Autonomous Vehicle Deviation Detection and Alerting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating accurately and safely, particularly in situations where detailed maps are incorrect or when encountering unexpected traffic patterns or road conditions, leading to driver discomfort and reduced system effectiveness.
Innovation Solution
A method that utilizes sensors to detect objects and compare their characteristics to traffic pattern model and detailed map information, determining deviation values and providing notifications to drivers or autonomously maneuvering the vehicle to maintain safety, such as slowing down or changing lanes, when deviation values exceed threshold limits.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If the autonomous vehicle relies completely on the vehicle's autonomous computing system to maneuver, then the driver's sense of safety decreases, but the usefulness of the autonomous vehicle increases
Solution Approach 1:
The system continuously monitors traffic patterns and compares actual traffic flow against expected patterns stored in memory. When deviations are detected, the system provides feedback to the driver through notifications, allowing the driver to take control if needed. This feedback loop maintains driver confidence while preserving autonomous operation during normal conditions.
Solution Approach 2:
The system pre-stores expected traffic flow patterns and characteristics in memory before encountering actual traffic situations. This preliminary preparation allows the system to quickly compare actual traffic against expected patterns and detect anomalies, enabling proactive driver notification before unsafe conditions develop.
2Measurement precision
If the vehicle uses highly detailed maps for navigation, then the navigation accuracy improves, but the difficulty of detecting and measuring road condition deviations increases
Solution Approach 1:
The system segments traffic flow analysis into distinct characteristics (speed, density, flow rate) and compares each against corresponding expected patterns stored in memory. This segmentation allows the system to handle complex road condition variations by analyzing individual traffic parameters separately, making deviation detection more manageable despite using highly detailed navigation data.
Solution Approach 2:
The system uses stored expected traffic flow patterns as an intermediary reference layer between the detailed map data and actual sensor observations. This intermediary layer of expected patterns simplifies the comparison process by providing a baseline for what normal traffic should look like, reducing the complexity of detecting deviations from actual road conditions.
3Reliability
If the system provides continuous monitoring and notification to the driver, then the driver's sense of safety improves, but the usefulness of the autonomous vehicle decreases
Solution Approach 1:
The system applies partial monitoring by only notifying the driver when traffic patterns deviate from expected patterns stored in memory. During normal operating conditions, the system operates fully autonomously without driver intervention. This selective notification approach maintains driver safety awareness while preserving the effectiveness of autonomous driving for the majority of time when conditions are normal.
Data Source
AI summary
Aspects of the disclosure relate generally to determining whether an autonomous vehicle should be driven in an autonomous or semiautonomous mode (where steering, acceleration, and braking are controlled by the vehicle's computer). For example, a computer may maneuver a vehicle in an autonomous or a semiautonomous mode. The computer may continuously receive data from one or more sensors. This data may be processed to identify objects and the characteristics of the objects. The detected objects and their respective characteristics may be compared to a traffic pattern model and detailed map information. If the characteristics of the objects deviate from the traffic pattern model or detailed map information by more than some acceptable deviation threshold value, the computer may generate an alert to inform the driver of the need to take control of the vehicle or the computer may maneuver the vehicle in order to avoid any problems.