IP Library Granted Patent US 12,516,952
Granted Patent B2
US 12,516,952 · App. 18/539,176 · Granted Jan 6, 2026

Environmental reference map building based on occupancy grid

Inventor: Jakub Porȩbski (Cracow, PL)
G01C21/3811G01C21/3837
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,516,952
App. No.
18/539,176
Granted
Jan 6, 2026
Kind
B2
Abstract

Disclosed is a method for building a reference map. The method includes accumulating perception sensor data for a vehicle moving through an environment. The method includes generating an occupancy grid from the accumulated sensor data as the vehicle moves. The cells in the occupancy grid have a status and a confidence characteristic associated with the respective cell status determined based on the accumulated data. The method includes building a reference map for the environment by recording reference map cell states based on the confidence characteristics of respective cell statuses in the occupancy grid. In response to the recording reference map cell states, each reference map cell is assigned a single state based on the confidence characteristics associated with the respective cell. The step of building the reference map further includes recording a weight associated with each assigned reference map cell state.

Claims (32)

1 . A method for building a reference map, the method comprising:

accumulating perception sensor data for a vehicle moving through an environment;

generating an occupancy grid from the accumulated sensor data as the vehicle moves, wherein cells in the occupancy grid have a status and a confidence characteristic associated with the respective cell status determined based on the accumulated data; and

building a reference map for the environment by recording reference map cell states based on the confidence characteristics of the respective cell statuses in the occupancy grid, wherein each cell of the reference map corresponds to a single cell in the occupancy grid,

wherein, when recording reference map cell states, each reference map cell is assigned a single state based on the confidence characteristics associated with the respective cell in the occupancy grid, and

wherein building the reference map further includes recording a weight associated with each assigned reference map cell state corresponding to the respective confidence characteristic of the respective cell status in the occupancy grid.

2 . The method of claim 1 wherein building the reference map includes recording reference map cells as having an occupied state based on the respective cell statuses in the occupancy grid having confidence characteristics meeting one or more criteria.

3 . The method of claim 1 wherein building the reference map includes recording reference map cells as having an unoccupied state based on the respective cell statuses in the occupancy grid having confidence characteristics meeting one or more criteria.

4 . The method of claim 1 wherein the perception sensor data includes radar data.

5 . The method of claim 1 wherein the occupancy grid includes a plurality of occupancy grid scans generated by a plurality of sensor scan cycles.

6 . The method of claim 1 wherein the confidence characteristic associated with the respective cell statuses includes an impact weighting based on a position of the cell relative to the vehicle moving through an environment.

7 . The method of claim 1 further comprising uploading the generated reference map to a server.

8 . The method of claim 1 wherein the generated reference map is represented as a point cloud.

9 . The method of claim 1 further comprising updating the reference map for the environment by:

comparing stored states for reference map cells with respective cells statuses in the occupancy grid; and

updating the stored states where the confidence characteristics for the respective cell status meet an update criteria.

10 . The method of claim 9 further comprising determining that the update criteria are met in response to the confidence characteristics for the cell statuses indicating a higher confidence level than the weight assigned to the respective stored reference map cell state.

11 . The method of claim 1 further comprising:

receiving reference map data from a vehicle moving through an environment, wherein the reference map data has been generated for the environment by recording reference map cell states based on the confidence characteristics of respective cell statuses in an occupancy grid generated from accumulated perception sensor data at the vehicle; and

updating the reference map for the environment by:

comparing the recorded reference map cell states in the reference map data with the respective cell statuses in the reference map and

updating the cell states where the confidence characteristics for the respective cell status meet an update criteria.

12 . An automotive electronic control unit comprising:

an input configured to accumulate perception sensor data for a vehicle moving through an environment;

an occupancy grid generating block configured to generate an occupancy grid from the accumulated sensor data as the vehicle moves, wherein cells in the occupancy grid have a status and a confidence characteristic associated with the respective cell status determined based on the accumulated data; and

a reference map building block configured to build a reference map for the environment by recording states for reference map cells based on the confidence characteristics of respective cells statuses in the occupancy grid, wherein each cell of the reference map corresponds to a single cell in the occupancy grid.

13 . A non-transitory computer-readable medium comprising instructions including:

accumulating perception sensor data for a vehicle moving through an environment;

generating an occupancy grid from the accumulated sensor data as the vehicle moves, wherein cells in the occupancy grid have a status and a confidence characteristic associated with the respective cell status determined based on the accumulated data; and

building a reference map for the environment by recording reference map cell states based on the confidence characteristics of the respective cell statuses in the occupancy grid, wherein each cell of the reference map corresponds to a single cell in the occupancy grid,

wherein, when recording reference map cell states, each reference map cell is assigned a single state based on the confidence characteristics associated with the respective cell in the occupancy grid, and

wherein building the reference map includes recording a weight associated with each assigned reference map cell state based on the respective confidence characteristic of the respective cell status in the occupancy grid.

Priority Claims (1)
EP 22213401 · Dec 14, 2022 · regional
Continuity (1)
Related Publication 20240200970A1 · Jun 20, 2024
References Cited (12)
US 11619497B2 · Yang · 2023 [cited by examiner]
US 20100274469A1 · Takahata · 2010 [cited by examiner]
US 20210131823A1 · Giorgio · 2021 [cited by examiner]
US 20220197301A1 · Moawad · 2022 [cited by examiner]
US 20230036838A1 · Slobodyanyuk · 2023 [cited by examiner]
EP 4016115A1 · 2022 [cited by applicant]
Extended European Search Report for EP App. No. 22213401 dated Sep. 15, 2023, 10 pages. [cited by applicant]
Jo et al., “Cloud Update of Tiled Evidential Occupancy Grid Maps for the Multi-Vehicle Mapping,” Sensors 2018, 18 (12), 4119; https://doi.org/10.3390/s18124119. [cited by applicant]
Wolcott et al., “Robust LIDAR localization using multiresolution Gaussian mixture maps for autonomous driving,” The International Journal of Robotics Research, vol. 36, Issue 3, 2017. [cited by applicant]
Clemens et al., “β-SLAM: Simultaneous localization and grid mapping with beta distributions,” Information Fusion, vol. 52, Dec. 2019. [cited by applicant]
Berger et al., “Direct Geometrical Map to Low-Level Grid Map Registration for Robust Online Localization,” 2018 21st International Conference on Intelligent Transportation Systems (ITSC), Maui, HI, USA, 2018, pp. 2223-2… [cited by applicant]
Poggenhans et al., “Precise Localization in High-Definition Road Maps for Urban Regions,” 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain, 2018, pp. 2167-2174, doi: 10.1109… [cited by applicant]