Connected-Car Sensor Strategy for HD Map Change Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing high definition maps struggle to accurately detect changes in regions due to variations in lighting and weather conditions, leading to erroneous change detection and prolonged update intervals, which can diminish their efficacy in supporting vehicle operations.
Innovation Solution
A system that determines the existence of changes in a region by locating connected cars with sensors, determining a strategy to obtain data based on sensor location and type, and transmitting instructions to control sensor data collection, enabling accurate comparison with past maps and timely updates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional change detection methods are used in high definition maps, then map updates can be performed, but lighting and weather conditions cause erroneous detection and prolonged update intervals
Solution Approach 1:
The patent introduces connected cars as intermediary data collection nodes equipped with sensors (cameras, LIDAR, radar) to gather regional data. These cars act as mobile sensing platforms that transmit data to the server, enabling more reliable change detection that is independent of fixed camera conditions and less susceptible to lighting and weather variations.
Solution Approach 2:
The system employs multiple types of sensors (visual cameras, LIDAR, radar) on connected cars to detect changes through multiple modalities. This multi-functional approach allows the system to overcome limitations of any single sensor type under varying lighting and weather conditions, improving both detection accuracy and update frequency.
2Reliability
If more frequent map updates are performed, then real-time accuracy improves, but data collection resources and processing time increase
Solution Approach 1:
Connected cars that are already in operation and equipped with sensors for other purposes (autonomous driving, advanced driver assistance) contribute their sensing capabilities to map update operations. This self-service approach allows the system to collect data without dedicated survey vehicles, reducing resource requirements and enabling more frequent updates.
Solution Approach 2:
The system selectively triggers data collection based on detected change indicators rather than continuous monitoring. When potential changes are detected, the system requests targeted data collection from nearby connected cars, performing partial action only when necessary to maintain reliability without excessive resource consumption.
3Area of stationary object
If distributed sensor networks are deployed across multiple connected cars, then detection coverage improves, but system complexity and coordination requirements increase
Solution Approach 1:
The system divides the regional monitoring task into segments assigned to individual connected cars based on their locations. Each car is responsible for collecting data in its vicinity, and the server coordinates these segmented efforts by identifying which cars are near potential changes and requesting data only from them, reducing overall system complexity.
Solution Approach 2:
The system dynamically assigns data collection tasks to connected cars based on their real-time locations and the detected change indicators. Rather than static assignments, the coordination adapts to the moving targets (connected cars) and changing conditions, optimizing coverage while managing complexity through flexible, demand-driven task allocation.
Data Source
AI summary
A system for determining an existence of a change in a region can include a processor, a communications device, and a memory. The memory can store a change determination module and a communications module. The change determination module can cause the processor to: (1) determine, in response to having obtained an indication of a possible change in the region, a location of a connected car in a vicinity of the region and facts about a sensor disposed on the connected car and (2) determine a strategy to obtain data about the possible change. The strategy can be based on at least one of the location of the connected car or the facts about the sensor. The communications module can cause the processor to transmit, via the communications device and to the connected car, an instruction to control, according to the strategy, the sensor to obtain the data.