# US 2021/0011481 A1 · Apparatus for controlling behavior of autonomous vehicle and method thereof

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

- Number: US 2021/0011481 A1
- Document ID: US20210011481A1
- Status: Published application
- Kind: A1
- Application number: 16/685,156
- Filed: 2019-11-15
- Published: 2021-01-14
- Earliest claimed: 2019-07-12
- Assignees: Hyundai Motor Company; Kia Motors Corporation
- Applicants: Hyundai Motor Company; Kia Motors Corporation
- Inventors: Dae Gil CHO
- Web page: https://patentgrep.com/patent/US20210011481A1

## CPC

- B60W 30/165: Automatically following the path of a preceding lead vehicle, e.g. "electronic tow-bar"
- B60W 40/04: Traffic conditions
- B60W 60/001: {Planning or execution of driving tasks}
- G05D 1/0088: {characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00)}
- G05D 1/0221: {involving a learning process}
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/82: using neural networks
- 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 20/584: {of vehicle lights or traffic lights}
- G06V 40/20: Movements or behaviour, e.g. gesture recognition (recognition of facial expressions G06V40/16)
- B60W 2420/403: Image sensing, e.g. optical camera
- B60W 2554/00: Input parameters relating to objects
- B60W 2554/4043: Lateral speed
- B60W 2554/4046: Behavior, e.g. aggressive or erratic
- B60W 2554/60: Traversable objects, e.g. speed bumps or curbs
- B60W 2554/80: Spatial relation or speed relative to objects
- B60W 2720/10: Longitudinal speed
- 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
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Disclosed are an apparatus for controlling the behavior of an autonomous vehicle and a method thereof. The apparatus includes a learning device that learns a behavior of a vehicle in a situation of avoiding an obstacle located on a road, and a controller that controls the behavior of the autonomous vehicle based on a learning result of the learning device.

## Claims

### Claim 1

An apparatus for controlling a behavior of an autonomous vehicle, the apparatus comprising:
a learning device configured to learn a behavior of a vehicle in a situation of avoiding an obstacle located on a road; and
a controller configured to control the behavior of the autonomous vehicle based on a learning result of the learning device.

### Claim 2 (depends on 1)

The apparatus of claim 1, further comprising:
a sensor configured to sense a behavior of a preceding vehicle traveling in a same lane as the autonomous vehicle.

### Claim 3 (depends on 2)

The apparatus of claim 2, wherein the sensor is configured to sense lateral and vertical behaviors of the preceding vehicle.

### Claim 4 (depends on 3)

The apparatus of claim 3, wherein the vertical behavior includes a vertical behavior of a left portion of a body of the preceding vehicle and a vertical behavior of a right portion of a body of the preceding vehicle.

### Claim 5 (depends on 3)

The apparatus of claim 3, wherein the controller is configured to apply the lateral behavior of the preceding vehicle sensed by the sensor to the learning result of the learning device to estimate whether an obstacle exists.

### Claim 6 (depends on 5)

The apparatus of claim 5, wherein the controller is configured to control the behavior of the autonomous vehicle to follow the lateral behavior of the preceding vehicle when the obstacle exists.

### Claim 7 (depends on 3)

The apparatus of claim 3, wherein the controller is configured to apply the vertical behavior of the preceding vehicle sensed by the sensor to the learning result of the learning device to estimate whether an obstacle exists.

### Claim 8 (depends on 7)

The apparatus of claim 7, wherein the controller is configured to reduce a speed of the autonomous vehicle when the obstacle exists.

### Claim 9 (depends on 1)

The apparatus of claim 1, wherein the learning device is configured to perform learning based on a recurrent neural network (RNN).

### Claim 10 (depends on 1)

The apparatus of claim 1, wherein the controller comprises a microprocessor.

### Claim 11 (depends on 1)

The apparatus of claim 1, wherein the learning device is configured to include a temporal order of data input to the learning device as learning data.

### Claim 12

A method of controlling a behavior of an autonomous vehicle, the method comprising:
learning, by a learning device, a behavior of a vehicle in a situation of avoiding an obstacle located on a road; and
controlling, by a controller, the behavior of the autonomous vehicle based on a learning result of the learning device.

### Claim 13 (depends on 12)

The method of claim 12, further comprising:
sensing, by a sensor, a behavior of a preceding vehicle traveling in a same lane as the autonomous vehicle.

### Claim 14 (depends on 13)

The method of claim 13, wherein the sensing of the behavior of the preceding vehicle includes:
sensing a lateral behavior of the preceding vehicle; and
sensing a vertical behavior of the preceding vehicle.

### Claim 15 (depends on 14)

The method of claim 14, wherein the sensing of the vertical behavior includes:
sensing a vertical behavior of a left portion of a body of the preceding vehicle; and
sensing a vertical behavior of a right portion of a body of the preceding vehicle.

### Claim 16 (depends on 14)

The method of claim 14, wherein the controlling of the behavior of the autonomous vehicle includes:
applying the lateral behavior of the preceding vehicle sensed by the sensor to the learning result of the learning device to estimate whether an obstacle exists; and
controlling the behavior of the autonomous vehicle to follow the lateral behavior of the preceding vehicle when the obstacle exists.

### Claim 17 (depends on 15)

The method of claim 15, wherein the controlling of the behavior of the autonomous vehicle includes:
applying the vertical behavior of the preceding vehicle sensed by the sensor to the learning result of the learning device to estimate whether an obstacle exists; and
reducing a speed of the autonomous vehicle when the obstacle exists.

### Claim 18 (depends on 12)

The method of claim 12, wherein the learning of the behavior of the vehicle is performed based on a recurrent neural network (RNN).

### Claim 19 (depends on 12)

The method of claim 12, wherein the controller comprises a microprocessor.

### Claim 20 (depends on 12)

The method of claim 12, wherein the learning device is configured to include a temporal order of data input to the learning device as learning data.
