AI Route Mapping for Predicting Drive-Assist Availability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current driving automation systems do not effectively provide users with real-time and historical data to inform route selection based on predicted autonomous driving levels, limiting the ability to optimize routes according to automation levels.
Innovation Solution
A system that collects real-time and historical data to train an inference engine, which predicts autonomous driving levels for road network segments, computes ratios of automation levels, and displays this information to users through a user interface, allowing for informed route selection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If traditional mapping applications only provide travel time optimization, then route selection is simple and fast, but users cannot make informed decisions about autonomous driving availability on different routes
Solution Approach 1:
The route is divided into multiple segments, and autonomous driving availability is predicted for each segment separately using an inference engine. This allows detailed information about automation availability on different portions of the route while maintaining overall system manageability.
Solution Approach 2:
The system pre-collects real-time and historical data, trains the inference engine in advance, and computes autonomous driving ratios before the user makes a routing decision. This preliminary processing enables informed route selection without adding complexity to the user interface.
2Measurement precision
If the system collects and processes real-time and historical data to predict autonomous driving levels, then route optimization accuracy improves, but data processing time and computational resources increase
Solution Approach 1:
The inference engine is trained offline using historical data before actual route predictions are needed. This preliminary training phase separates the computationally intensive model development from the real-time prediction phase, enabling fast predictions when users need routing information.
Solution Approach 2:
The system uses historical data from the same system to continuously improve its predictions. The inference engine learns from accumulated data and becomes more accurate over time without requiring additional external resources, optimizing the balance between prediction quality and processing efficiency.
Data Source
AI summary
Routes may be presented to a vehicle operator with information about predicted autonomous driving levels. A road network route to a destination is received. The road network route is partitioned into segments. Indicia of the segments are provided to an inference engine. The inference engine predicts levels of autonomous driving for the respective segments generated by the inference engine based on the indicia of the segments. Based on the predicted levels of autonomous driving for the respective segments, a ratio of a level of autonomous driving for the road network route is computed. The ratio corresponds to a proportion of time and/or distance for the road network route during which a driver-system is predicted to be engaged at the level of autonomous driving. A user interface is displayed, which includes a graphic representation of the road network route and a graphic indication of the ratio.