Systems and methods for autonomous horn activation and kidnapping detection

Patent metadata

Field	Value
Publication number	US-2025022313-A1
Application number	US-202318221825-A
Country	US
Kind code	A1
Filing date	Jul 13, 2023
Priority date	Jul 13, 2023
Publication date	Jan 16, 2025
Grant date	—

Abstract

An autonomous vehicle can include a horn; a sensor(s) configured to capture images; and one or more processors. The one or more processors can be configured to receive a sequence of images from the sensor(s), the sequence of images captured by the sensor(s) as the autonomous vehicle was moving; execute a machine learning model using the sequence of images as input to detect a human inside a second vehicle or in the surrounding environment of the autonomous vehicle depicted within the sequence of images; determine, based on the detection of the human inside the second vehicle or in the surrounding environment of the autonomous vehicle within the sequence of images, the human is depicted performing a defined arm gesture within the sequence of images; and activate the horn responsive to the determination that the human is depicted performing the defined arm gesture within the sequence of images.

First claim

What is claimed is:

1 . An autonomous vehicle, comprising:
a sensor configured to capture images; and one or more processors configured to:
detect an alert indicating one or more vehicle characteristics;
receive a sequence of images from the sensor;
determine a second vehicle depicted within the sequence of images has the one or more vehicle characteristics;
responsive to the determination that the second vehicle depicted within the sequence of images has the one or more vehicle characteristics, execute a machine learning model using the sequence of images as input to determine a human inside the second vehicle is performing a distressed action; and
activate a distress response protocol responsive to the determination that the human inside the second vehicle is performing the distressed action.

2 . The autonomous vehicle of claim 1 , wherein the one or more processors are configured to detect the alert by:
querying a database stored in a remote computing device, the database configured to store a list of alerts, each alert including an identification of an individual and one or more vehicle characteristics; and identifying the alert from the database.

3 . The autonomous vehicle of claim 2 , further comprising:
a network interface configured to communicate with a server,
wherein the one or more processors are configured to activate the distress response protocol by transmitting, via the network interface, a message comprising the identification of the individual from the alert to a remote computing device.

4 . The autonomous vehicle of claim 3 , wherein transmitting the message comprises transmitting a current location of the autonomous vehicle to the remote computing device.

5 . The autonomous vehicle of claim 1 , wherein the one or more processors are configured to detect the alert by receiving the alert from a remote computing device.

6 . The autonomous vehicle of claim 1 , wherein the one or more processors are configured to determine the second vehicle depicted within the sequence of images has the one or more vehicle characteristics by:
executing a second machine learning model using the sequence of images as input to extract features from the sequence of images; and determine the second vehicle depicted within the sequence of images has the one or more vehicle characteristics by determining the features satisfy a condition associated with the detected alert.

7 . The autonomous vehicle of claim 1 , wherein the distressed action corresponds to an action associated with a kidnapped individual.

8 . The autonomous vehicle of claim 1 , wherein the autonomous vehicle comprises:
a tractor; and a trailer pulled by the tractor,
wherein the sensor is mounted to a top surface of the tractor.

9 . The autonomous vehicle of claim 8 , wherein the sensor is configured to capture images in a 360 degree rotation.

10 . The autonomous vehicle of claim 1 , wherein the one or more processors are configured to:
detect a second alert indicating second one or more vehicle characteristics; receive a second sequence of images from the sensor; determine a third vehicle depicted within the second sequence of images has the second one or more vehicle characteristics; responsive to the determination that the third vehicle depicted within the second sequence of images has the second one or more vehicle characteristics, execute the machine learning model using the second sequence of images as input to determine the second sequence of images does not depict a second human associated with the third vehicle performing the distressed action; and discard the second sequence of images without activating the distress response protocol responsive to the determination that the second sequence of images does not depict a second human associated with the third vehicle performing the distressed action.

11 . The autonomous vehicle of claim 1 , wherein the one or more processors are further configured to:
identify a location of the alert; identify a current location of the autonomous vehicle; determine a distance between the location of the alert and the current location of the autonomous vehicle; and determine whether the second vehicle depicted with the sequences of images has the one or more characteristics in response to a determination that the distance is less than a threshold.

12 . A method, comprising:
detecting, by one or more processors of an autonomous vehicle, an alert indicating one or more vehicle characteristics; receiving, by the one or more processors of the autonomous vehicle from a sensor of the autonomous vehicle, a sequence of images from the sensor; determining, by the one or more processors, a second vehicle depicted within the sequence of images has the one or more vehicle characteristics; responsive to the determining that the second vehicle depicted within the sequence of images has the one or more vehicle characteristics, executing, by the one or more processors, a machine learning model using the sequence of images as input to determine a human inside the second vehicle is performing a distressed action; and activating, by the one or more processors, a distress response protocol responsive to the determining that the human inside the second vehicle is performing the distressed action.

13 . The method of claim 12 , wherein detecting the alert comprises:
querying, by the one or more processors, a database stored in a remote computing device, the database configured to store a list of alerts, each alert including an identification of an individual and one or more vehicle characteristics; and identifying, by the one or more processors, the alert from the database.

14 . The method of claim 13 , wherein activating the distress response protocol comprises transmitting, by the one or more processors and via a network interface, a message comprising the identification of the individual from the alert to a remote computing device.

15 . The method of claim 14 , wherein transmitting the message comprises transmitting, by the one or more processors, a current location of the autonomous vehicle to the remote computing device.

16 . The method of claim 12 , wherein detecting the alert comprises receiving, by the one or more processors, the alert from a remote computing device.

17 . The method of claim 12 , determining a second vehicle depicted within the sequence of images has the one or more vehicle characteristics comprises:
executing, by the one or more processors, a second machine learning model using the sequence of images as input to extract features from the sequence of images; and determining, by the one or more processors, the second vehicle depicted within the sequence of images has the one or more vehicle characteristics by determining the features satisfy a condition associated with the detected alert.

18 . The method of claim 12 , wherein the distressed action corresponds to an action associated with a kidnapped individual.

19 . The method of claim 12 , further comprising:
identifying, by the one or more processors, a location of the alert; identifying, by the one or more processors, a current location of the autonomous vehicle; determining, by the one or more processors, a distance between the location of the alert and the current location of the autonomous vehicle; and determining, by the one or more processors, whether the second vehicle depicted with the sequences of images has the one or more characteristics in response to a determination that the dista

Assignees

• Torc Robotics Inc

Inventors

• Harrison Christopher
• Culhane Andrew

Classifications

• B60W2556/45

  External transmission of data to or from the vehicle · CPC title

• G08B21/02

  Alarms for ensuring the safety of persons · CPC title

• G08B13/19647

  Systems specially adapted for intrusion detection in or around a vehicle · CPC title

• G06V20/56

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

• G06V10/40

  Extraction of image or video features · CPC title