Autonomous Vehicle Parking Control With Multi-Sensor Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in accurately and autonomously navigating and parking themselves in designated or undesignated parking spots, as existing technologies rely heavily on GPS which is not precise enough for precise parking operations, and require human intervention to finalize the parking process.
Innovation Solution
The implementation of a system that uses a combination of GPS, cameras for lane and object detection, magnetic sensors for fiducial marker detection, and proximity sensors to determine trajectory information and control vehicle operations, allowing the autonomous vehicle to autonomously drive to and park within a designated area by sending signals to steering, throttle, and brake systems based on real-time sensor data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS is used for autonomous vehicle navigation and parking, then the vehicle can navigate to a destination, but the precision is not sufficient for accurate parking operations
Solution Approach 1:
The patent combines multiple sensing technologies (GPS, cameras, magnetic sensors, proximity sensors) into an integrated sensing system. This merging of different sensor types allows the system to overcome the limitations of GPS alone by adding layers of precision through visual recognition of lane markers, detection of magnetic fiducial markers, and measurement of distances to parking area boundaries, thereby achieving accurate parking positioning.
Solution Approach 2:
The patent segments the parking navigation process into multiple stages: coarse positioning using GPS, intermediate positioning using camera detection of lane markers and objects, and fine positioning using magnetic sensor detection of fiducial markers and proximity sensor measurement of distances to boundaries. Each stage provides progressively more precise location information, culminating in accurate parking placement.
2Measurement precision
If multiple sensor systems are integrated for precise parking control, then parking precision is improved, but system complexity increases
Solution Approach 1:
The patent implements a dynamic sensor activation strategy where different sensors are activated based on the vehicle's proximity to the parking area and the current stage of the parking process. GPS is used for long-range navigation, cameras are activated when approaching the parking area to detect lane markers and objects, magnetic sensors are activated when near the parking area to detect fiducial markers, and proximity sensors are activated during the final positioning phase. This dynamic approach reduces overall system complexity by not requiring all sensors to operate simultaneously.
Solution Approach 2:
The patent employs feedback mechanisms where sensor data is continuously processed to update the vehicle's position estimate and adjust the trajectory. The system uses feedback from camera detection of lane markers and objects to refine positioning, feedback from magnetic sensors detecting fiducial markers to confirm entry into the parking area, and feedback from proximity sensors measuring distances to boundaries for final positioning adjustments. This feedback loop enables the complex multi-sensor system to self-regulate and achieve precise parking control.
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
Enables autonomous vehicles to accurately and safely navigate and park in various parking scenarios, reducing the need for human intervention and improving parking precision by integrating multiple sensor data sources for precise control of vehicle movements.
Implementation Method 1
obtain, at a first time and from a magnetic sensor located underneath the autonomous vehicle, a first signal indicating a first distance from the magnetic sensor to a fiducial marker located on a perimeter of the parking area
Data Source
AI summary
The disclosed technology enables automated parking of an autonomous vehicle. An example method of performing automated parking for a vehicle comprises obtaining, from a plurality of global positioning system (GPS) devices located on or in an autonomous vehicle, a first set of location information that describes locations of multiple points on the autonomous vehicle, where the first set of location information are associated with a first position of the autonomous vehicle, determining, based on the first set of location information and a location of the parking area, a trajectory information that describes a trajectory for the autonomous vehicle to be driven from the first position of the autonomous vehicle to a parking area, and causing the autonomous vehicle to be driven along the trajectory to the parking area by causing operation of one or more devices located in the autonomous vehicle based on at least the trajectory information.