Annotated Virtual Tracks for Autonomous Obstacle-Aware Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles rely solely on self-detection of their surroundings, leading to processing large amounts of data in real-time, which can result in false-positive obstacle detections and inefficient sensor usage, as they are unaware of areas associated with previous obstacles.
Innovation Solution
The creation of an annotated virtual track system that captures and shares location and control information from lead vehicles to inform trailing vehicles, providing detailed road information and sensor control data to enhance obstacle detection and navigation, including areas not mapped conventionally.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If autonomous vehicles rely solely on self-detection of their surroundings, then they can operate independently without external infrastructure, but they must process large amounts of data in real-time which leads to false-positive obstacle detections and inefficient sensor usage
Solution Approach 1:
The system performs preliminary actions by having lead vehicles detect and map obstacles before trailing vehicles arrive. The annotated virtual track pre-identifies obstacle locations, allowing trailing vehicles to receive advance warning and adjust their sensor usage and navigation accordingly, rather than detecting obstacles in real-time
Solution Approach 2:
The patent introduces an intermediary system consisting of a service provider and annotated virtual track data that mediates between lead vehicles and trailing vehicles. This intermediary processes obstacle information centrally and delivers it to trailing vehicles, reducing the processing burden on individual vehicle sensors while improving detection reliability
2Productivity
If autonomous vehicles use onboard sensors to detect obstacles in real-time, then they can respond to current conditions, but they are subject to false-positive detections which cause undesirable actions
Solution Approach 1:
The system implements feedback by having lead vehicles detect obstacles and communicate this information back to trailing vehicles through the service provider. The annotated virtual track provides continuous feedback about obstacle locations, allowing trailing vehicles to adjust their sensor detection parameters and avoid false-positive detections while maintaining navigation efficiency
3Loss of information
If autonomous vehicles process large amounts of sensor data in real-time, then they can detect current obstacles, but they cannot optimize sensor usage for areas known to have previous obstacles
Solution Approach 1:
The system performs preliminary obstacle detection and mapping by lead vehicles, storing this information in annotated virtual track data. This preliminary action eliminates the need for trailing vehicles to re-detect known obstacles in real-time, reducing data processing time while maintaining complete obstacle information availability through the pre-mapped annotations
Data Source
AI summary
Recent location and control information received from “lead” vehicles that traveled over a segment of land, sea, or air is captured to inform, via aggregated data, subsequent “trailing” vehicles that travel over that same segment of land, sea, or air. The aggregated data may provide the trailing vehicles with annotated road information that identifies obstacles. In some embodiments, at least some sensor control data may be provided to the subsequent vehicles to assist those vehicles in identifying the obstacles and/or performing other tasks. Besides, obstacles, the location and control information may enable determining areas traveled by vehicles that are not included in conventional maps, as well as vehicle actions associated with particular locations, such as places where vehicles park or make other maneuvers.