Crowdsourced Object Mapping for Autonomous Vehicle Status Checks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous vehicle technologies lack systems to determine their operating status in real-time, particularly in detecting objects accurately during navigation, which can lead to unsafe conditions.
Innovation Solution
A system utilizing a crowdsourced object map stored in a cloud service compares data from a current vehicle with previously collected data from other vehicles to assess the operating status, enabling corrective actions and updates when discrepancies are detected.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If autonomous vehicles use sensors and AI algorithms to detect objects in real-time, then the vehicle can navigate autonomously, but the system may fail to detect certain objects leading to safety issues
Solution Approach 1:
The system implements feedback by continuously comparing real-time sensor detections with historical crowd-sourced detection data stored in a database. When a discrepancy is found (e.g., an object is detected by the vehicle's sensors but not by other vehicles in the crowd-sourced data), the system generates alerts and can terminate autonomous mode, providing closed-loop feedback to ensure detection reliability
Solution Approach 2:
The patent introduces crowd-sourced object detection data as an intermediary layer between the vehicle's own sensors and the final navigation decisions. This external data source acts as a mediator to validate or challenge the vehicle's sensor readings, improving overall detection reliability without requiring the vehicle to rely solely on its own sensors
2Reliability
If the vehicle terminates autonomous driving mode upon detecting a system health issue, then safety is improved, but productivity is reduced due to interruption of normal operation
Solution Approach 1:
The system applies partial action by implementing a hierarchical response to detected issues: rather than immediately terminating autonomous mode for all detected anomalies, the system first generates alerts and only terminates autonomous driving when specific critical conditions are met (e.g., multiple vehicles fail to detect the same object, or detection confidence falls below thresholds). This allows the system to maintain productivity for minor issues while ensuring safety for critical ones
Data Source
AI summary
A map in a cloud service stores physical objects previously detected by other vehicles that have previously traveled over the same road that a current vehicle is presently traveling on. New data received by the cloud service from the current vehicle regarding new objects that are being encountered by the current vehicle can be compared to the previous object data stored in the map. Based on this comparison, an operating status of the current vehicle is determined. In response to determining the status, an action such as terminating an autonomous navigation mode of the current vehicle is performed.