before the vehicle actually travels them. By evaluating routes in advance for potential stranding risks and disengagement probabilities, the system can select routes that have been pre-validated for autonomous vehicle compatibility, preventing problems before they occur
2Reliability
If routing avoids specific locations (highways, toll roads), then certain risks are reduced, but routing flexibility and options are limited
Solution Approach 1:
The routing system dynamically adjusts route preferences based on real-time conditions and vehicle state. Rather than statically avoiding certain location types, the system can adaptively select from diverse route options depending on current traffic, weather, and autonomous driving conditions, allowing flexibility while maintaining risk management
Solution Approach 2:
The system changes routing parameters (such as route cost weights, risk thresholds, and preference settings) based on vehicle performance data and environmental conditions. This allows the same routing infrastructure to serve different risk profiles and operational contexts without being locked into fixed avoidance rules
3Productivity
If the vehicle operates in autonomous mode on complex routes, then routing efficiency is improved, but the likelihood of disengagement and manual intervention increases
Solution Approach 1:
The system incorporates feedback loops where vehicle performance data, disengagement events, and operational outcomes are continuously monitored and used to refine routing decisions. This feedback mechanism allows the system to learn from past experiences and adjust future route selections to maintain higher autonomous operation stability
Solution Approach 2:
The system prepares contingency plans and alternative routes in advance to cushion against potential autonomous operation failures. By having pre-planned fallback options ready, the system can maintain autonomous mode stability even when encountering complex or challenging driving scenarios
Data Source
AI summary
Aspects of the disclosure provide for the selection of a route for a vehicle having an autonomous driving mode. For instance, an initial location of the vehicle may be identified. This location may be used to determine a set of possible routes to a destination location. A cost for each route of the plurality is determined by inputting time of day information, map information, and details of that route into one or more models in order to determine whether the vehicle is likely to be stranded along that route and assessing the cost based at least in part on the determination of whether the vehicle is likely to be stranded along that route. One of the routes of the set of possible routes may be selected based on any determined costs. The vehicle may be controlled in the autonomous driving mode using the selected one.