Probe Vehicle Mapping with Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for mapping terrain and roads are inefficient and prone to errors, lacking accurate and real-time data collection and integration of road features, leading to outdated maps and potential safety hazards.
Innovation Solution
A system utilizing probe vehicles equipped with cameras, GPS, and inertial measurement units, transmitting images and data to a remote processor for map creation and updating, incorporating position and inertial information to identify road features and objects, enabling continuous and accurate mapping of road networks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional mapping methods are used, then map creation is simpler and less complex, but mapping accuracy and real-time updating capability deteriorate
Solution Approach 1:
The mapping system is segmented into multiple independent probe vehicles, each equipped with its own sensors and processing capabilities. Each vehicle independently collects and processes mapping data, with results aggregated by a central server. This segmentation allows the system to achieve high mapping accuracy through distributed multi-vehicle collaboration while managing complexity by making each unit self-sufficient rather than requiring one monolithic complex system.
Solution Approach 2:
The probe vehicles are designed with multi-functionality, serving both as navigation vehicles and as mobile mapping platforms. The same vehicle platform performs multiple functions: transportation, data collection via cameras and LIDAR, position determination via GPS, and inertial measurement. This universality reduces overall system complexity by eliminating dedicated mapping equipment while maintaining high mapping precision through integrated sensor fusion.
2Productivity
If manual mapping methods are used, then equipment requirements are simpler, but productivity and real-time updating capability deteriorate
Solution Approach 1:
The system implements continuous mapping operations through probe vehicles that constantly collect and transmit data during normal navigation. Rather than periodic manual surveys, the vehicles continuously capture images, LIDAR scans, and position data, enabling real-time map updates. This continuous action dramatically increases productivity by transforming mapping from an intermittent manual process to an ongoing automated operation, with the central server continuously processing incoming data streams.
Solution Approach 2:
The system incorporates feedback mechanisms where the central server processes mapping data from probe vehicles, updates the map database, and can request additional data collection from specific vehicles based on detected changes or areas requiring verification. This feedback loop enables automated quality control and continuous improvement of map accuracy, increasing productivity by eliminating manual review processes while managing complexity through algorithmic decision-making.
3Measurement precision
If probe vehicles with multiple sensors are deployed, then mapping accuracy and real-time capability improve, but energy consumption increases
Solution Approach 1:
The system merges multiple sensing functions (cameras, LIDAR, GPS, inertial sensors) into an integrated sensor suite on each probe vehicle. By combining these sensors and fusing their data at the vehicle level before transmission, the system achieves high road feature detection accuracy while reducing redundant data transmission. The sensor fusion algorithms integrate information from multiple sources to create a unified accurate representation of the environment, improving measurement precision while managing energy consumption through efficient data processing.
Solution Approach 2:
The system employs partial action by selectively activating and transmitting data from sensors based on operational needs. Rather than continuously transmitting all sensor data at full resolution, the system processes data locally and transmits only essential information or data indicating significant changes. This approach maintains high detection accuracy for critical road features while reducing overall energy consumption by minimizing data transmission bandwidth requirements.
Data Source
AI summary
Method and system for mapping terrain including one or more roads includes a vehicle equipped with at least one camera, a position determining system that determines its position and an inertial measurement unit (IMU) that provides at least one inertial property of the vehicle, all of which are in a set configuration relative to one another. A processor at a remote location apart from the vehicle converts images from the camera(s) to a map including objects from the images by identifying common objects in multiple images and using the position information and the inertial measurement information from when the multiple images were obtained and knowledge of the set configuration of the camera(s), the position determining system and the IMU. The images, position information and inertial measurement information are transmitted to the processor by a communications unit on the vehicle.