# US 2022/0055613 A1 · Advanced passenger safety for an autonomous vehicle

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

- Number: US 2022/0055613 A1
- Document ID: US20220055613A1
- Status: Published application
- Kind: A1
- Application number: 17/515,953
- Filed: 2021-11-01
- Published: 2022-02-24
- Earliest claimed: 2019-05-13
- Assignees: GM Cruise Holdings LLC
- Applicants: GM Cruise Holdings LLC
- Inventors: Hemant Kavadia; Nishant Sharma; Abhishek Jain
- Web page: https://patentgrep.com/patent/US20220055613A1

## CPC

- B60W 30/08: {Active safety systems} predicting or avoiding probable or impending collision {or attempting to minimise its consequences}
- B60W 30/085: Taking automatic action to adjust vehicle attitude in preparation for collision, e.g. braking for nose dropping
- B60W 30/095: Predicting travel path or likelihood of collision
- B60W 50/0097: {Predicting future conditions}
- B60W 60/0016: {of the vehicle or its occupants}
- G05B 17/02: electric
- G05D 1/0088: {characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00)}
- G06F 30/15: Vehicle, aircraft or watercraft design
- G06F 30/20: Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30)
- G06F 30/27: using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
- G06T 7/593: from stereo images
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06V 20/593: {Recognising seat occupancy}
- B60R 11/04: Mounting of cameras operative during drive; Arrangement of controls thereof relative to the vehicle
- B60R 2011/0003: {inside the vehicle}
- B60W 2050/0028: {Mathematical models, e.g. for simulation}
- B60W 2400/00: Indexing codes relating to detected, measured or calculated conditions or factors
- B60W 2420/403: Image sensing, e.g. optical camera
- B60W 2540/049: Number of occupants
- B60W 2540/223: Posture, e.g. hand, foot, or seat position, turned or inclined
- B60W 2540/227: Position in the vehicle
- G06T 2207/10012: Stereo images
- G06T 2207/30196: Human being; Person
- G06T 2207/30268: Vehicle interior
- G06V 40/161: {Detection; Localisation; Normalisation}
- H04N 23/698: for achieving an enlarged field of view, e.g. panoramic image capture
- B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- B60R: VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

Systems and methods can improve passenger safety for an Autonomous Vehicle (AV) based on the integration of sensor data captured by the AV's interior and exterior sensors. The AV can determine passenger occupancy data corresponding to where each passenger is detected within the AV by the interior sensors. The AV can determine multiple sets of one or more driving actions that the AV can perform at a future time. The AV can generate crash impact data corresponding to where each passenger is detected from one or more simulated collisions between the AV and one or more objected detected by the exterior sensors when the AV performs one or more sets of driving actions from among the multiple sets. The AV can determine ranked sets of driving actions based on the passenger occupancy data and the crash impact data.

## Claims

### Claim 1

A computer-implemented method comprising:
determining, by an Autonomous Vehicle (AV), passenger occupancy data corresponding to where each passenger is detected within the AV by one or more interior sensors of the AV;
determining, by the AV, multiple sets of one or more driving actions that the AV can perform at a future time;
generating, by the AV, crash impact data from one or more simulated collisions between the AV and one or more objects detected by one or more exterior sensors of the AV when the AV performs one or more sets of driving actions from among the multiple sets; and
determining, by the AV, ranked sets of one or more driving actions from among the multiple sets based on the passenger occupancy data and the crash impact data.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, further comprising:
determining, from the multiple sets, that a collision is unavoidable; and
performing a highest ranking set of driving actions from among the ranked sets.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein the crash impact data includes one or more principal directions of force for the one or more simulated collisions.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein the crash impact data includes one or more crash or injury severity metrics.

### Claim 5 (depends on 4)

The computer-implemented method of claim 4, wherein the one or more crash or injury severity metrics includes an aggregate crash or injury metric for the AV or a passenger.

### Claim 6 (depends on 4)

The computer-implemented method of claim 4, wherein the one or more crash or injury severity metrics includes one or more individual crash or injury severity metrics corresponding to where each passenger is detected within the AV.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, further comprising:
capturing sensor data using four or more cameras arranged to capture fields of view including for or more seats of the AV; and
detecting where each passenger is seated within the AV from the sensor data.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, further comprising:
capturing sensor data as 360 degree image data using one or more cameras disposed toward a center of a ceiling of the AV; and
detecting where each passenger is seated within the AV from the sensor data.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, further comprising:
capturing sensor data as 180 degree image data using one or more cameras disposed toward a front or a rear of the AV; and
detecting where each passenger is seated within the AV from the sensor data.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1, further comprising:
processing image data from one or more pairs of cameras to generate stereoscopic image data;
determining disparity information from the stereoscopic image data; and
determining three-dimensional position data of a passenger detected within the AV from the disparity information.

### Claim 11 (depends on 1)

The computer-implemented method of claim 1, further comprising:
determining a demographic trait of a passenger detected within the AV.

### Claim 12 (depends on 1)

The computer-implemented method of claim 1, further comprising:
determining an extent to which a seat of the AV occupied by a passenger is reclined.

### Claim 13

An Autonomous Vehicle (AV), comprising:
one or more processors;
one or more interior sensors;
one or more exterior sensors; and
memory including instructions that, when executed by the one or more processors, cause the AV to:
determine passenger occupancy data corresponding to where each passenger is detected within the AV by the one or more interior sensors;
determine multiple sets of one or more driving actions that the AV can perform at a future time;
generate crash impact data from one or more simulated collisions between the AV and one or more objects detected by the one or more exterior sensors when the AV performs one or more sets of driving actions from among the multiple sets; and
determine ranked sets of one or more driving actions from among the multiple sets based on the passenger occupancy data and the crash impact data.

### Claim 14 (depends on 13)

The AV of claim 13, wherein the instructions, when executed, further cause the AV to:
determine, from the multiple sets, that a collision is unavoidable; and
perform a highest ranking set of driving actions from among the ranked sets.

### Claim 15 (depends on 14)

The AV of claim 14, wherein the crash impact data includes one or more principal directions of force for the one or more simulated collisions.

### Claim 16 (depends on 15)

The AV of claim 15, wherein the crash impact data further includes one or more crash or injury severity metrics corresponding to the one or more principal directions of force.

### Claim 17

A non-transitory computer-readable storage medium including instructions that, upon being executed by one or more processors of an Autonomous Vehicle (AV), cause the AV to:
determine passenger occupancy data corresponding to where each passenger is detected within the AV by one or more interior sensors of the AV;
determine multiple sets of one or more driving actions that the AV can perform at a future time;
generate crash impact data from one or more simulated collisions between the AV and one or more objects detected by one or more exterior sensors of the AV when the AV performs one or more sets of driving actions from among the multiple sets;
determine ranked sets of one or more driving actions from among the multiple sets based on the passenger occupancy data and the crash impact data; and
perform a highest ranking set of driving actions from among the ranked sets in response to a determination, from the multiple sets, that a collision is unavoidable.

### Claim 18 (depends on 17)

The non-transitory computer-readable storage medium of claim 17, wherein the instructions, when executed, further cause AV system to:
process image data from one or more pairs of cameras to generate stereoscopic image data;
determine disparity information from the stereoscopic image data; and
determine three-dimensional position data of one or more passengers of the AV from the disparity information.

### Claim 19 (depends on 17)

The non-transitory computer-readable storage medium of claim 17, wherein the instructions, when executed, further cause AV system to:
determine a demographic trait of a passenger detected within the AV.

### Claim 20 (depends on 17)

The non-transitory computer-readable storage medium of claim 17, wherein the instructions, when executed, further cause AV system to:
determine an extent to which a seat of the AV occupied by a passenger is reclined.
