External Display Detection for Autonomous Vehicle Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous and semi-autonomous vehicles face challenges in navigating through environments obscured by large vehicles with external displays, as they may misinterpret information from these displays, leading to potential collisions due to difficulty in distinguishing between the physical presence of the display and the information projected within it.
Innovation Solution
A detection system equipped with cameras and LIDAR sensors that analyze images and depth information to identify external displays, track objects within them, and determine their state, including trajectory estimates, to generate appropriate driving maneuver recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous vehicle uses sensors to detect objects in the environment, then it can navigate and avoid obstacles, but it cannot detect objects obscured by large vehicles with external displays
Solution Approach 1:
The system uses the external display as an intermediary information source. Instead of directly detecting obscured objects with sensors, the system detects the display itself and extracts object information from the displayed content, allowing indirect perception of objects that would otherwise be completely hidden from sensor view
Solution Approach 2:
The system creates a virtual copy of the obscured environment by analyzing the external display content. The display shows a representation of the scene on the other side of the large vehicle, and the system processes this visual copy to detect and track objects, effectively replicating the function of direct sensor detection without the physical line-of-sight requirement
2Loss of information
If the autonomous vehicle interprets information from external displays, then it can see through obstructing vehicles, but it may misinterpret the display information leading to potential collisions
Solution Approach 1:
The system segments the detection task into distinct stages: first detecting the external display as a separate object, then analyzing the content within the display boundary, and finally extracting object information from that content. This segmentation allows the system to distinguish between the physical display structure and the informational content it presents, reducing misinterpretation risks
Solution Approach 2:
The system introduces an intermediary processing layer that analyzes the relationship between the display frame and its content. By detecting the display boundaries first and using them as a reference frame, the system can accurately interpret objects within the display while accounting for the display's physical position and orientation, preventing confusion between the display itself and projected information
3Measurement precision
If the vehicle tracks objects within external displays, then it can determine object states and trajectories, but it increases system complexity
Solution Approach 1:
The system uses the same detection and tracking modules for both direct sensor detection and external display analysis. The detection module identifies objects in both real sensor data and display-captured images, while the tracking module follows object trajectories in both cases. This multi-functionality allows the system to handle display-based information without requiring entirely separate specialized subsystems, managing complexity through code reuse and unified processing pipelines
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
The system improves vehicle safety by accurately interpreting information from external displays, enabling safe navigation through obstructed areas and preventing potential collisions by distinguishing between the physical display and projected information.
Implementation Method 1
a camera to capture images of a scene within the environment
Implementation Method 2
A detection system equipped with cameras and LIDAR sensors that analyze images and depth information
Data Source
AI summary
System, methods, and other embodiments described herein relate to selecting a route for a vehicle to travel. In one embodiment, the detection system generates a driving maneuver recommendation for a vehicle having a plurality of sensors configured to acquire information about an environment around the vehicle, the sensors including at least a camera to capture one or more images of a scene within the environment, by determining that at least a portion of each image in a set of images captured by the camera indicates an external display in the environment, tracking an object within the portion of each image in the set of images to determine a state of the object, the state including at least a trajectory estimate for the object, and determining a recommended driving maneuver based at least in part on the determined state of the object.