Unmanned Vehicle Parking Path Optimization via Average Obstacle Distance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for generating a parking path for unmanned driving vehicles are inefficient, leading to a low success rate and long parking times due to the need to evaluate numerous candidate paths and assess collision risks with obstacles.
Innovation Solution
A method where a controller in the vehicle generates a reference parking path by combining operations like head-in and head-out driving, and left/right turning, adjusting moving distances to find a path with the longest average obstacle distance, setting it as the optimum path if the distance exceeds a predetermined minimum.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If numerous candidate parking paths are evaluated to ensure safety, then parking reliability improves, but parking time increases significantly
Solution Approach 1:
The system performs preliminary actions by pre-generating multiple candidate parking paths using template-based patterns before actual parking execution. This allows the vehicle to have ready-made path options that can be quickly evaluated and selected, avoiding time-consuming real-time path generation while ensuring reliable parking through pre-planned alternatives
Solution Approach 2:
The system changes parameters by evaluating multiple candidate paths with different geometric parameters (curvature, length, obstacle distances) and selecting the optimal path based on safety margins and collision risk assessment. This parameter-based optimization enables quick comparison and selection without exhaustive simulation of each path
2Reliability
If collision risk is assessed for each candidate path, then parking safety improves, but computational complexity increases
Solution Approach 1:
The system uses simple, computationally inexpensive collision assessment methods that provide sufficient safety evaluation without requiring complex simulations. Each candidate path is evaluated using straightforward geometric calculations and safety margin checks rather than detailed physics-based collision modeling, reducing computational burden while maintaining adequate safety assessment
Solution Approach 2:
The collision risk assessment is segmented into discrete evaluation steps for each candidate path, allowing the control system to process multiple paths independently and efficiently. Each path is assessed using the same modular evaluation framework, simplifying the overall control logic while enabling comprehensive safety checking across all candidates
3Device complexity
If remote control is used for partial parking path, then system simplicity is maintained, but automation level decreases
Solution Approach 1:
The system performs preliminary path generation and optimization automatically before requiring user intervention. Multiple candidate paths are generated and evaluated in advance, with the best option selected and ready for execution, minimizing the need for remote control while maintaining system simplicity through automated preparatory work
Solution Approach 2:
The system serves itself by automatically generating candidate paths, evaluating collision risks, and selecting the optimal parking path without continuous user input. The control unit independently performs path planning and optimization, reducing reliance on remote control while keeping the overall system simple and user-friendly
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
A method of generating an optimum parking path of an unmanned driving vehicle (1) which is performed by a controller (104) in the unmanned driving vehicle (1), wherein the controller (104) changes (S203) a moving distance for a plurality of operations in a reference parking path (P1), finds a parking path in which an average obstacle distance, which is an average distance between at least one near-to-path obstacle (301, 302, 303, 401, 402, 403, 501, 502, 601, 602, 701 702, 801, 802, 1101, 1102) and the unmanned driving vehicle (1), is longest among a plurality of candidate parking paths, and sets (S205) the parking path having the longest average obstacle distance, as an optimum parking path (P2) in response to the longest average obstacle distance being longer than a predetermined minimum distance.