Autonomous Parking Control Using Sensor Fusion and Path Replay
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle vision systems lack the capability to autonomously park vehicles in complex environments, such as public parking structures, and fail to adapt to dynamic changes in parking scenarios, relying heavily on manual intervention and limited sensor data.
Innovation Solution
A vehicle parking system utilizing multiple exterior sensors, including cameras, ultrasonic sensors, and radar, with an embedded control unit and image processing capabilities to capture and analyze data, allowing for autonomous navigation, path learning, and dynamic adjustments to ensure safe and precise parking in various environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple exterior sensors (cameras, ultrasonic sensors, radar) are integrated for autonomous parking, then the system's ability to detect and adapt to dynamic parking environments is improved, but the device complexity increases
Solution Approach 1:
The system divides the complex sensing task into specialized segments: cameras for visual path learning and recognition, ultrasonic sensors for proximity detection, and radar for depth measurement. Each sensor type handles specific aspects of environment perception, allowing the system to manage complexity through functional segmentation while maintaining high adaptability to dynamic parking scenarios
Solution Approach 2:
The embedded control unit serves multiple functions: it processes data from all sensor types, performs path learning and recognition, executes autonomous parking control, and adapts to dynamic environmental changes. This multi-functional integration allows the system to achieve versatile adaptability without proportionally increasing overall system complexity
2Ease of operation
If the system learns and records parking paths for autonomous replay, then the ease of operation is improved, but the loss of time for path learning and recording increases
Solution Approach 1:
The system performs path learning and recording in advance during the driver's manual parking operation. The camera system continuously captures and stores visual information about the parking path, environment features, and vehicle trajectory. This preliminary action occurs during normal parking operations, so the actual autonomous parking execution requires no additional time investment from the user
Solution Approach 2:
The system creates a visual copy or map of the parking environment and path using camera data during the learning phase. This copied information is stored and later replayed during autonomous parking execution, allowing the system to replicate the learned path without requiring the driver to manually control the vehicle again, thus improving ease of operation while minimizing time loss
3Extent of automation
If the system provides both home parking and valet parking features with full autonomous control, then the extent of automation is improved, but the difficulty of detecting and measuring dynamic obstacles increases
Solution Approach 1:
The system merges data from multiple sensor types (cameras for visual detection, ultrasonic sensors for proximity, radar for depth) to create a comprehensive view of the parking environment. This sensor fusion approach enables the system to detect and measure dynamic obstacles with high accuracy, supporting full autonomous control for both home parking and valet parking features while managing the complexity of obstacle detection in dynamic environments
Data Source
AI summary
A vehicular parking system includes a plurality of exterior viewing cameras, at least one receiver and a control. The control, when the vehicle is located at an entrance of a parking structure, controls the vehicle to autonomously drive the vehicle from the entrance of the parking structure toward a parking location in the parking structure. The parking structure includes a positioning system having a plurality of short range communication devices at known locations at the parking structure. Responsive to communication signals generated by the devices, the control determines the location of the vehicle relative to the known locations and drives the vehicle from the entrance of the parking structure toward the parking location in the parking structure. With the vehicle positioned at the parking location, and responsive at least to image processing by the image processor of captured image data, the control parks the vehicle in the parking location.