Dual Road Surface Cameras for Autonomous Vehicle Self-Location
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing self-location estimation methods for autonomous vehicles, such as SLAM and RTK-GNSS, face accuracy issues in environments with limited features or obstructed satellite views, and are further compromised by varying sunlight conditions or road surface coverages like sand, leading to reduced location estimation accuracy.
Innovation Solution
The implementation of dual road surface image obtaining devices, such as cameras, on an autonomous vehicle, which alternately capture images of the road surface and compare them with stored map images to estimate self-location, ensuring continued accuracy even under adverse conditions by utilizing redundant data from multiple sources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single road surface image obtaining device is used for self-location estimation, then the device complexity is reduced, but the measurement precision of self-location is reduced when sunshine conditions vary or road surface is partially covered with sand
Solution Approach 1:
The system divides the image acquisition function into multiple independent devices (first and second road surface image obtaining devices) positioned at different locations on the vehicle. Each device captures images independently, and the system segments the operation into alternating phases where different devices take turns acquiring images based on timing signals, ensuring continuous accurate self-location estimation even when one device's view is obscured.
Solution Approach 2:
Different image obtaining devices are positioned at different local positions on the vehicle body to capture images from different perspectives. This local differentiation allows the system to select images with better quality features depending on local conditions such as sunlight angle and road surface coverage, thereby maintaining high measurement precision across varying environmental conditions.
2Reliability
If multiple road surface image obtaining devices are used to maintain accuracy under adverse conditions, then the measurement precision is improved, but the device complexity increases
Solution Approach 1:
The system implements periodic action by alternating the operation of multiple image obtaining devices in time-phased intervals. A timing signal controller coordinates the devices to operate sequentially rather than simultaneously, with each device activated at specific time periods. This periodic operation maintains reliable self-location estimation while reducing the instantaneous processing load and system complexity compared to continuous multi-device operation.
Solution Approach 2:
The system uses multiple image obtaining devices as redundant copies of the same functional unit. Each device is a copy capable of performing the same image acquisition and self-location estimation function. This copying approach enhances reliability through redundancy while managing complexity by using identical, standardized device configurations that can be controlled through a unified timing signal system.
3Productivity
If images are captured continuously by multiple devices, then the productivity of self-location estimation is improved, but the use of energy increases
Solution Approach 1:
The timing signal controller implements periodic action by activating image obtaining devices at specific time intervals rather than continuously. Each device operates in alternating phases, capturing images only when its timing signal is active. This periodic operation maintains high productivity by ensuring frequent image acquisition for accurate self-location estimation while significantly reducing energy consumption compared to continuous operation of all devices.
Solution Approach 2:
The system performs preliminary action by pre-coordinating the operation schedule of multiple image obtaining devices through timing signals. The controller预先 determines which device should capture images at each time period, optimizing the allocation of imaging tasks before execution. This preliminary coordination enables efficient use of energy by ensuring that only necessary devices operate at necessary times, while maintaining high estimation output frequency through advance planning of the imaging sequence.
Data Source
AI summary
An autonomous vehicle includes first and second road surface image obtaining devices that are located on a bottom surface of the vehicle body and obtain images of a road surface below the vehicle body, respectively. The autonomous vehicle also includes a memory unit that stores a map image of the road surface, the map image being associated with geographical location information. The autonomous vehicle further includes first and second self-location estimating units that each compare a feature extracted from the image of the road surface obtained by corresponding one of the first and second road surface image obtaining devices with a feature extracted from the map image, thereby estimating a self-location of the autonomous vehicle.