# US 12,181,890 B2 · High-definition mapping

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

- Number: US 12,181,890 B2
- Document ID: US12181890B2
- Status: Granted
- Kind: B2
- Application number: 17/814,909
- Filed: 2022-07-26
- Published: 2023-01-26
- Granted: 2024-12-31
- Earliest claimed: 2021-07-26
- Assignees: Cyngn, Inc.
- Applicants: Cyngn, Inc.
- Inventors: Biao Ma; Lior Tal
- Web page: https://patentgrep.com/patent/US12181890B2

## CPC

- G01C 21/3804: {Creation or updating of map data}
- G05D 1/0274: {using mapping information stored in a memory device (navigation using map-matching G01C21/30)}
- G01C 21/1652: {with ranging devices, e.g. LIDAR or RADAR}
- G05D 1/0212: {with means for defining a desired trajectory (involving a plurality of land vehicles G05D1/0287)}
- G05D 1/0248: {in combination with a laser (lasers per se H01S)}
- G05D 1/027: {comprising intertial navigation means, e.g. azimuth detector (inertial navigation G01C21/16; inertial navigation combined with non-inertial navigation instruments G01C21/165)}
- G05D 1/0272: {comprising means for registering the travel distance, e.g. revolutions of wheels (measuring distance traversed on the ground by vehicles, e.g. using odometers G01C22/00)}
- G05D 1/243: Means capturing signals occurring naturally from the environment, e.g. ambient optical, acoustic, gravitational or magnetic signals (using passive navigation aids external to the vehicle G05D1/244; using signals from positioning sensors located off-board the vehicle G05D1/249)
- G05D 1/246: using environment maps, e.g. simultaneous localisation and mapping [SLAM]
- G06V 20/10: Terrestrial scenes (scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59)
- G01C: MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY (measuring liquid level G01F; radio navigation, determining distance or velocity by use of propagation effects, e.g. Doppler effects, propagation time, of radio waves, analogous arrangements using other waves G01S)
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method may include obtaining sensor data about a total measurable world around an autonomous vehicle. The sensor data may be captured by sensor units co-located with the autonomous vehicle. The method may include generating a mapping dataset including the obtained sensor data and identifying data elements that each represents a point in the mapping dataset. The method may include sorting the data elements according to a structural data categorization that is a template for a high-definition map of the total measurable world and determining a mapping trajectory of the autonomous vehicle. The mapping trajectory may describe a localization and a path of motion of the autonomous vehicle. The method may include generating the high-definition map based on the structural data categorization and relative to the mapping trajectory of the autonomous vehicle, and the high-definition map may be updated based on the path of motion of the autonomous vehicle.

## Claims

### Claim 1

A method comprising:
obtaining first sensor data at a first frequency from a first sensor and second sensor data at a second frequency from a second sensor located within an autonomous vehicle (AV), the first sensor data and the second sensor data being representative of an environment around the AV and comprises a plurality of data points, wherein the second frequency is higher than the first frequency;
averaging data values of two or more of the data points included in the second sensor data to cause a number of the plurality of data points included in the second sensor data to be equal to a number of the plurality of data points included in the first sensor data to generate a set of sensor data;
generating a mapping dataset based on the set of sensor data;
identifying a plurality of data elements in the mapping dataset in which each data element of the plurality of data elements corresponds to at least one data point of the plurality of data points;
assigning a first portion of the plurality of data elements to a first structural data categorization and a second portion of the plurality of data elements to a second structural data categorization, wherein:
the data elements assigned to the first structural data categorization correspond to surface features of objects in the environment; and
the data elements assigned to the second structural data categorization correspond to edge features of the objects in the environment and are assigned based on a contrast in intensity of properties of proximate data points of the sensor data along a continuous line;
identifying the objects in the environment based on boundaries delineated by the edge features and positioning of the surface features relative to the edge features;
determining a mapping trajectory of the AV, the mapping trajectory describing a localization and a path of motion of the AV;
generating a high-definition map based on the identified objects and relative to the mapping trajectory of the AV;
updating the high-definition map based on the path of motion of the AV; and
controlling the AV such that the AV navigates the environment based on the updated high-definition map.

### Claim 2 (depends on 1)

The method of claim 1, wherein:
the first sensor comprises a Light Detection and Ranging (LiDAR) sensor and the second sensor comprises an inertial measurement unit (IMU) sensor;
the first frequency is between 5 Hertz (Hz) and 20 Hz; and
the second frequency is between 30 Hz and 100 Hz.

### Claim 3 (depends on 1)

The method of claim 1, wherein the averaging the data values of the two or more of the data points included in the second sensor data to cause the number of the plurality of data points included in the second sensor data to be equal to the number of the plurality of data points included in the first sensor data to generate a set of sensor data comprises
pairing the data points included in the first sensor data with the averaged data points included in the second sensor data corresponding to same time points to generate the set of sensor data at a third frequency.

### Claim 4 (depends on 1)

The method of claim 1, wherein the first structural data categorization or the second structural data categorization correspond to at least one of: intensity values of the data elements, proximity between data elements, degree of changes to the data elements between two or more scans of the environment, or color values of the data elements.

### Claim 5

An autonomous vehicle (AV) system configured to perform driving operations, the AV system comprising:
one or more processors; and
one or more non-transitory computer-readable storage media configured to store instructions that, in response to being executed, cause the AV system to perform operations, the operations comprising:
obtaining first sensor data and second sensor data from a sensor unit co-located within the AV, the first sensor data and the second sensor data being representative of an environment around the AV and wherein the first sensor data and second sensor data both comprise a plurality of data points;
synthesizing the plurality of data points of the second sensor data to reduce a number of the data points included in the second sensor data to be equal to a number of the data points included in the first sensor data;
pairing the data points included in the first sensor data with the synthesized data points included in the second sensor data corresponding to same time points to generate a set of sensor data, wherein the data points included in the first sensor data are paired with the synthesized data points included in the second sensor data that correspond to same time points as the data points included in the first sensor data;
generating a mapping dataset based on the set of sensor data;
identifying a plurality of data elements in the mapping dataset in which each data element of the plurality of data elements corresponds to at least one data point of the plurality of data points;
assigning a first portion of the plurality of data elements a first structural data categorization and a second portion of the plurality of data elements to a second structural data categorization, wherein:
the data elements assigned to the first structural data categorization correspond to surface features of objects in the environment; and
the data elements assigned to the second structural data categorization correspond to edge features of the objects in the environment and are assigned based on a contrast in intensity of properties of proximate data points of the sensor data along a continuous line;
identifying the objects in the environment based on boundaries delineated by the edge features and positioning of the surface features relative to the edge features;
determining a mapping trajectory of the AV, the mapping trajectory describing a localization and a path of motion of the AV;
generating a high-definition map based on the identified objects and relative to the mapping trajectory of the AV;
identifying a region of the high-definition map corresponding to the path of motion of the AV based on the mapping trajectory;
updating the region of the high-definition map corresponding to the path of motion of the AV to generate an updated high-definition map; and
controlling the AV such that the AV navigates the environment based on the updated high-definition map.

### Claim 6 (depends on 5)

The AV system of claim 5, wherein the operations further comprise:
applying a dual-channel extended Kalman filter to the sensor data to align the sensor data;
determining odometry information describing a state of the AV based on the aligned sensor data; and
sending the odometry information describing the state of the AV to a downstream computer system associated with the AV.

### Claim 7 (depends on 6)

The AV system of claim 6, wherein:
the second sensor data comprises Light Detection and Ranging (LiDAR) data generated by a LiDAR sensor of the sensor unit at a frequency between 5 Hertz (Hz) and 20 Hz; and
the first sensor data comprises Inertial Measurement Unit (IMU) data generated by a motion sensor of the sensor unit at a frequency between 40 Hz and 100 Hz.

### Claim 8 (depends on 7)

The AV system of claim 7, wherein the determining the odometry information comprises:
setting a first state of the AV based on the LiDAR data and the IMU data at a first time point;
estimating a second state of the AV based on a portion of the IMU data generated by the motion sensor before additional LiDAR data is generated by the LiDAR sensor at a second time point that is subsequent to the first time point;
verifying whether the second state is within a threshold of expected variance from the first state based on the IMU data;
obtaining the additional LiDAR data from the LiDAR sensor at a third time point subsequent to the second time point; and
determining a third state of the AV by updating the estimated second state based on the additional LiDAR data.