User trained map for valet parking feature

Patent metadata

Field	Value
Publication number	US-12146754-B2
Application number	US-202217582125-A
Country	US
Kind code	B2
Filing date	Jan 24, 2022
Priority date	Mar 19, 2021
Publication date	Nov 19, 2024
Grant date	Nov 19, 2024

Abstract

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.

First claim

The invention claimed is:

1. A method of providing a user trained map for driver assistance in a vehicle, the method comprising:
entering a training mode, wherein a driven speed of the vehicle in the training mode ranges within a pre-defined training speed limit defined to avoid negatively affecting map accuracy;
acquiring and at least temporarily storing vehicle sensor data related to a position of the vehicle while the vehicle is operating in the 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.

2. The method of claim 1 , wherein the training mode receives manual steering input from a user of the vehicle.

3. The method of claim 1 , wherein the vehicle sensor data includes GPS (Global Positioning System) data.

4. The method according to claim 1 , further comprising:
entering an autonomous driving mode if the autonomous driving mode has not already been entered;
steering the vehicle, in the autonomous driving mode, from the drop-off location along the parking route at least partially based on the trained digital map;
identifying a parking location on the parking route; and
parking the vehicle in the parking location.

5. The method according to claim 4 , wherein identifying the parking location includes identifying the parking location at least partially based on vehicle sensor data, the vehicle sensor data including at least one of camera data, Lidar data, radar data, ultrasonic sensor data, and proximity sensor data.

6. The method of claim 4 , comprising receiving instructions from a user to park the vehicle.

7. The method according to claim 1 , comprising:
entering an autonomous driving mode if the autonomous driving mode has not already been entered; and
steering the vehicle, in the autonomous driving mode, to the pickup location at least partially based on the trained digital map.

8. The method of claim 7 , comprising receiving instructions from a user to move the vehicle from the parking location to the pickup location.

9. The method according to claim 1 , comprising:
determining that the vehicle is entering a car park;
determining whether digital map information of the car park is available; and
proposing entry into and performance of the training mode to a user of the vehicle.

10. The method according to claim 9 , comprising:
determining that the digital map information of the car park is available; and
confirming that the digital map information is correct by comparison of the digital map information with the trained digital map.

11. The method according to claim 10 , comprising guiding the user of the vehicle in training mode along the parking route at least partially based on the digital map information.

12. The method according to claim 1 , comprising: (a) post-processing the trained digital map, wherein post-processing includes refining the trained digital map using additional vehicle sensor data and/or external digital map data, the vehicle sensor data comprising at least one of camera data, Lidar data, radar data, ultrasonic sensor data, and proximity sensor data, and/or (b) making the trained digital map available to a central server computer for sharing the trained digital map with other users.

13. The method of claim 1 , wherein generating and storing the trained digital map of the parking route at least partially based on the acquired vehicle sensor data includes discarding a portion of the route for which the vehicle exceeded the pre-defined training limit.

14. A computing device comprising a processor and a memory, the memory storing instructions executable by the processor, the instructions including instructions to:
communicate with a sensor apparatus of a vehicle to acquire vehicle sensor data, including Global Positioning System (GPS) data from a GPS sensor;
communicate with a data storage device for storing and providing data such as vehicle sensor data and digital map data;
enter a training mode, wherein a driven speed of the vehicle in the training mode ranges within a pre-defined training speed limit defined to avoid negatively affecting map accuracy;
acquire and at least temporarily store vehicle sensor data related to a position of the vehicle while the vehicle is operating in the training mode;
generate and store a trained digital map of a parking route at least partially based on the acquired vehicle sensor data;
acquire and store 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
exit the training mode.

15. The computing device of claim 14 , further including instructions to:
enter an autonomous driving mode if the autonomous driving mode has not already been entered;
steer the vehicle, in the autonomous driving mode, from the drop-off location along the parking route at least partially based on the trained digital map;
identify a parking location on the parking route; and
park the vehicle in the parking location.

16. The computing device of claim 15 , wherein the instructions to identify a parking location include instructions to:
identify the parking location at least partially based on vehicle sensor data, the vehicle sensor data including at least one of camera data, Lidar data, radar data, ultrasonic sensor data, and proximity sensor data.

17. The computing device of claim 14 , further including instructions to:
determine that the vehicle is entering a car park;
determine whether digital map information of the car park is available; and
propose entry into and performance of the training mode to a user of the vehicle.

18. The computing device of claim 17 , further including instructions to:
determine that the digital map information of the car park is available; and
confirm that the digital map information is correct by comparison of the digital map information with the trained digital map.

19. The computing device of claim 14 , further including instructions to generate and store the trained digital map of the parking route at least partially based on the acquired vehicle sensor data includes discarding a portion of the route for which the vehicle exceeded the pre-defined training limit.

20. An autonomous driving system for a vehicle, comprising:
a vehicle sensor apparatus including at least a Global Positioning System (GPS) sensor;
control and servo units configured to autonomously drive the vehicle, at least partially based on vehicle sensor data from the vehicle sensor apparatus;
a data storage device for storing and providing data;
a user interface; and
a computing device comprising a controller and a memory, the memory storing instructions executable by the controller, the instructions including instructions to:
communicate with a sensor apparatus of the vehicle to acquire vehicle sensor data, the sensor apparatus including Global Positioning System (GPS) data from a GPS sensor;
communicate with a data storage device for storing and providing data such as vehicle sensor data and digital map data;
enter a training mode, wherein a driven speed of the vehicle in the training mode ranges within a pre-defined training speed limit defined to avoid negatively affecting map accuracy;
acquire and at least temporarily s

Assignees

• Ford Global Tech Llc

Inventors

• Benmimoun Ahmed
• Ma Chenhao
• Pak Tony Tae-Jin
• Golgiri Hamid M
• Pilutti Thomas Edward
• Celli John Michael

Classifications

• G08G1/168

  Driving aids for parking, e.g. acoustic or visual feedback on parking space · CPC title

• G01C21/3438

  Rendezvous; Ride sharing · CPC title

• B62D15/027

  Parking aids, e.g. instruction means · CPC title

• G01C21/3837

  Data obtained from a single source · CPC title

• G01C21/3811

  Point data, e.g. Point of Interest [POI] · CPC title