Obscured Obstacle Detection via Measured Vehicle Trust Levels
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern automated vehicles face difficulties in detecting transient roadway hazards such as potholes and small debris, which can be obscured by traffic or lie outside the detection range of sensors, leading to potential collisions, especially in level 3 autonomous implementations without human oversight.
Innovation Solution
The system utilizes observations from trusted measured vehicles to predict obscured obstacles by analyzing their behaviors and movements, establishing a trust level for each vehicle based on reliability, and updates the vehicular environment map in real-time to guide the host vehicle in avoiding these hazards.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the host vehicle relies on its own sensors to detect obstacles, then it can directly perceive visible hazards, but it cannot detect obscured obstacles that are outside its detection range or blocked by traffic
Solution Approach 1:
The patent uses measured vehicles as intermediaries to detect obscured obstacles. These vehicles act as mediators by sensing hazards that the host vehicle cannot directly detect and transmitting this information to the host vehicle, thereby resolving the limitation of direct sensor detection for obscured obstacles
Solution Approach 2:
The system performs preliminary detection of obstacles by measured vehicles before the host vehicle encounters them. This advance detection allows the host vehicle to be warned of obscured hazards ahead of time, enabling proactive avoidance rather than reactive response
2Measurement precision
If the system collects data from multiple measured vehicles to predict obstacles, then it improves obstacle prediction accuracy, but it increases system complexity and data processing requirements
Solution Approach 1:
The patent applies a trust level threshold to filter measured vehicle data, using only data from vehicles that meet a minimum trust criterion. This partial acceptance approach balances prediction accuracy with system simplicity by avoiding the need to process and evaluate all possible data sources equally
Solution Approach 2:
The system changes the parameter of data quality assessment by introducing trust levels for different measured vehicles. This parameter transformation allows the system to weight and prioritize data from more reliable vehicles, improving prediction accuracy without requiring equally complex processing of all data sources
3Reliability
If the system uses trust levels to evaluate measured vehicles, then it improves the reliability of prediction data, but it requires additional evaluation mechanisms and increases processing overhead
Solution Approach 1:
The trust level of measured vehicles is evaluated and established in advance before their data is used for obstacle prediction. This preliminary evaluation mechanism allows the system to quickly filter and weight data based on pre-computed trust values, reducing real-time processing overhead while maintaining high reliability
Data Source
AI summary
The systems and methods described herein disclose detecting obstacles in a vehicular environment using host vehicle input and associated trust levels. As described here, measured vehicles, either manual or autonomous, that detect an obstacle in the environment will operate to respond to the obstacle. As such, those movements can be used to determine if an obstacle exists in the environment, even if the obstacle cannot be detected directly. The systems and methods can include a host vehicle receiving prediction data about an evasive behavior from one or more measured vehicles in a vehicular environment. A trust level can then be established for the measured vehicles. An obscured obstacle can be determined using the evasive behavior and the trust level which can then be mapped in the vehicular environment. A guidance input can then be created for the host vehicle using the obscured obstacle and the trust level.