Crowdsourced Object Mapping for Autonomous Vehicle Status Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous vehicle technologies lack effective methods to determine the operating status of vehicles in real-time, particularly in detecting objects around them during navigation, which can lead to potential safety issues if not properly addressed.
Innovation Solution
A system utilizing a crowdsourced object map stored in a cloud service compares data from a current vehicle's sensors with previously collected data from other vehicles that have traveled on the same route, allowing for real-time determination of the vehicle's operating status and triggering corrective actions if anomalies are detected.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If autonomous vehicles use sensors and AI algorithms to detect objects in real-time, then the vehicle's ability to identify objects and navigate is improved, but the system complexity and computational requirements increase
Solution Approach 1:
The patent combines multiple sensor inputs (cameras, radars, LIDAR) with crowdsourced map data and AI algorithms into an integrated system. The server merges object detection data from multiple vehicles to create a comprehensive crowdsourced map, while individual vehicles integrate sensor data with map information to improve detection accuracy and reduce computational burden on onboard systems.
Solution Approach 2:
The system pre-generates crowdsourced object maps containing location, type, and status information of objects along routes before vehicles need to traverse them. This preliminary action allows vehicles to have advance knowledge of objects and potential hazards, reducing the real-time detection burden and improving response time while maintaining high accuracy.
2Measurement precision
If the vehicle uses more sensors and advanced detection algorithms, then object detection capability is improved, but the energy consumption increases
Solution Approach 1:
The system uses partial action by leveraging pre-processed crowdsourced map data to supplement sensor detection. Vehicles don't need to detect and process all objects from scratch using energy-intensive sensors and algorithms; instead, they use sensor data to verify or update information already available in the crowdsourced map, reducing overall energy consumption while maintaining detection accuracy.
Solution Approach 2:
The system implements feedback loops where sensor detection results are compared against crowdsourced map data. When sensor detection confirms map information or provides updates, the system adjusts processing intensity accordingly. This feedback mechanism optimizes energy usage by avoiding redundant processing of well-known objects while maintaining high detection accuracy for novel or changed objects.
3Productivity
If the vehicle operates autonomously without human intervention, then productivity and efficiency are improved, but safety risks increase if detection fails
Solution Approach 1:
The crowdsourced object map serves as a safety cushion by providing pre-collected information about objects, hazards, and route conditions. This beforehand knowledge acts as a backup layer that compensates for potential sensor failures or detection errors, enhancing safety without requiring human intervention. The map data provides a safety net that cushions against detection failures.
Solution Approach 2:
The crowdsourced map system acts as an intermediary between the vehicle's sensors and the autonomous control system. Rather than relying solely on real-time sensor data or complex AI decisions, the intermediary map provides verified object information that mediates the detection process, improving reliability by filtering and validating data before it reaches the autonomous control system.
4Reliability
If real-time monitoring and comparison with crowdsourced data is implemented, then system health monitoring is improved, but communication and data processing requirements increase
Solution Approach 1:
The system extracts only the essential operating status information (detection failures, system health metrics) from vehicle sensor data for transmission to the server. Rather than transmitting all raw sensor data, the extraction process identifies and sends only critical information that needs comparison with crowdsourced maps, reducing data transmission load while maintaining monitoring accuracy.
Solution Approach 2:
The server performs preliminary filtering and matching of vehicle status reports against crowdsourced map data before full processing. This preliminary action identifies obvious mismatches or anomalies that can be quickly addressed, reducing the overall data processing load by handling routine comparisons efficiently and focusing intensive processing only on complex or ambiguous cases.
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.