Performing autonomous path navigation using deep neural networks
A method, computer readable medium, and system are disclosed for performing autonomous path navigation using deep neural networks. The method includes the steps of receiving image data at a deep neural network (DNN), determining, by the DNN, both an orientation of a vehicle with respect to a path and a lateral position of the vehicle with respect to the path, utilizing the image data, and controlling a location of the vehicle, utilizing the orientation of the vehicle with respect to the path and the lateral position of the vehicle with respect to the path.
1. A method, comprising:
receiving image data at a deep neural network (DNN);
determining, by the DNN, both an orientation of a vehicle with respect to a path and a lateral position of the vehicle with respect to the path, utilizing the image data; and
controlling a location of the vehicle, utilizing the orientation of the vehicle with respect to the path and the lateral position of the vehicle with respect to the path.
2. The method of claim 1 , wherein the image data is one or more of optical data, infrared data, light detection and ranging (LIDAR) data, radar data, depth data, and sonar data.
3. The method of claim 1 , wherein the DNN includes a supervised classification network.
4. The method of claim 1 , wherein the DNN implements a loss function.
5. The method of claim 1 , wherein the orientation with respect to the path includes a probability that a vehicle is currently facing left with respect to the path, a probability that a vehicle is currently facing right with respect to the path, and a probability that a vehicle is currently facing straight with respect to the path.
6. The method of claim 1 , wherein the lateral position with respect to the path includes a probability that a vehicle is currently shifted left with respect to the path, a probability that a vehicle is currently shifted right with respect to the path, and a probability that a vehicle is centered with respect to the path.
7. The method of claim 1 , wherein the orientation and lateral position are determined in real-time within the vehicle.
8. The method of claim 1 , wherein controlling the location of the vehicle includes converting the orientation of the vehicle with respect to the path and the lateral position of the vehicle with respect to the path into steering directions.
9. The method of claim 1 , wherein the DNN controls directional stability by utilizing predictions with a reduced confidence.
10. The method of claim 1 , wherein a second DNN performs object detection within the path.
11. The method of claim 1 , wherein a third DNN performs obstacle detection associated with the path.
12. A system comprising:
a processor that is configured to:
receive image data at a deep neural network (DNN);
determine, by the DNN, both an orientation of a vehicle with respect to a path and a lateral position of the vehicle with respect to the path, utilizing the image data; and
control a location of the vehicle, utilizing the orientation of the vehicle with respect to the path and the lateral position of the vehicle with respect to the path.
13. The system of claim 12 , wherein the image data is one or more of optical data, infrared data, light detection and ranging (LIDAR) data, radar data, depth data, and sonar data.
14. The system of claim 12 , wherein the DNN includes a supervised classification network.
15. The system of claim 12 , wherein the DNN implements a loss function.
16. The system of claim 12 , wherein the orientation with respect to the path includes a probability that a vehicle is currently facing left with respect to the path, a probability that a vehicle is currently facing right with respect to the path, and a probability that a vehicle is currently facing straight with respect to the path.
17. The system of claim 12 , wherein the lateral position with respect to the path includes a probability that a vehicle is currently shifted left with respect to the path, a probability that a vehicle is currently shifted right with respect to the path, and a probability that a vehicle is centered with respect to the path.
18. The system of claim 12 , wherein the orientation and lateral position are determined in real-time within the vehicle.
19. The system of claim 12 , wherein controlling the location of the vehicle includes converting the orientation of the vehicle with respect to the path and the lateral position of the vehicle with respect to the path into steering directions.
20. A computer-readable storage medium storing instructions that, when executed by a processor, causes the processor to perform steps comprising:
receiving image data at a deep neural network (DNN);
determining, by the DNN, both an orientation of a vehicle with respect to a path and a lateral position of the vehicle with respect to the path, utilizing the image data; and
controlling a location of the vehicle, utilizing the orientation of the vehicle with respect to the path and the lateral position of the vehicle with respect to the path.