LIDAR Odometry With Dynamic Surfel Maps for Pose Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in accurately localizing themselves within their environment due to occasional sensor input errors, especially over long operating lifetimes, which can affect the reliability and precision of their navigation and motion planning.
Innovation Solution
A LIDAR odometry system generates a real-time local environment map using LIDAR observations, aligning them with a local environment map to determine a transform between a vehicle frame and a keyframe, minimizing distances between LIDAR points and surfels to provide precise pose estimates, and updating the map as the vehicle traverses its environment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the autonomous vehicle uses traditional localization methods with stored map data, then the system is simpler to implement, but the accuracy and precision of pose estimates deteriorate because the map data may not represent the current state of the environment
Solution Approach 1:
The patent implements a dynamic localization system that continuously updates the environment map in real-time as the vehicle traverses the environment. The map transitions from a static stored representation to a dynamic structure that adapts to current environmental conditions, ensuring pose estimates reflect the most up-to-date environmental state while maintaining computational efficiency
Solution Approach 2:
The system incorporates feedback mechanisms where LIDAR observations are continuously compared with the environment map, and the map is updated based on the discrepancies and new observations. This feedback loop ensures that the localization system corrects for sensor errors and maintains high precision pose estimates by constantly refining the environmental representation
2Duration of action of moving object
If the autonomous vehicle operates over a high-mileage operating lifetime, then the vehicle can cover more distance and perform more tasks, but sensor input errors accumulate and localization accuracy deteriorates
Solution Approach 1:
The system performs preliminary actions by establishing a local environment map at the start of each operational session and continuously maintaining it. This preliminary map structure is then used as a reference framework throughout the operation, allowing the system to detect and correct drift accumulation over time by referring back to the established map and updating it with new observations
Solution Approach 2:
The system implements continuous feedback mechanisms where LIDAR observations are constantly compared with the environment map, and the map is updated based on the discrepancies and new observations. This feedback loop ensures that the localization system corrects for sensor errors and maintains high precision pose estimates by constantly refining the environmental representation
3Measurement precision
If the system uses real-time LIDAR observations to update the environment map, then the accuracy of pose estimates improves, but the computational processing time and latency increase
Solution Approach 1:
The patent segments the environment into local keyframes and surfels, creating a modular representation that can be efficiently processed. The environment map is divided into manageable local maps oriented with respect to keyframes, allowing the system to process only relevant portions of the environment at any given time, thereby reducing computational latency while maintaining precision
Solution Approach 2:
The system applies local quality by maintaining detailed surfel representations only in the immediate vicinity of the vehicle, while coarser representations are used for distant areas. The local environment map focuses computational resources on the most relevant nearby environment, improving processing efficiency while maintaining high precision for the critical localization task
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 enhances the accuracy and precision of autonomous vehicle localization, improving navigation and motion planning by ensuring that pose estimates reflect the current state of the environment, thereby increasing computational confidence and reducing latency.
Implementation Method 1
LIDAR odometry system can generate, in real-time, a local environment map of a vehicle's environment generated from recent LIDAR observations
Implementation Method 2
The LIDAR odometry system can control for (e.g., minimize) the total or average distance between the LIDAR points and corresponding surfels to determine a transform between the vehicle frame and the keyframe of the local environment map
Data Source
AI summary
A localization system can obtain a LIDAR observation oriented relative to a vehicle frame, the vehicle frame oriented with respect to a pose of a vehicle; access a local environment map descriptive of the environment of the vehicle, wherein the local environment map is oriented relative to a keyframe at a given time, the local environment map including a plurality of surfels and generated in real-time during a current operational instance of the vehicle based on one or more prior LIDAR observations captured during the current operational instance of the vehicle; determine a transform between the vehicle frame and the keyframe by aligning the LIDAR observation to the local environment map based on a similarity between the LIDAR observation and the local environment map; and determine an updated pose of the vehicle based on the transform and the pose of the vehicle in the vehicle frame at the given.