Method and apparatus for passenger recognition and boarding support of autonomous vehicle

Patent metadata

Field	Value
Publication number	US-2020019761-A1
Application number	US-201916559114-A
Country	US
Kind code	A1
Filing date	Sep 3, 2019
Priority date	Aug 26, 2019
Publication date	Jan 16, 2020
Grant date	—

Abstract

Disclosed is an apparatus for passenger recognition and boarding/alighting support of an autonomous vehicle. An apparatus for passenger recognition and boarding/alighting support of an autonomous vehicle according to an embodiment of the present disclosure may include a vehicle communicator configured to receive scheduled passenger information, a sensor configured to sense people outside the vehicle, and a vehicle controller configured to extract a passenger candidate group by analyzing the sensed people outside the vehicle, and calculate the number of reserved passengers using the extracted passenger candidate group and the received scheduled passenger information. One or more of an autonomous vehicle, a server, and a terminal of the present disclosure may be associated or combined with an artificial intelligence module, a drone (Unmanned Aerial Vehicle, UAV), a robot, an AR (Augmented Reality) device, a VR (Virtual Reality) device, a device associated with 5G network services, etc.

First claim

What is claimed is:

1 . An apparatus for passenger recognition and boarding/alighting support of an autonomous vehicle, the apparatus comprising:
a vehicle communicator configured to receive scheduled passenger information about a scheduled passenger from a user terminal or a stop terminal; a sensor configured to sense people within a predetermined area outside a vehicle on the basis of an appointed stop place; and a vehicle controller configured to extract a passenger candidate group by analyzing the people outside the vehicle sensed by the sensor and calculate the number of reserved passengers using the extracted passenger candidate group and the received scheduled passenger information.

2 . The apparatus of claim 1 , wherein the vehicle controller extracts the passenger candidate group by analyzing at least one of faces, motions, and movement directions of the people sensed in the predetermined area outside the vehicle.

3 . The apparatus of claim 2 , wherein the vehicle controller compares the faces of people pertaining to the passenger candidate group and face pictures in the scheduled passenger information, and calculates the number of matched people, and calculates the number of scheduled passengers by subtracting the calculated number of people from the sum of the number of the people in the passenger candidate group and the number of scheduled passengers.

4 . The apparatus of claim 2 , wherein the vehicle controller determines passenger types on the basis of at least one of faces, body shapes, walks, and belongings of the people pertaining to the reserved passengers and determines a stop position of the vehicle on the basis of a position of a passenger pertaining to the mobility handicapped.

5 . The apparatus of claim 1 , wherein the vehicle controller determines boarding standby time of the vehicle on the basis of the number of the reserved passengers, and
divides the predetermined area into several sections on the basis of separation distances with respect to the appointed stop place, and differently adjusts the boarding standby time in accordance with sections where the reserved passengers exist of the several sections.

6 . The apparatus of claim 5 , wherein the vehicle controller determines passenger types of the reserved passengers on the basis of at least one of faces, body shapes, walks, and belongings of the people outside the vehicle, and
readjusts the adjusted boarding standby time or adjusts the separation distances for discriminating sections where expectant passengers exist, on the basis of the passenger types of the reserved passengers.

7 . The apparatus of claim 1 , wherein the vehicle controller divides the predetermined area into several sections on the basis of separation distances with respect to the appointed stop place, and determines the passenger candidate group existing in a section closest to the appointed stop place of the several sections as first fixed passengers, and
determines the scheduled passengers as second fixed passengers, and calculates the fixed passengers obtained by subtracting duplicate people from the sum of the number of the first fixed passengers and the second fixed passengers as the reserved passengers.

8 . The apparatus of claim 1 , wherein the vehicle controller runs the vehicle by selecting one of a fixed route running mode and a flexible route running mode by reflecting passenger demand information and driving area information, and
the passenger demand information is determined using a deep neural network model trained in advance with scheduled passenger information and passenger information of the autonomous vehicle for each day and time band.

9 . The apparatus of claim 8 , wherein the vehicle controller stops the vehicle at every predetermined stop on a determined route when the fixed route running mode is selected,
stops the vehicle at stops where a passenger who will alight exists in the vehicle or where a reserved passenger exists, of the predetermined stops on the predetermined route, and stops the vehicle at a point, where there is a call for stopping the vehicle from the user terminal or the stop terminal, on the predetermined route.

10 . The apparatus of claim 1 , wherein when the vehicle stops for a passenger to board or alight, the appointed stop place is a point where an inlet/outlet door of the vehicle is disposed, and
the sensor senses people outside the vehicle within a predetermined area on the basis of the inlet/outlet door.

11 . The apparatus of claim 1 , further comprising an external display configured to provide driving information to people outside the vehicle, and
the vehicle controller determines whether to stop the vehicle and boarding standby time at the appointed stop place in accordance with the calculated number of the reserved passengers, displays whether to stop the vehicle and the boarding standby time through the external display, and extracts again the passenger candidate group by analyzing at least one of faces, motions, and movement directions of the people sensed by the sensor in the predetermined area.

12 . The apparatus of claim 1 , wherein the vehicle communicator performs a procedure of initial access to a 5G network on the basis of an SSB (synchronization signal block), and receives scheduled passenger information about a scheduled passenger from the user terminal or the stop terminal on the basis of a downlink grant (DL grant).

13 . A method for passenger recognition and boarding/alighting support of an autonomous vehicle, the method comprising:
receiving scheduled passenger information about a scheduled passenger from a user terminal or a stop terminal on the basis of a downlink grant (DL grant); sensing people within a predetermined area outside a vehicle on the basis of an appointed stop place; extracting a passenger candidate group by analyzing the sensed people outside the vehicle; and calculating the number of reserved passengers using the extracted passenger candidate group and the received scheduled passenger information.

14 . The method of claim 13 , wherein the extracting of a passenger candidate group includes extracting the passenger candidate group by analyzing at least one of faces, motions, and movement directions of the people sensed in the predetermined area outside the vehicle.

15 . The method of claim 13 , wherein the calculating of the number of reserved passengers includes:
comparing faces of people pertaining to the passenger candidate group and face pictures in the scheduled passenger information and calculating the number of matched people; and calculating the number of reserved passengers by subtracting the calculated number of people from the sum of the number of the people in the passenger candidate group and the number of scheduled passengers.

16 . The method of claim 13 , further comprising:
determining boarding standby time of the vehicle on the basis of the number of the reserved passengers, and dividing the predetermined area into several sections on the basis of separation distances with respect to the appointed stop place, and differently adjusting the boarding standby time in accordance with sections where the reserved passengers exist of the several sections.

17 . The method of claim 16 , further comprising:
determining the passenger types of the reserved passengers on the basis of at least one of faces, body shapes, walks, and belongings of the people outside the vehicle; and readjusting the adjusted boarding standby time or adjusting the separation distances for discriminating sect

Assignees

• Lg Electronics Inc

Inventors

• Kang Sung Suk
• Kim Eun Suk
• Lee Eun Ju

Classifications

• G06V40/103

  Static body considered as a whole, e.g. static pedestrian or occupant recognition · CPC title

• G06V20/56

  exterior to a vehicle by using sensors mounted on the vehicle · CPC title

• G06V10/82

  using neural networks · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06V40/172

  Classification, e.g. identification · CPC title