Autonomous Vehicle HD Mapping With Asynchronous Sensor Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous vehicle systems face challenges in generating and maintaining accurate, high-definition maps of their environment, which is crucial for safe and effective navigation.
Innovation Solution
The system obtains sensor data from various sources, including LiDAR and IMU sensors, and uses a method to generate a high-definition map by sorting data elements according to a structural data categorization. This map is updated based on the autonomous vehicle's motion trajectory, allowing for accurate localization and path planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensor data from multiple sources (LiDAR, IMU) is integrated to generate high-definition maps, then the accuracy and completeness of environmental representation is improved, but the system complexity and computational load increase
Solution Approach 1:
The system segments the complex mapping task into distinct functional modules: sensor data acquisition (LiDAR, IMU), trajectory determination, data element identification, and structural categorization. Each module handles a specific aspect of the mapping process, reducing overall system complexity while maintaining high mapping accuracy through coordinated operation of these specialized components.
Solution Approach 2:
The patent introduces an intermediary processing layer that receives raw sensor data and transforms it into structured mapping datasets. This intermediary system performs synchronization, filtering, and organization of multi-source sensor data before final map generation, thereby managing the complexity of integrating heterogeneous sensor inputs while preserving measurement precision.
2Manufacturing precision
If sensor data is captured at high frequencies to improve mapping detail, then the resolution and completeness of the map is improved, but the data processing time and computational resources increase
Solution Approach 1:
The system extracts and processes only the most relevant data elements from high-frequency sensor streams. By identifying and filtering key features (data elements representing points in the mapping dataset) from the overwhelming volume of raw sensor data, the system maintains high mapping resolution while reducing processing time through selective extraction of essential information.
Solution Approach 2:
The patent employs partial processing of sensor data by focusing computational resources on processing a subset of data points that contribute most significantly to map quality. Rather than processing every single data point from high-frequency sensors, the system selectively processes representative samples that capture the essential environmental features, thereby achieving high resolution with reduced computational burden.
3Reliability
If the high-definition map is continuously updated based on vehicle motion trajectory, then the map accuracy and localization precision are improved, but the computational overhead and energy consumption increase
Solution Approach 1:
The system implements periodic updates of the high-definition map based on vehicle trajectory milestones rather than continuous updates. Mapping updates are triggered at specific intervals or when the vehicle reaches predetermined locations, allowing the system to maintain accurate localization precision while reducing computational overhead and energy consumption by avoiding unnecessary continuous processing.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enables the creation of high-definition maps that provide accurate and complete representations of the environment, facilitating efficient and safe navigation for autonomous vehicles by improving localization and path planning.
Implementation Method 1
The first sensor type may be a Light Detection And Ranging (LiDAR) sensor type that is configured to capture the first sensor data at a frequency between 30 Hertz (Hz) and 100 Hz
Implementation Method 2
The second sensor type is an inertial measurement unit (IMU) sensor type that is configured to capture the second sensor data at a frequency between 5 Hz and 20 Hz
Data Source
AI summary
A method may include obtaining input information representative of an autonomous vehicle. The input information may include a plurality of data types. Each data type of the plurality of data types may be asynchronous. The method may also include aligning the input information to a point in time. In addition, the method may include determining odometry information indicating a state of the autonomous vehicle at the point in time based on the aligned input information. Further, the method may include sending the odometry information to a downstream system.