Systems and methods for autonomous vehicle path planning

Patent metadata

Field	Value
Publication number	US-12560929-B2
Application number	US-202318356744-A
Country	US
Kind code	B2
Filing date	Jul 21, 2023
Priority date	Jul 21, 2023
Publication date	Feb 24, 2026
Grant date	Feb 24, 2026

Abstract

Systems and methods for autonomous vehicle path planning are described herein. An example vehicle includes an image sensor to obtain an image of a scene of an area surrounding the vehicle. The vehicle also includes navigation system circuitry to: analyze the image and generate a semantically segmented image that identifies one or more types of features in the image; project the semantically segmented image to a two-dimensional (2D) map projection; convert the 2D map projection into a cost map; and determine a path for the vehicle based on the cost map.

First claim

What is claimed is:

1 . A vehicle comprising:
an image sensor to obtain an image of a scene of an area of a celestial body surrounding the vehicle, wherein the vehicle includes a rover on the celestial body; one or more wheels; driving system circuitry; and navigation system circuitry to:
generate, based on the image, a semantically segmented image that identifies one or more types of features in the image;
determine an attitude of the vehicle based on output from an inertial measurement unit (IMU);
project the semantically segmented image to a two-dimensional (2D) map projection based on the attitude to account for at least one of an angle or a skew of the image;
convert the 2D map projection into a cost map, the cost map defining a grid of values corresponding to at least one hazard of the area of the celestial body;
determine a path for the vehicle based on the cost map; and
control the driving system circuitry to operate the one or more wheels to drive the vehicle along the determined path.

2 . The vehicle of claim 1 , wherein the navigation system circuitry is to generate the semantically segmented image by executing a machine learning model, the machine learning model stored in a memory on the vehicle.

3 . The vehicle of claim 2 , wherein the machine learning model is a convolutional neural network (CNN).

4 . The vehicle of claim 2 , wherein the machine learning model is trained based on prior missions on the celestial body.

5 . The vehicle of claim 2 , wherein the machine learning model is trained during operation of the vehicle on the celestial body.

6 . The vehicle of claim 1 , wherein the navigation system circuitry is to project the semantically segmented image to the 2D map projection by using a transformation equation.

7 . The vehicle of claim 1 , wherein the one or more types of features include rocks.

8 . The vehicle of claim 1 , wherein the navigation system circuitry is to continuously access new images from the image sensor and update the path based on the new images.

9 . The vehicle of claim 1 , wherein the image sensor is an RGB camera.

10 . The vehicle of claim 1 , wherein the image sensor is a thermal infrared sensor.

11 . The vehicle of claim 1 , wherein the image sensor is a hyperspectral imaging sensor.

12 . The vehicle of claim 1 , wherein the image sensor is a first image sensor of a pair of image sensors of a stereo camera.

13 . The vehicle of claim 1 , wherein the image sensor includes a stereo camera, and wherein the navigation system circuitry is to determine the path based at least in part on the image from the stereo camera.

14 . The vehicle of claim 1 , wherein the 2D map projection is converted into the cost map with a leading edge detection algorithm.

15 . A non-transitory machine readable storage medium comprising instructions that, when executed, cause programmable circuitry of a vehicle to:
access an image of a scene of an area of a celestial body surrounding the vehicle, the image obtained by an image sensor on the vehicle, wherein the vehicle includes a rover on the celestial body; generate, based on the image, a semantically segmented image that identifies one or more types of features in the image; determine an attitude of the vehicle based on output from an inertial measurement unit (IMU); project the semantically segmented image to a two-dimensional (2D) map projection based on the attitude to account for at least one of an angle or a skew of the image; convert the 2D map projection to a cost map, the cost map defining a grid of values corresponding to at least one hazard of the area of the celestial body; determine a path for the vehicle based on the cost map; and operate at least one wheel of the vehicle to drive the vehicle along the determined path.

16 . The non-transitory machine readable storage medium of claim 15 , wherein the instructions, when executed, cause the programmable circuitry to generate the semantically segmented image by executing a machine learning model.

17 . The non-transitory machine readable storage medium of claim 16 , wherein the machine learning model is a convolution neural network (CNN).

18 . The non-transitory machine readable storage medium of claim 15 , wherein the one or more types of features include rocks.

Assignees

• Boeing Co

Inventors

• Kalin Joshua D
• Evans Nick S
• Loper Taylor S
• Fagerburg Joseph E

Classifications

• G05D2111/10

  Optical signals · CPC title

• G05D2107/38

  Extra-terrestrial environments, e.g. asteroids · CPC title

• G05D1/2435

  Extracting 3D information · CPC title

• G05D2109/10

  Land vehicles · CPC title

• G05D2105/87

  for exploration, e.g. mapping of an area · CPC title