LiDAR Scan Encoding With Mixed Compression for HD Map Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional maps for autonomous vehicles lack the precision and timeliness required for safe navigation due to limitations in sensor data accuracy and the expense and inefficiency of traditional mapping methods, which struggle to keep up with frequent road updates.
Innovation Solution
The method involves encoding and compressing sensor data, particularly LiDAR data, to generate high-definition maps with sub-2 cm resolution, allowing autonomous vehicles to accurately navigate by representing data as image representations and applying lossless or lossy compression based on error tolerability, enabling efficient storage and transmission.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional maps are created using survey teams with high resolution sensors, then measurement precision is improved, but productivity deteriorates due to the expensive and time-consuming process taking months to complete
Solution Approach 1:
Autonomous vehicles serve themselves by collecting and contributing sensor data to the map system while navigating, eliminating the need for dedicated survey teams. The vehicles' own sensors capture environmental data during normal operation, which is then processed and added to the HD map database, enabling continuous map updates without external intervention
Solution Approach 2:
The map creation and update process operates continuously as autonomous vehicles navigate through environments. Instead of periodic survey campaigns, the system accumulates sensor data continuously from multiple vehicles, enabling real-time map maintenance that keeps pace with frequent road updates of 5-10% per year
2Ease of operation
If GPS systems are used for location determination, then ease of operation is improved, but measurement precision deteriorates with accuracies of approximately 3-5 meters and large error conditions
Solution Approach 1:
The system merges GPS data with HD map data and sensor data to create a multi-source localization system. GPS provides coarse location, while HD map features and sensor measurements refine the position estimate to centimeter-level accuracy, combining the ease of GPS operation with high precision requirements
Solution Approach 2:
The HD map serves as an intermediary between GPS and the vehicle's actual position. GPS provides satellite-based coordinates, the HD map provides detailed environmental context and feature locations, and the system uses this intermediary layer to translate coarse GPS data into precise vehicle positioning relative to road features
3Measurement precision
If LiDAR sensor data is collected at high resolution, then measurement precision is improved, but loss of substance increases due to the large amount of data requiring storage and transmission
Solution Approach 1:
The system extracts only the essential and relevant features from the complete LiDAR point cloud data. Instead of storing all raw sensor measurements, it identifies and extracts key environmental features such as road boundaries, obstacles, and landmarks that are critical for navigation, discarding redundant information while maintaining navigation accuracy
Solution Approach 2:
The LiDAR data processing is segmented into multiple stages: raw data collection, feature identification, selective extraction, and compressed storage. This segmentation allows the system to process high-resolution data temporarily for accurate mapping while storing only the essential extracted features, reducing overall storage requirements
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 achieves significantly improved compression ratios with minimal error, providing autonomous vehicles with precise, up-to-date maps that enhance navigation accuracy and reduce storage and transmission requirements.
Implementation Method 1
sensor data gathered by autonomous vehicles, such that the encoded sensor data can be transmitted between vehicles and an online system (e.g., the cloud) that generates HD map. Here, sensor data gathered by autonomous vehicles can be three dimensional data gathered by light detection and ranging (LiDAR) methods.
Data Source
AI summary
Embodiments relate to methods for efficiently encoding sensor data captured by an autonomous vehicle and building a high definition map using the encoded sensor data. The sensor data can be LiDAR data which is expressed as multiple image representations. Image representations that include important LiDAR data undergo a lossless compression while image representations that include LiDAR data that is more error-tolerant undergo a lossy compression. Therefore, the compressed sensor data can be transmitted to an online system for building a high definition map. When building a high definition map, entities, such as road signs and road lines, are constructed such that when encoded and compressed, the high definition map consumes less storage space. The positions of entities are expressed in relation to a reference centerline in the high definition map. Therefore, each position of an entity can be expressed in fewer numerical digits in comparison to conventional methods.