# US 2021/0070320 A1 · Method and Apparatus for Determining Information Related to a Lane Change of Target Vehicle, Method and Apparatus for Determining a Vehicle Comfort Metric for a Prediction of a Driving Maneuver of a Target Vehicle and Computer Program

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

- Number: US 2021/0070320 A1
- Document ID: US20210070320A1
- Status: Published application
- Kind: A1
- Application number: 16/951,195
- Filed: 2020-11-18
- Published: 2021-03-11
- Earliest claimed: 2018-11-08
- Assignees: Bayerische Motoren Werke Aktiengesellschaft
- Applicants: Bayerische Motoren Werke Aktiengesellschaft
- Inventors: Naveen Shankar NAGARAJA; Oliver SCHEEL; Loren SCHWARZ
- Web page: https://patentgrep.com/patent/US20210070320A1

## CPC

- B60W 60/0013: {specially adapted for occupant comfort}
- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- B60W 30/0956: {the prediction being responsive to traffic or environmental parameters}
- B60W 50/0097: {Predicting future conditions}
- B60W 50/0098: {Details of control systems ensuring comfort, safety or stability not otherwise provided for}
- 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 3/045: Combinations of networks
- G06N 3/09: Supervised learning
- G06N 20/00: Machine learning
- 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
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method for determining information related to a lane change of a target vehicle includes obtaining information related to an environment of the target vehicle. The information related to the environment relates to a plurality of features of the environment of the target vehicle. The plurality of features are partitioned into two or more groups of features. The method further determines two or more weighting factors for the two or more groups of features. An attention mechanism is used for determining the two or more weighting factors. The method further determines the information related to the lane change of the target vehicle based on the information related to the environment of the target vehicle using a machine-learning network. A weighting of the plurality of features of the environment of the target vehicle within the machine-learning network is based on the two or more weighting factors for the two or more groups of features.

## Claims

### Claim 1

A method for determining a vehicle comfort metric for a prediction of a driving maneuver of a target vehicle, the method comprising:
obtaining information related to an extent of the driving maneuver of the target vehicle;
obtaining information related to a prediction of the driving maneuver of the target vehicle; and
determining the vehicle comfort metric for the prediction of the driving maneuver based on a comparison of the information related to the extent of the driving maneuver and the information related to the prediction of the driving maneuver,
wherein the comfort metric is determined based on one or more elements of the group of: a delay between a start of the driving maneuver and a first prediction of the driving maneuver, an overlap between the driving maneuver and the prediction of the driving maneuver, a number of discontinuous predictions of the driving maneuver, and a missed prediction of the driving maneuver.

### Claim 2

A computer product comprising a non-transitory computer readable medium having stored thereon program that, when executed on a computer, a processor, or a programmable hardware component, carries out the acts of:
obtaining information related to an extent of the driving maneuver of the target vehicle;
obtaining information related to a prediction of the driving maneuver of the target vehicle; and
determining a vehicle comfort metric for the prediction of the driving maneuver based on a comparison of the information related to the extent of the driving maneuver and the information related to the prediction of the driving maneuver,
wherein the comfort metric is determined based on one or more elements of the group of: a delay between a start of the driving maneuver and a first prediction of the driving maneuver, an overlap between the driving maneuver and the prediction of the driving maneuver, a number of discontinuous predictions of the driving maneuver, and a missed prediction of the driving maneuver.

### Claim 3

An apparatus for determining a vehicle comfort metric for a prediction of a driving maneuver of a target vehicle, the apparatus comprising:
at least one interface for obtaining information related to an extent of the driving maneuver of the target vehicle and for obtaining information related to a prediction of the driving maneuver of the target vehicle; and
a computation module configured to:
determine the vehicle comfort metric for the prediction of the driving maneuver based on a comparison of the information related to the extent of the driving maneuver and the information related to the prediction of the driving maneuver,
wherein the comfort metric is determined based on one or more elements of the group of a delay between a start of the driving maneuver and a first prediction of the driving maneuver, an overlap between the driving maneuver and the prediction of the driving maneuver, a number of discontinuous predictions of the driving maneuver, and a missed prediction of the driving maneuver.
