Autonomous Vehicle Unparking with Ranked Target Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automatic unparking systems for transportation vehicles require user input to select a target positioning, which can be complex and time-consuming, especially in scenarios with obstacles or varying traffic directions, and may propose impermissible target positions.
Innovation Solution
A method using a control unit to determine possible target positionings based on current parking situation data, including orientation, starting position, and traffic direction, assigning probabilities to each, and ranking them for user selection or autonomous unparking along a predetermined route.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the system provides multiple possible target positionings with probability rankings, then the user can select the most appropriate target position, but the unparking process becomes more complex and time-consuming due to user interaction requirements
Solution Approach 1:
The control unit automatically determines the target positioning by analyzing parking situation data, obstacle information, and traffic directions without requiring user intervention. The system serves itself by autonomously selecting the most appropriate target position based on pre-calculated probabilities, thereby eliminating the time loss associated with user selection while maintaining operational ease
Solution Approach 2:
The system pre-calculates multiple possible target positionings and their probabilities before the unparking maneuver begins. By preparing these options in advance and automatically selecting the best one, the system eliminates the need for real-time user decision-making, thus reducing unparking time while preserving ease of operation through pre-planned optimal solutions
2Reliability
If the system considers multiple possible target positionings with different probabilities, then more thorough analysis is performed, but the device complexity increases
Solution Approach 1:
The control unit segments the target positioning problem into discrete possible positions with calculated probabilities. By dividing the continuous space into specific candidate positions and evaluating each independently based on parking situation data and obstacle information, the system achieves reliable target selection without requiring overly complex continuous optimization algorithms
Solution Approach 2:
The system changes the parameter representation from continuous position coordinates to discrete probability-weighted target positions. By transforming the problem into evaluating specific candidate positions with associated probabilities rather than searching continuous space, the system maintains high reliability in target selection while reducing control unit complexity through simplified evaluation criteria
3Productivity
If the system autonomously selects target positioning without user input, then unparking speed increases, but the system may select impermissible or suboptimal target positions
Solution Approach 1:
The control unit uses feedback from parking situation data, obstacle detection information, and traffic direction data to automatically determine appropriate target positions. The system continuously evaluates multiple candidate positions against these feedback parameters and selects the most suitable one, achieving both high unparking speed and reliable target position selection without user intervention
Solution Approach 2:
The control unit acts as an intermediary between the parking situation analysis and the unparking execution. It processes parking situation data, obstacle information, and traffic directions through probability calculations to mediate the selection of appropriate target positions, ensuring both speed and appropriateness by filtering options through systematic evaluation before autonomous execution
4Use of energy by moving object
If the system optimizes for minimal movements and energy consumption, then energy efficiency improves, but the route planning becomes more complex
Solution Approach 1:
The system changes the optimization parameters to explicitly include minimal movements and energy consumption as selection criteria for target positioning. By incorporating these parameters into the probability calculation framework, the system automatically favors routes with fewer movements and lower energy requirements, achieving energy efficiency without requiring separate complex optimization algorithms
Solution Approach 2:
The system merges the route optimization criteria (minimal movements, energy consumption) with the target position selection process. By combining these considerations into a unified probability-based evaluation framework, the system achieves energy-efficient route planning without increasing device complexity, as the same control unit structures handle both position selection and route optimization together
Data Source
AI summary
A transportation vehicle with a control unit and a method for unparking a transportation vehicle from a parking space, wherein the control unit controls the transportation vehicle at least partly autonomously, wherein the method provides data relating to a current parking situation; determines possible target positionings of the transportation vehicle based on the provided data; determines a probability with which the respective target positioning corresponds to a desired target positioning of a user of the transportation vehicle while taking into account the provided data; orders the target positionings in a ranking according to the probability, and provides the ranking.