Unexpected impulse change collision detector

Patent metadata

Field	Value
Publication number	US-2018102001-A1
Application number	US-201615288463-A
Country	US
Kind code	A1
Filing date	Oct 7, 2016
Priority date	Oct 7, 2016
Publication date	Apr 12, 2018
Grant date	—

Abstract

Aspects of the disclosure relate to detecting vehicle collisions. In one example, one or more computing devices may receive acceleration data of a vehicle and the expected acceleration data of the vehicle over a period of time. The one or more computing devices may determine a change in the vehicle's acceleration over the period of time, where the change in the vehicle's acceleration over the period of time is the difference between the expected acceleration data and the acceleration data. The one or more computing devices may detect an occurrence when the change in the vehicle's acceleration is greater than a threshold value and assign the occurrence into a collision category. Based on the assigned collision category, the one or more computing devices may perform a responsive action.

First claim

1 . A computer implemented method for detecting vehicle collisions, the method comprising:
receiving, by one or more computing devices, acceleration data of a vehicle over a period of time; receiving, by the one or more computing devices, expected acceleration data of the vehicle over the period of time; determining, by the one or more computing devices, a change in the vehicle's acceleration over the period of time, where the change in the vehicle's acceleration over the period of time is the difference between the expected acceleration data and the acceleration data; detecting an occurrence, by the one or more computing devices, when the change in the vehicle's acceleration is greater than a threshold value; assigning, by the one or more computing devices, the occurrence into a collision category; and performing, by the one or more computing devices, a responsive action based on the assigned collision category.

2 . The method of claim 1 , wherein the expected acceleration data is received from an acceleration and deceleration system and the acceleration data is received from a positioning system.

3 . The method of claim 1 , wherein the collision categories include at least high energy collision category and a low energy collision category.

4 . The method of claim 3 , wherein when the occurrence is categorized as a high energy collision, the responsive action performed by the one or more computing devices includes one or more of shutting down an engine, alerting occupants of the vehicle, alerting an emergency response team, alerting a remote assistant operator, unlocking and/or opening doors of the vehicle, and/or causing the vehicle to pull over and stop.

5 . The method of claim 3 , wherein when the occurrence is categorized as a low energy collision, the responsive action performed by the one or more computing devices includes automatically alerting a remote assistant operator; and
receiving a communication from the remote assistant operator, where the communication causes the vehicle to automatically pull over and shut down or continue driving.

6 . The method of claim 5 , further comprising:
receiving, by the one or more computing devices, additional data of a the vehicle's surroundings captured by a sensor during the period of time; determining based on the additional data, by the one or more computing devices, an object in the vehicle's vicinity and capable of contacting the vehicle during the period of time; based on the determining of the object, re-categorizing the occurrence into the high-fidelity low energy collision category.

7 . The method of claim 3 , wherein when the occurrence is categorized as a high-fidelity low energy collision, the responsive action performed by the one or more computing devices includes automatically shutting down unnecessary vehicle systems, alerting an emergency response team, alerting a remote assistant operator, unlock and/or opening the vehicle's doors.

8 . A system for or detecting vehicle collisions, the system comprising one or more processors configured to:
receive acceleration data of a vehicle over a period of time; receive expected acceleration data of the vehicle over the period of time; determine a change in the vehicle's acceleration over the period of time, where the change in the vehicle's acceleration over the period of time is the difference between the expected acceleration data and the acceleration data; detect an occurrence when the change in the vehicle's acceleration is greater than a threshold value; assign the occurrence into a collision category; and perform a responsive action based on the assigned collision category.

9 . The system of claim 8 , wherein the expected acceleration data is received from an acceleration and deceleration system and the acceleration data is received from a positioning system.

10 . The system of claim 8 , wherein the collision categories include at least high energy collision category and a low energy collision category.

11 . The system of claim 10 , wherein when the occurrence is categorized as a high energy collision, the responsive action performed by the one or more computing devices includes one or more of shutting down an engine, alerting occupants of the vehicle, alerting an emergency response team, alerting a remote assistant operator, unlocking and/or opening doors of the vehicle, and/or causing the vehicle to pull over and stop.

12 . The system of claim 10 , wherein when the occurrence is categorized as a low energy collision, the responsive action performed includes automatically alerting a remote assistant operator; and
receiving a communication from the remote assistant operator, where the communication causes the vehicle to automatically pull over and shut down or continue driving.

13 . The system of claim 12 , wherein the one or more processors are further configured to receive additional data of a the vehicle's surroundings captured by a sensor during the period of time;
determine, based on the additional data, an object in the vehicle's vicinity and capable of contacting the vehicle during the period of time; and based on the determining of the object, re-categorize the occurrence into the high-fidelity low energy collision category.

14 . The system of claim 10 , wherein when the occurrence is categorized as a high-fidelity low energy collision, the responsive action performed includes automatically shutting down unnecessary vehicle systems, alerting an emergency response team, alerting a remote assistant operator, unlock and/or opening the vehicle's doors.

15 . The system of claim 10 , wherein the system further comprises the vehicle.

16 . A non-transitory computer readable medium on which instructions are stored, the instructions when executed by one or more processors, cause the one or more processors to perform a method of detecting vehicle collisions, the method comprising:
receiving acceleration data of a vehicle over a period of time; receiving expected acceleration data of the vehicle over the period of time; determining a change in the vehicle's acceleration over the period of time, where the change in the vehicle's acceleration over the period of time is the difference between the expected acceleration data and the acceleration data; detecting an occurrence when the change in the vehicle's acceleration is greater than a threshold value; assigning the occurrence into a collision category; and performing a responsive action based on the assigned collision category.

17 . The non-transitory computer readable medium of claim 16 , wherein the expected acceleration data is received from an acceleration and deceleration system and the acceleration data is received from a positioning system.

18 . The non-transitory computer readable medium of claim 16 , wherein the collision categories include at least high energy collision category and a low energy collision category.

19 . The non-transitory computer readable medium of claim 18 , wherein when the occurrence is categorized as a high energy collision, the responsive action performed by the one or more computing devices includes one or more of shutting down an engine, alerting occupants of the vehicle, alerting an emergency response team, alerting a remote assistant operator, unlocking and/or opening doors of the vehicle, and/or causing the vehicle to pull over and stop.

20 . The non-transitory computer readable medium of claim 18 , wherein when the occurrence is categorized as a low energy collision, the res

Assignees

• Waymo Llc

Inventors

• Faust Aleksandra
• Fairfield Nathaniel

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• B60W2554/00

  Input parameters relating to objects · CPC title

• B60W2556/50

  of positioning data, e.g. GPS [Global Positioning System] data · CPC title

• B60Y2302/05

  Leading to automatic stopping of the vehicle · CPC title

• B60R2021/01252

  Devices other than bags · CPC title