CN-122029578-A - Sensor measurement grid complexity management

Abstract

Techniques are provided for generating an occupancy grid based on inputs from a plurality of heterogeneous sensors. An example method for generating an occupancy grid includes obtaining detection information from a plurality of heterogeneous sensors, generating a single measurement grid based on the detection information from the plurality of heterogeneous sensors, determining occupancy probabilities for a plurality of cells in the single measurement grid, and outputting the occupancy grid based at least in part on the occupancy probabilities.

Inventors

• V. Apayadanabalan
• V. Slobodian Yuk
• R. D. Gowaika
• M.P. Johnson Wilson
• A. Josh
• J. Poplowski

Assignees

• 高通股份有限公司

Dates

Publication Date

20260512

Application Date

20240830

Priority Date

20240829

Claims (20)

1. 1. A method for generating an occupancy grid, the method comprising: obtaining detection information from a plurality of heterogeneous sensors; Generating a single measurement grid based on the detection information from the plurality of heterogeneous sensors; Determining the probability of occupancy of a plurality of cells in the single measurement grid, and The occupancy grid is output based at least in part on the occupancy probability.
2. 2. The method of claim 1, wherein generating the single measurement grid comprises combining the detection information in a single data buffer.
3. 3. The method of claim 1, wherein the plurality of heterogeneous sensors includes a first radar configured to detect a target in a first region and a second radar configured to detect a target in a second region different from the first region.
4. 4. The method of claim 1, wherein the plurality of heterogeneous sensors comprises lidar.
5. 5. The method of claim 1, wherein the plurality of heterogeneous sensors comprises cameras.
6. 6. The method of claim 1, wherein obtaining the detection information comprises receiving remote sensor detection information via a network interface.
7. 7. The method of claim 1, wherein the occupancy probability comprises an occupancy probability and an idle probability for each of the plurality of cells.
8. 8. The method of claim 1, wherein the occupancy probabilities comprise dynamic probabilities and static probabilities for each of the plurality of cells.
9. 9. The method of claim 1, wherein the occupancy grid comprises a grid cell state having an indication of a speed of at least one cell of the plurality of cells.
10. 10. An apparatus, the apparatus comprising: At least one memory; A plurality of heterogeneous sensors; at least one processor communicatively coupled to the at least one memory and the plurality of heterogeneous sensors, the at least one processor configured to: Obtaining detection information from the plurality of heterogeneous sensors; Generating a single measurement grid based on the detection information from the plurality of heterogeneous sensors; calculating the probability of occupancy of a plurality of cells in the single measurement grid, and An occupancy grid is output based at least in part on the occupancy probability.
11. 11. The apparatus of claim 10, wherein the at least one processor is further configured to combine the detection information in a single data buffer in the at least one memory.
12. 12. The apparatus of claim 10, wherein the plurality of heterogeneous sensors comprises a first radar configured to detect a target in a first region, and a second radar configured to detect a target in a second region different from the first region.
13. 13. The apparatus of claim 10, wherein the plurality of heterogeneous sensors comprises lidar.
14. 14. The apparatus of claim 10, wherein the plurality of heterogeneous sensors comprises cameras.
15. 15. The apparatus of claim 10, wherein the at least one processor is further configured to receive remote sensor detection information via a network interface.
16. 16. The apparatus of claim 10, wherein the occupancy probability comprises an occupancy probability and an idle probability for each of the plurality of cells.
17. 17. The apparatus of claim 10, wherein the occupancy probabilities comprise a dynamic probability and a static probability for each of the plurality of cells.
18. 18. The apparatus of claim 10, wherein the occupancy grid comprises a grid cell status with an indication of a speed of at least one cell of the plurality of cells.
19. 19. An apparatus for generating an occupancy grid, the apparatus comprising: Means for obtaining detection information from a plurality of heterogeneous sensors; means for generating a single measurement grid based on the detection information from the plurality of heterogeneous sensors; means for determining the probability of occupancy of a plurality of cells in said single measurement grid, and Means for outputting the occupancy grid based at least in part on the occupancy probability.
20. 20. The apparatus of claim 19, wherein the means for generating the single measurement grid comprises means for combining the detection information in a single data buffer.

Description

Sensor measurement grid complexity management Cross Reference to Related Applications The present application claims the benefit of U.S. patent application Ser. No. 18/819,026, entitled "SENSOR MEASUREMENT GRID COMPLEXITY MANAGEMENT (sensor measurement grid complexity management)" filed on month 8 and 29 of 2024, which claims the benefit of U.S. provisional application Ser. No. 63/594,579, entitled "SENSOR MEASUREMENT GRID COMPLEXITY MANAGEMENT (sensor measurement grid complexity management)" filed on month 31 of 2023, which is assigned to the assignee of the present application and is hereby incorporated by reference in its entirety for all purposes. Background As the industry tends to deploy more and more sophisticated self-driven technologies, which are capable of operating the vehicle with little or no human input, and are therefore semi-autonomous or autonomous, vehicles are becoming more intelligent. Autonomous and semi-autonomous vehicles may be able to detect information about their location and surrounding environment (e.g., using ultrasound, radar, laser radar, SPS (satellite positioning system), and/or odometry, and/or one or more sensors such as accelerometers, cameras, etc.). Autonomous and semi-autonomous vehicles typically include a control system to interpret information about the environment in which the vehicle is located to identify hazards and determine the navigation path to follow. The control system may be configured to calculate an occupancy grid based on inputs from the plurality of sensors. A perception module within the vehicle may be configured to utilize the occupancy grid for collision avoidance and navigation. Disclosure of Invention An example method for generating an occupancy grid in accordance with the present disclosure includes obtaining detection information from a plurality of heterogeneous sensors, generating a single measurement grid based on the detection information from the plurality of heterogeneous sensors, determining occupancy probabilities for a plurality of cells in the single measurement grid, and outputting the occupancy grid based at least in part on the occupancy probabilities. Implementations of such methods may include one or more of the following features. Generating a single measurement grid may include combining the detection information in a single data buffer. The plurality of heterogeneous sensors may include a first radar configured to detect a target in a first region and a second radar configured to detect a target in a second region different from the first region. The plurality of heterogeneous sensors may include lidar and/or cameras. Obtaining the detection information may include receiving remote sensor detection information via a network interface. The occupancy probabilities may include occupancy probabilities and idle probabilities for each of the plurality of cells. The occupancy probabilities may include dynamic probabilities and static probabilities for each of the plurality of cells. The occupancy grid may include a grid cell status having an indication of a speed of at least one cell of the plurality of cells. An example apparatus according to the present disclosure includes at least one memory, a plurality of heterogeneous sensors, at least one processor communicatively coupled to the at least one memory and the plurality of heterogeneous sensors, the at least one processor configured to obtain detection information from the plurality of heterogeneous sensors, generate a single measurement grid based on the detection information from the plurality of heterogeneous sensors, calculate occupancy probabilities for a plurality of cells in the single measurement grid, and output the occupancy grid based at least in part on the occupancy probabilities. Items and/or techniques described herein may provide one or more of the following capabilities, as well as other capabilities not mentioned. Multiple sensors (such as cameras, radars, and lidars) may obtain detection information of objects approaching autonomous or semi-autonomous vehicles. The detection information may be used to generate an occupancy grid. The detection information from multiple sensors may be combined into a single data buffer and plotted on a single measurement grid. Each cell in a single measurement grid may be analyzed to determine the occupied and/or free space probabilities. Analysis of a single measurement grid may require fewer processing cycles than existing multi-grid techniques. The process of fusing multiple sensor-based occupancy grids may be eliminated. The reduction in processing cycles may reduce the latency associated with generating the occupancy grid. The object detection process may be improved. Other capabilities may be provided, and not every implementation according to the present disclosure must provide any of the capabilities discussed, let alone all of the capabilities. Drawings FIG. 1 is a top view of an example self-vehicle. FIG. 2 is a block