# US 2022/0284744 A1 · Detecting and collecting accident related driving experience event data

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0284744 A1
- Document ID: US20220284744A1
- Status: Published application
- Kind: A1
- Application number: 17/686,481
- Filed: 2022-03-04
- Published: 2022-09-08
- Earliest claimed: 2021-03-04
- Assignees: Zenseact AB
- Applicants: Zenseact AB
- Inventors: Mina ALIBEIGI; Majid KHORSAND VAKILZADEH
- Web page: https://patentgrep.com/patent/US20220284744A1

## CPC

- G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle
- G07C 5/008: {communicating information to a remotely located station (transmission systems for measured values G08C)}
- G06F 11/3495: {for systems}
- G06F 18/24133: {Distances to prototypes}
- G06V 20/59: inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
- G07C 5/10: using counting means or digital clocks
- G06Q 50/265: {Personal security, identity or safety}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G07C: TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

A computer-implemented method and related aspects for detecting and collecting accident-related driving data on a vehicle are included. The method includes receiving a driving experience data stream from a source on-board the vehicle, determining an accident similarity score for a data segment of the driving experience data stream, wherein the accident similarity score is based on a similarity measurement of data features extracted from the data segment to data features of a historic accident or near-accident driving experience event, determining a criticality score for the data segment, and storing, in dependence on at least one of the determined accident similarity score and the determined criticality score, at least the extracted data features from the data segment as an accident-related driving experience event in association with at least the determined criticality score.

## Claims

### Claim 1

A computer-implemented method for detecting and collecting accident-related driving experience event data on a vehicle, the method comprising:
receiving a driving experience data stream from a source on-board the vehicle;
determining an accident similarity score for a data segment of the driving experience data stream, wherein the accident similarity score is based a similarity measurement of data features extracted from the data segment to data features of historical accident or near-accident driving experience events;
determining a criticality score for the data segment; and
storing, in dependence on at least one of the determined accident similarity score and the determined criticality score, at least the extracted data features from the data segment as an accident-related driving experience event in association with at least the determined criticality score.

### Claim 2 (depends on 1)

The method of claim 1, wherein the storing comprises storing at least the extracted data features as an accident-related driving experience event based on the accident similarity score meeting a similarity accident score condition.

### Claim 3 (depends on 1)

The method of claim 1, wherein the storing comprises storing the data segment including the extracted data features as an accident-related driving experience event based on the determined criticality score of the data segment meeting a criticality score condition.

### Claim 4 (depends on 2)

The method of claim 2, further comprising, responsive to a triggering event, sending data comprising at least one stored accident-related driving experience event to a remote server.

### Claim 5 (depends on 1)

The method of claim 1, wherein the source on-board the vehicle of the driving experience data stream is an on-board ADS and wherein the driving experience data stream comprises situational, environmental and behavioral object-level sensory information and the data features extracted from the data segment represent one or more or all of:
driver state features;
occupant state features;
behavioural features, including vehicle state and other objects;
environmental features; and
situational features.

### Claim 6 (depends on 1)

The method of claim 1, wherein determining the accident similarity score of the data segment comprises:
inputting the data segment into an accident similarity assessment module comprising a machine learning model trained to extract features from the input data segment using historic accident or historic near-accident driving experience event data;
extracting features from the data segment using the accident similarity assessment module; and
determining the accident similarity score for the data segment based on a measurement of the similarity of the extracted features with historic accident and historic near-accident driving experience event features.

### Claim 7 (depends on 6)

The method of claim 6, wherein based on the determined accident similarity score not meeting a threshold score condition for the data segment to be associated with a historic accident or a near-accident driving experience event, the method further comprises:
determining, based on the criticality score meeting a threshold criticality score condition, the data segment comprises a different type of accident or near accident driving experience event to the historic accident or near-accident event.

### Claim 8 (depends on 1)

The method of claim 1, wherein determining an accident similarity score and/or determining a criticality score for a data segment of the data stream comprises determining an accident similarity score and/or a criticality score for each of a plurality of time-sequential data segments.

### Claim 9 (depends on 1)

The method of claim 1, wherein the criticality score is dependent on a set of one or more accident criticality parameters representing one or more of:
sensory information for the proximity of objects in the surrounding environment of the vehicle;
object-level behavioural features;
internal vehicle state features;
vehicle state features;
one or more occupant states;
a driver state.

### Claim 10 (depends on 9)

The method of claim 9, wherein the criticality score is determined by inputting the set of accident criticality parameters into a deterministic, probabilistic and/or statistical, accident criticality assessment module.

### Claim 11 (depends on 1)

A control system of a vehicle, the control system comprising:
a memory;
a controller or control circuitry comprising one or more processors or processing circuitry;
computer code stored in the memory,
wherein, when the computer code is loaded from the memory and executed by the one or more processors or processing circuitry of the controller or control circuitry, the control system is caused to perform the method of claim 1.

### Claim 12 (depends on 11)

A ground vehicle, the vehicle comprising:
a perception system comprising at least one sensor configured to monitor a surrounding environment of the ground vehicle and generate a sensor data stream;
a localization system configured to monitor a geographical map position of the ground vehicle and to generate a localization data stream;
a data transceiver configurable to transmit to, and receive data from, a remote server; and
a control system according to claim 11.

### Claim 13

A computer-implemented method for collecting accident-related driving experience event data from a plurality of vehicles, the method comprising:
receiving, responsive to a data transfer triggering event occurring on at least one of the plurality of vehicles, data comprising at least one accident-related driving experience event that the vehicle has detected in a data stream of driving experience events generated on-board the vehicle and an associated criticality score for each received accident-related driving experience event; and
storing the received accident-related driving experience event data in one or more fleet accident-related experience data libraries.

### Claim 14 (depends on 13)

The method of claim 13, wherein each received accident-related driving experience event comprises a data segment and at least an accident similarity score and an accident criticality score of the data segment.

### Claim 15

A server for collecting accident-related driving experience event data from a plurality of vehicles, the server comprising:
a memory;
a control circuitry comprising one or more processors or processing circuitry; and
computer code stored in the memory,
wherein, when the computer code is loaded from the memory and executed by the one or more processors or processing circuitry of the control circuitry or controller, the server is caused to:
receive, responsive to a data transfer triggering event occurring on one of the plurality of vehicles, data comprising at least one accident-related driving experience event that the vehicle has detected in a data stream of driving experience events generated on-board the vehicle together with an associated criticality score for each of the at least one accident related-driving experience event; and
store the received accident-related driving experience event data with accident-related driving experience event data from at least one other vehicle.
