Autonomous Vehicle Blind Intersection Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automated driving systems face difficulties in detecting traffic conditions, especially in congested urban environments where buildings and other objects obstruct the view of vehicle sensors, leading to insufficient lead time for vehicle maneuvers.
Innovation Solution
An automated driving system that includes a perception system and a computing device capable of detecting and tracking objects within obstructed viewing regions using external imaging assist devices, such as reflective surfaces, to transmit images and enable timely vehicle maneuvers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous vehicle uses standard sensors to detect traffic conditions, then the system structure remains simple, but the detection capability is insufficient in obstructed viewing regions
Solution Approach 1:
The patent introduces an external imaging assist device as an intermediary to capture images of obstructed viewing regions. This device acts as a mediator between the blocked sensors and the areas that need to be monitored, allowing the system to detect objects in blind spots without requiring complex sensor arrays throughout the vehicle.
Solution Approach 2:
The patent utilizes reflective surfaces and imaging devices positioned at different spatial locations and orientations to capture views from alternative dimensions. By reflecting images from different angles and positions, the system gains detection capability in obstructed regions without adding sensors to every possible location.
2Loss of time
If the vehicle approaches a blind intersection, then the vehicle can maintain its speed, but the lead time for detecting hidden objects is insufficient
Solution Approach 1:
The system performs preliminary detection actions by continuously monitoring for imaging assist devices and capturing images of potential obstructed regions before the vehicle reaches blind intersections. This advance detection provides lead time for planning maneuvers without requiring the vehicle to slow down prematurely.
Solution Approach 2:
The system uses feedback from detected imaging assist devices to adjust detection strategies. When an imaging assist device is detected, the system increases monitoring of reflected images from that device, providing real-time feedback that enhances detection capability exactly when and where needed without affecting overall vehicle speed.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enhances the ability of autonomous vehicles to detect hidden objects in obstructed areas, providing sufficient time for safe navigation by analyzing images from assist devices and implementing appropriate vehicle maneuvers.
Implementation Method 1
The imaging assist device may include a reflective surface capable of transmitting an image of the obstructed viewing region to the perception system
Data Source
AI summary
An automated driving system for an autonomous vehicle may include a perception system and a computing device for detecting and tracking a location of an object within an obstructed viewing region blocked from view of sensors associated with the perception system. The computing device and perception system may identify an obstructed viewing region and detect an external imaging assist device located within a sensor field of the perception system. The imaging assist device is capable of transmitting images of the obstructed viewing region to the perception system. The computing device analyzes the images received from the imaging assist device for purposes of detecting an object within the obstructed viewing region and tracking its location relative to the autonomous vehicle. The computing device may transmit a command to an autonomous vehicle system to implement an autonomous vehicle maneuver based at least in part on the tracked location of the hidden object.