Automated Parking Path Planning Using Segmented Optimal Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current parking assist systems for vehicles lack the ability to efficiently determine and navigate a feasible path to a target parking space, especially in complex environments with obstacles and varying parking slot configurations, often requiring high computational resources and struggling with non-holonomic vehicle characteristics.
Innovation Solution
A parking assist system utilizing multiple cameras and sensors to capture data, process images, and determine a path of travel by defining nodes and using optimal control algorithms to plan and optimize the vehicle's path, considering obstacles, steering capabilities, and vehicle maneuverability, while also allowing for geometric path construction to reduce computational complexity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If optimal control algorithms are used to determine the path of travel, then the path planning accuracy and vehicle maneuverability are improved, but the computational resources and processing time are increased
Solution Approach 1:
The path planning process is divided into discrete segments defined by nodes representing specific vehicle states (position, orientation). The continuous path determination is segmented into discrete optimal control calculations between nodes, reducing computational complexity while maintaining accuracy.
Solution Approach 2:
The system pre-calculates and stores optimal control parameters for common parking scenarios and vehicle states. When executing a parking maneuver, the system retrieves and applies pre-determined control strategies rather than calculating everything from scratch, reducing real-time computational burden.
2Measurement precision
If multiple sensors and cameras are used to capture environmental data, then the detection accuracy and obstacle identification are improved, but the device complexity and data processing requirements are increased
Solution Approach 1:
Data from multiple sensors (cameras, ultrasonic sensors, other detection devices) are merged and integrated into a unified environmental model. The sensor processing system combines inputs from all sensors to create a comprehensive view of the parking environment, reducing the need for each individual sensor to operate independently at full complexity.
Solution Approach 2:
The sensor processing system is designed to handle multiple sensor types and multiple functions (obstacle detection, path planning, vehicle state monitoring) through a single integrated processing architecture. This multi-functional approach reduces overall system complexity compared to having separate dedicated processing units for each sensor and function.
3Productivity
If the path is broken down into nodes and segments, then the computational complexity is reduced and processing efficiency is improved, but the path smoothness and driving comfort may be degraded
Solution Approach 1:
The system applies curvature smoothing to the segmented path nodes, transforming sharp angular transitions into smooth curved trajectories. The optimal control algorithm incorporates continuity constraints that ensure smooth transitions between path segments, maintaining driving comfort while preserving the computational efficiency of the segmented approach.
Solution Approach 2:
The path representation is made dynamic by allowing continuous adjustment of node positions and interpolating between nodes to generate smooth trajectories. The system dynamically refines the path segments during calculation to balance computational efficiency with path smoothness, ensuring comfortable vehicle movement.
Data Source
AI summary
A method for automated parking of a vehicle includes providing image data captured by at least one vision sensor of the vehicle to an electronic control unit (ECU), and providing a parking scene map to the ECU. A free parking space present in the parking scene map is selected as a target parking space, and a parking path from a current vehicle location to the target parking space is formulated. The vehicle is autonomously maneuvered along the parking path towards the target parking space. Responsive to detection of a pedestrian in the target parking space or along the parking path, the vehicle is stopped until the detected pedestrian moves out of the target parking space or out of the parking path. After the detected pedestrian has moved out of the target parking space or out of the parking path, the vehicle continues autonomous maneuvering along the parking path towards the target parking space.