Autonomous Vehicle Pullover Scoring for Safer Curb Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in selecting optimal pullover locations for temporary parking, pickup, and drop-off, as existing systems lack comprehensive evaluation methods that consider various factors such as curb occupancy, traffic conditions, and passenger feedback, leading to unpredictable and inconvenient experiences.
Innovation Solution
A method that evaluates pullover locations by combining multiple inputs including curb occupancy, likelihood of unparking vehicles, road geometry, traffic conditions, legal restrictions, history of autonomous vehicle interactions, and passenger feedback to generate a pullover quality value (PQ value), which prioritizes safer and more convenient locations for selection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple factors are considered for pullover location evaluation, then the quality and reliability of pullover selection is improved, but the complexity of the evaluation system increases
Solution Approach 1:
The evaluation system is segmented into multiple independent input factors (curb occupancy, traffic conditions, road geometry, legal restrictions, etc.), each evaluated separately and then combined to determine the overall pullover quality value. This allows comprehensive evaluation while maintaining manageable complexity through modular assessment of each factor.
Solution Approach 2:
The processor performs multiple functions by receiving diverse inputs (sensor data, map data, historical data), evaluating different characteristics, and generating a comprehensive pullover quality value. This multi-functional approach consolidates various evaluation tasks into a single integrated system that assesses multiple aspects simultaneously.
2Measurement precision
If comprehensive inputs are collected for pullover evaluation, then the accuracy of pullover quality assessment is improved, but the time required for evaluation increases
Solution Approach 1:
The system collects and processes multiple inputs (curb occupancy, traffic conditions, road geometry, legal restrictions, historical data) simultaneously and combines them to determine the pullover quality value in advance, before the vehicle needs to execute the pullover maneuver. This preliminary comprehensive evaluation ensures accurate assessment without causing time delays during critical decision moments.
3Ease of operation
If pullover locations are selected based on multiple characteristics, then passenger convenience and safety are improved, but the difficulty of detecting and measuring suitable locations increases
Solution Approach 1:
The processor acts as an intermediary that receives diverse inputs from multiple sources (sensors, maps, historical data), evaluates them against multiple characteristics, and generates a simplified pullover quality value. This intermediary processing consolidates complex multi-characteristic evaluation into a single actionable metric that guides location selection while ensuring passenger convenience and safety.
Data Source
AI summary
Aspects of the disclosure relate to evaluating quality of a predetermined pullover location for an autonomous vehicle. For instance, a plurality of inputs for the predetermined pullover location may be received. The plurality of inputs may each include a value representative of a characteristic of the predetermined pullover location. The plurality of inputs may be combined to determine a pullover quality value for the predetermined pullover location. The pullover quality value may be provided to a vehicle in order to enable the vehicle to select a pullover location for the vehicle.