# US 11,029,685 B2 · Autonomous risk assessment for fallen cargo

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

- Number: US 11,029,685 B2
- Document ID: US11029685B2
- Status: Granted
- Kind: B2
- Application number: 16/731,447
- Filed: 2019-12-31
- Published: 2020-04-30
- Granted: 2021-06-08
- Earliest claimed: 2018-10-18
- Assignees: Cartica Ai Ltd
- Applicants: Cartica Ai Ltd
- Inventors: Igal Raichelgauz; Karina Odinaev
- Web page: https://patentgrep.com/patent/US11029685B2

## CPC

- B60W 60/0025: {specially adapted for specific operations}
- G06F 18/23: Clustering techniques
- G06F 18/23213: with fixed number of clusters, e.g. K-means clustering
- G06N 3/045: Combinations of networks
- G06V 10/255: {Detecting or recognising potential candidate objects based on visual cues, e.g. shapes}
- G06V 10/454: {Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]}
- G06V 20/58: Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V 20/597: {Recognising the driver's state or behaviour, e.g. attention or drowsiness}
- G08G 1/056: with provision for distinguishing direction of travel
- G08G 1/16: Anti-collision systems (road vehicle drive control systems for predicting or avoiding probable or impending collision otherwise than by control of a particular sub-unit B60W30/08)
- G08G 1/162: {event-triggered}
- G08G 1/165: {for passive traffic, e.g. including static obstacles, trees}
- G08G 1/166: {for active traffic, e.g. moving vehicles, pedestrians, bikes}
- G08G 1/22: {Platooning, i.e. convoy of communicating vehicles}
- B60W 30/09: Taking automatic action to avoid collision, e.g. braking and steering
- B60W 30/0956: {the prediction being responsive to traffic or environmental parameters}
- B60W 40/02: related to ambient conditions
- B60W 40/06: Road conditions
- B60W 40/08: related to drivers or passengers
- B60W 50/14: Means for informing the driver, warning the driver or prompting a driver intervention
- B60W 60/0011: {involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles}
- B60W 60/0016: {of the vehicle or its occupants}
- B60W 60/0017: {of other traffic participants}
- B60W 60/0051: {from occupants to vehicle}
- B60W 2040/0872: {Driver physiology}
- B60W 2540/10: Accelerator pedal position
- B60W 2540/12: Brake pedal position
- B60W 2540/18: Steering angle
- B60W 2554/00: Input parameters relating to objects
- B60W 2554/4023: large-size vehicles, e.g. trucks
- B60W 2554/4046: Behavior, e.g. aggressive or erratic
- B60W 2556/65: Data transmitted between vehicles
- G05B 13/029: {using neural networks and expert systems}
- G05D 1/0044: {by providing the operator with a computer generated representation of the environment of the vehicle, e.g. virtual reality, maps (maps used for automatic navigation G05D1/0274; flight directors G01C23/005)}
- G05D 1/0061: {for transition from automatic pilot to manual pilot and vice versa}
- G05D 1/0088: {characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00)}
- G05D 1/0214: {in accordance with safety or protection criteria, e.g. avoiding hazardous areas (monitoring the location of vehicles within a certain area, e.g. forbidden or allowed areas, in traffic control systems for road vehicles G08G1/13)}
- G05D 1/0293: {Convoy travelling}
- G05D 1/225: operated by off-board computers
- G05D 1/617: Safety or protection, e.g. defining protection zones around obstacles or avoiding hazards (arrangements for controlling the position or course of two or more vehicles for avoiding collisions therebetween G05D1/693; arrangements for reacting to or preventing system or operator failure G05D1/80)
- G05D 1/695: for maintaining a fixed relative position of the vehicles, e.g. for convoy travelling or formation flight
- G05D 1/81: Handing over between on-board automatic and on-board manual control
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06F 18/2431: Multiple classes
- G06N 3/042: Knowledge-based neural networks; Logical representations of neural networks
- G06N 3/08: Learning methods
- G06N 5/04: Inference or reasoning models
- G06N 20/00: Machine learning
- G06T 2207/30261: Obstacle
- G06V 10/759: {Region-based matching}
- G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle
- G06V 20/584: {of vehicle lights or traffic lights}
- G07C 5/02: Registering or indicating driving, working, idle, or waiting time only (apparatus forming part of taximeters G07B13/00)
- G08G 1/048: with provision for compensation of environmental or other condition, e.g. snow, vehicle stopped at detector
- G08G 1/09626: {where the origin of the information is within the own vehicle, e.g. a local storage device, digital map}
- H04W 4/46: for vehicle-to-vehicle communication [V2V]
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93})
- 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
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- 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
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

A method for detecting fallen cargo, the method may include receiving by a computerized system, sensed information related to driving sessions of multiple vehicles; applying a machine learning process on the sensed information to detect fallen cargo and to classify the fallen cargo to fallen cargo classes; estimating, from the sensed information, an impact of at least some of the fallen cargo classes on a behavior of at least some of the multiple vehicles; and determining, based on the impact, at least one suggested vehicle behavior as a response to a detection of at least some of the fallen cargo classes.

## Claims

### Claim 1

A method for detecting fallen cargo, the method comprises:
receiving by a computerized system, sensed information related to driving sessions of multiple vehicles;
applying a machine learning process on the sensed information to detect multiple fallen cargo items and to classify each of the multiple fallen cargo items to a fallen cargo class out of fallen cargo classes;
estimating, from the sensed information, an impact of each fallen cargo class of at least two of the fallen cargo classes on a behavior of each vehicle of at least two of the multiple vehicles; and
determining, based on the impact, at least one suggested vehicle behavior as a response to a detection of each fallen cargo class of the at least two fallen cargo classes;
wherein the estimating of the impact comprises estimating a level of danger associated with each fallen cargo class of at least two of the fallen cargo classes; and
wherein for each vehicle of the at least two of the multiple vehicles, the estimating of the level of danger is responsive to a rate of deviation of the vehicle from a previous propagation direction of the vehicle, wherein the previous propagation direction of vehicle is a direction of propagation of the vehicle before reaching a fallen cargo of a class of at least two of the fallen cargo classes.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the suggested vehicle behavior is an optimal vehicle behavior in relation to a safety of the vehicle.

### Claim 3 (depends on 1)

The method according to claim 1, comprising the applying of the machine learning process on visual information of the sensed information.

### Claim 4 (depends on 1)

The method according to claim 1, wherein the estimating of the impact is based at least in part on motion estimation of the vehicle.

### Claim 5 (depends on 1)

The method according to claim 1, wherein the estimating of the impact is based at least in part on sensed information sensed by at least one vehicle sensor.

### Claim 6 (depends on 1)

The method according to claim 1, wherein the suggested vehicle behavior is an optimal vehicle behavior in relation to a combination of a safety of the vehicle and vehicle fuel consumption.

### Claim 7 (depends on 1)

The method according to claim 1, wherein the suggested vehicle behavior is an optimal vehicle behavior in relation to a combination of a safety of the vehicle and brake deterioration.

### Claim 8 (depends on 1)

The method according to claim 1, comprising suggesting a generation of a driver perceivable alert when a fallen cargo is detected.

### Claim 9 (depends on 1)

The method according to claim 1, comprising generating a profile of a driver of a vehicle that is expected to perform the at least one suggested vehicle behavior, wherein the suggesting of the at least one suggested vehicle behavior is also responsive to the profile of the driver.

### Claim 10 (depends on 1)

The method according to claim 1, wherein the fallen cargo classes comprises a first fallen cargo class and a second fallen cargo class that are defined at different resolutions.

### Claim 11

A non-transitory computer readable medium that stores instructions for:
receiving by a computerized system, sensed information related to driving sessions of multiple vehicles;
applying a machine learning process on the sensed information to detect multiple fallen cargo items and to classify each of the multiple fallen cargo items to a fallen cargo class out of fallen cargo classes;
estimating, from the sensed information, an impact of each fallen cargo class of at least two of the fallen cargo classes on a behavior of each vehicle of at least two of the multiple vehicles; and
suggesting, based on the impact, at least one suggested vehicle behavior as a response to a detection of each fallen cargo class of the at least two fallen cargo classes
wherein the estimating of the impact comprises estimating a level of danger associated with each fallen cargo class of at least two of the fallen cargo classes; and
wherein for each vehicle of the at least two of the multiple vehicles, the estimating of the level of danger is responsive to a rate of deviation of the vehicle from a previous propagation direction of the vehicle, wherein the previous propagation direction of vehicle is a direction of propagation of the vehicle before reaching a fallen cargo of a class of at least two of the fallen cargo classes.

### Claim 12 (depends on 11)

The non-transitory computer readable medium according to claim 11, wherein the suggested vehicle behavior is an optimal vehicle behavior in relation to a safety of the vehicle.

### Claim 13 (depends on 11)

The non-transitory computer readable medium according to claim 11, that stores instructions for the applying of the machine learning process on visual information of the sensed information.

### Claim 14 (depends on 11)

The non-transitory computer readable medium according to claim 11, wherein the estimating of the impact is based at least in part on motion estimation of the vehicle.

### Claim 15 (depends on 11)

The non-transitory computer readable medium according to claim 11, wherein the estimating of the impact is based at least in part on sensed information sensed by at least one vehicle sensor.

### Claim 16 (depends on 11)

The non-transitory computer readable medium according to claim 11, wherein the suggested vehicle behavior is an optimal vehicle behavior in relation to a combination of a safety of the vehicle and vehicle fuel consumption.

### Claim 17 (depends on 11)

The non-transitory computer readable medium according to claim 11, wherein the suggested vehicle behavior is an optimal vehicle behavior in relation to a combination of a safety of the vehicle and brake deterioration.

### Claim 18 (depends on 11)

The non-transitory computer readable medium according to claim 11, that stores instructions for suggesting a generation of a driver perceivable alert when a fallen cargo is detected.

### Claim 19

A computerized system that comprises a processor and multiple units that are configured to
receive sensed information related to driving sessions of multiple vehicles;
apply a machine learning process on the sensed information to detect multiple fallen cargo items and to classify each of the multiple fallen cargo items to a fallen cargo class out of fallen cargo classes;
estimate, from the sensed information, an impact of each fallen cargo class of at least two of the fallen cargo classes on a behavior of each vehicle of at least two of the multiple vehicles; and
suggest, based on the impact, at least one suggested vehicle behavior as a response to a detection of each fallen cargo class of the at least two fallen cargo classes
wherein the estimating of the impact comprises estimating a level of danger associated with each fallen cargo class of at least two of the fallen cargo classes; and
wherein for each vehicle of the at least two of the multiple vehicles, the estimating of the level of danger is responsive to a rate of deviation of the vehicle from a previous propagation direction of the vehicle, wherein the previous propagation direction of vehicle is a direction of propagation of the vehicle before reaching a fallen cargo of a class of at least two of the fallen cargo classes.