Annotated Virtual Tracks for Autonomous Obstacle Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles rely solely on self-detection of their surroundings, leading to potential false-positive obstacle detections and inefficient sensor data collection, as they lack real-time information about hazards and obstacles not included in conventional maps.
Innovation Solution
A system that captures and aggregates location and control information from lead vehicles to create annotated virtual track data, which is shared with trailing vehicles to enhance their navigation and sensor control, including identifying obstacles and optimizing sensor data collection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If autonomous vehicles rely solely on self-detection of surroundings using onboard sensors, then the vehicle can operate independently without external infrastructure, but this leads to false-positive obstacle detections and inefficient sensor data collection
Solution Approach 1:
The patent combines onboard sensor data with map data from a remote server to create a comprehensive view of the environment. The map data includes annotated information about hazards and obstacles detected by other vehicles, which is merged with local sensor detections to reduce false positives and improve overall detection accuracy.
Solution Approach 2:
The system pre-processes and stores hazard information in map data before the autonomous vehicle encounters potential obstacles. By having this information available in advance through map updates, the vehicle can prepare for known hazards rather than relying solely on real-time sensor detection, reducing false positives and improving response time.
2Productivity
If autonomous vehicles process large amounts of sensor data in real-time using only onboard sensors, then the vehicle maintains operational independence, but this increases computational load and may cause false-positive detections
Solution Approach 1:
The patent extracts and separates hazard information processing from the real-time onboard sensor processing. By obtaining pre-processed hazard information from map data received from a remote server, the vehicle reduces the computational burden on onboard processors while maintaining or improving detection accuracy through the combination of map data and real-time sensor data.
3Device complexity
If conventional maps are used for navigation, then the vehicle has a simplified representation for path planning, but the maps are infrequently updated and lack detailed hazard information
Solution Approach 1:
The patent transforms static conventional maps into dynamic map data that is frequently updated with real-time hazard information. The map data structure is enhanced to include annotated information about obstacles and hazards detected by other vehicles, allowing the navigation system to maintain simplicity while accessing current hazard information through periodic updates from a remote server.
4Ease of operation
If onboard sensors are used without guidance from known hazard locations, then the sensor system operates autonomously, but sensor data collection is inefficient and not optimized for areas with previous obstacles
Solution Approach 1:
The system uses map data containing information about known hazard locations to provide feedback guidance for sensor operation. This feedback mechanism allows the sensor controller to optimize data collection by focusing sensors on areas with known or suspected hazards, improving the efficiency of sensor data collection while maintaining autonomous operation through automated control based on map information.
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.