User-Trained Parking Route Maps for Unmapped Valet Parking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current advanced driver-assistance systems (ADAS) for vehicles, such as Valet Parking Assistance (VaPA), are unable to function in areas without reliable digital maps or where map data is outdated, limiting their functionality in unmapped or poorly mapped terrains.
Innovation Solution
A method where the vehicle enters a training mode, allowing users to manually drive and define parking routes using sensor data, generating a user-trained digital map for VaPA, which can be shared and refined, enabling immediate VaPA functionality without relying on existing map data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the vehicle uses pre-existing digital map data for VaPA, then the system can provide automated parking assistance in mapped areas, but the system cannot function in unmapped or poorly mapped areas
Solution Approach 1:
The system performs preliminary mapping actions by guiding the user to manually drive through the parking area and collect sensor data before VaPA functionality is needed. This preliminary data collection creates a custom digital map that enables reliable operation in previously unmapped areas, resolving the contradiction between adaptability and reliability.
Solution Approach 2:
The system allows the user to personally create and train the digital map for their specific parking area rather than relying on pre-existing maps or other users' data. This self-service approach enables the vehicle to adapt to any parking location the user visits, significantly improving versatility while maintaining reliability through user-specific mapping.
2Measurement precision
If the system relies on pre-existing digital map data, then map accuracy can be maintained, but the system cannot provide VaPA in areas without map data
Solution Approach 1:
The system creates locally customized digital maps specific to each user's parking areas rather than relying on generic pre-existing maps. This local quality approach ensures high measurement precision for the user's specific locations while simultaneously expanding geographic coverage to any area the user visits, resolving the contradiction between accuracy and versatility.
3Adaptability or versatility
If the vehicle collects and processes sensor data to create custom maps, then VaPA can work in unmapped areas, but the complexity of the system increases
Solution Approach 1:
The system introduces a training mode as an intermediary step between the user and the mapping process. This mediator guides the user through a structured data collection process, simplifying the complexity of creating custom maps while enabling operation in unmapped areas. The training mode acts as a bridge that manages the complexity burden.
Solution Approach 2:
The user personally performs the map creation process by manually driving through the parking area during training mode. This self-service approach distributes the complexity burden to the user rather than requiring the system to automatically map environments, reducing device complexity while maintaining adaptability to unmapped areas.
4Area of stationary object
If the system uses crowd-sourced map data from other vehicles, then map coverage can be expanded, but the system cannot guarantee user-specific location accuracy
Solution Approach 1:
The system prioritizes creating locally customized maps for each user's specific parking areas rather than using generic crowd-sourced data. This local quality approach ensures high location accuracy for user-specific destinations while the user can still benefit from crowd-sourced maps for initial exploration or areas where custom mapping hasn't been performed yet.
Data Source
AI summary
A user trained map for providing driver assistance in a vehicle is obtained by entering a training mode, acquiring and at least temporarily storing vehicle sensor data related to the vehicle's position during training mode while the vehicle is operating in training mode, generating and storing a trained digital map of a parking route at least partially based on the acquired vehicle sensor data, acquiring and storing position information related to a drop-off location and to a pickup location, the drop-off location and the pickup location being part of the parking route, and exiting the training mode.