Single Active Sensor 3D Localization for Mobile Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles often require multiple expensive, large, and heavy sensor systems for 3D localization, which is impractical in certain applications.
Innovation Solution
A system utilizing a single active sensor, such as a camera, and an off-board or on-board computing system with a pre-created 3D map to determine the vehicle's pose and generate an updated travel path, allowing for autonomous navigation with reduced on-board sensing requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple sensor systems (radar, lidar, sonar, GPS, odometers, inertial measurement units) are used for 3D localization, then localization accuracy and reliability are improved, but system cost, size, and weight increase
Solution Approach 1:
The patent extracts the complex multi-sensor system and replaces it with a single active sensor (camera) combined with pre-acquired 3D map data. The localization function is extracted from the vehicle's on-board systems and performed off-board using the pre-stored environmental map, allowing the vehicle to determine its pose with minimal on-board sensing while maintaining accuracy through comparison of sensor inputs with the detailed pre-mapped environment
Solution Approach 2:
The patent applies preliminary action by acquiring and storing comprehensive 3D map data of the environment before the vehicle begins its journey. This pre-acquired environmental information includes detailed geometric and semantic data that is stored off-board, enabling the vehicle to perform accurate localization with minimal on-board sensors by comparing real-time sensor inputs against the pre-prepared environmental model
2Reliability
If multiple sensor systems are used for 3D localization, then navigation reliability is improved, but vehicle weight increases
Solution Approach 1:
The patent removes heavy sensor systems (radar, lidar, sonar, inertial measurement units) from the vehicle and replaces them with a single lightweight camera. The computational burden and associated hardware are extracted from the vehicle and placed off-board, where the processing system uses the vehicle's camera input combined with pre-stored 3D map data to determine accurate pose information, significantly reducing vehicle weight while maintaining navigation reliability
Solution Approach 2:
The patent uses a visual copy (camera images) instead of physical copies of the environment acquired by heavy sensors. The single camera captures visual information that is processed and compared against the pre-acquired 3D map, creating a lightweight sensing system that replicates the localization function of much heavier sensor systems without the associated weight penalty
3Measurement precision
If multiple sensor systems are used for 3D localization, then positioning precision is improved, but system cost increases
Solution Approach 1:
The patent uses a visual copy (camera) instead of expensive physical sensing systems. The camera captures images that are processed by an off-board system comparing them against pre-acquired 3D map data, providing accurate positioning information at a fraction of the cost of radar, lidar, or inertial measurement systems. The computational processing of visual data replaces expensive hardware while maintaining measurement precision
Solution Approach 2:
The patent replaces expensive, complex sensor systems with a single, inexpensive camera. The camera is a relatively low-cost device compared to radar, lidar, or inertial measurement units, and when combined with off-board processing and pre-stored 3D maps, it achieves accurate localization at significantly reduced system cost
Data Source
AI summary
A system configured to autonomously operate a vehicle within an environment is disclosed herein. The system includes a vehicle including a sensing system with a single active sensor configured to detect objects within an environment as the vehicle travels on a journey along a travel path within the environment. The system further includes a computing system communicably coupled to the vehicle. The computing system includes a memory configured to store a three-dimensional map of the environment, and a processor configured to determine an updated pose of the vehicle based on the three-dimensional map and input from the single active sensor of the vehicle. The processor is further configured to generate an updated travel path for the vehicle, wherein the updated travel path is generated based on the updated pose of the vehicle within the environment determined by the computing system.