Autonomous Parking Trajectory Planning via Virtual Map

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for autonomous parking of motor vehicles in parking lots require complex sensor systems for continuous monitoring and distance measurement, which can be cumbersome and prone to errors.

Innovation Solution

A method that uses a virtual map to plan a trajectory by moving a geometric figure representing the vehicle, allowing for collision-free parking without the need for comprehensive sensors, by determining free and occupied parking spaces using detection devices and planning a path that avoids restricted areas.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If complex sensor systems are used for continuous monitoring and distance measurement, then parking safety and collision avoidance are improved, but device complexity and cost increase

Engineering Contradiction:
Improveparking safetyVSAvoidsensor system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent creates a virtual copy of the physical parking environment by generating a virtual map that represents the parking lot layout, parking spaces, and obstacles. This virtual representation allows the system to plan trajectories and detect collisions in silico without requiring complex physical sensors to continuously monitor the environment, thereby reducing device complexity while maintaining parking safety

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent introduces a virtual map as an intermediary between the vehicle's navigation system and the physical parking environment. Instead of directly sensing the environment with complex sensors, the system uses the virtual map to mediate trajectory planning and collision detection, simplifying the sensor requirements while ensuring safe parking operations

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If comprehensive sensors are deployed for continuous environment monitoring, then collision detection accuracy is improved, but measurement precision requirements and system complexity increase

Engineering Contradiction:
Improvecollision detection accuracyVSAvoidsensor system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system creates a virtual copy of the parking environment with precise geometric representations of parking spaces and obstacles. By performing collision detection in this virtual model, the system achieves high measurement precision without requiring complex physical sensors, as the precision requirements are transferred to the virtual map generation and processing stage

Inventive Principle:
Principle #26Copying

3Device complexity

If a virtual map approach is used for trajectory planning, then device complexity is reduced, but the accuracy of parking space detection may worsen

Engineering Contradiction:
Improvesensor system complexityVSAvoidparking space detection accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The system performs preliminary actions by pre-generating a virtual map of the parking environment that includes accurate representations of parking spaces, boundaries, and obstacles. This pre-processing of environmental information allows the system to use simpler sensors during actual parking operations while maintaining detection accuracy, as the critical spatial information is already captured in the virtual model

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3323697B1Planning of a trajectory for autonomous parking of a motor vehicle in a parking space environment
Publication Date: 2021.11.17 VALEO SCHALTER & SENSOREN GMBH
  • EP3323697B1 patent drawingFigure 1
  • EP3323697B1 patent drawingFigure 2

AI summary

The invention relates to a method aimed at enabling the planning of a trajectory (13) for the autonomous parking of a motor vehicle (11) in a parking area (1) with multiple parking spaces (20) largely without the need for complex sensors, comprising the steps of: - Determining (S1, S2) a geometric figure (10) relating to the dimensions of the motor vehicle (11) by a first detection device (32) of the parking area (1), - Determining (S3) the occupancy (23) of the multiple parking spaces (20) by a second detection device (37) of the parking area (1), - Determining (S4) a drivable area (30) or restricted area (31) of the parking area (1) on the basis of a map (2) of the parking area (1) and on the basis of the detected parking space occupancy (23) by a control unit (36) of the parking area (1),- Planning the trajectory (13) to move the geometric figure (10) onto an area (28) of the map (2) representing a free parking space (21) by the control unit (36) of the parking space environment (1) such that the geometric figure (10) never overlaps the restricted area (31) or never even partially leaves the drivable area (30).