UNSURPERVISED CLASSIFICATION OF ENCOUNTERING SCENARIOS USING CONNECTED VEHICLE DATASETS

• US 20200133269A1
• Filed: 10/30/2018
• Published: 04/30/2020
• Est. Priority Date: 10/30/2018
• Status: Active Grant

• Current Assignee: Board of Regents of the University of Michigan (University of Michigan)
• Original Assignee: Board of Regents of the University of Michigan (University of Michigan)
• Inventors: Wang, Wenshuo, Ramesh, Aditya, Zhao, Ding
• Granted Patent: US 11,194,331 B2
• Time in Patent Office: Days
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G05D 1/0221 involving a learning process
• CPC Class Codes: G05D 1/0289 with means for avoiding collisions between vehicles vehicle fittings for automatically controlling speed including means for detecting potential obstacles B60K31/0008; avoiding obstacles by action on the steering system B62D; radar, sonar, lidar systems designed for anti-collision purposes G01S13/93, G01S15/93, G01S17/93
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06F 18/23 Clustering techniques
• CPC Class Codes: G06F 18/23213 with fixed number of clusters, e.g. K-means clustering
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06F 18/24133 Distances to prototypes
• CPC Class Codes: G06N 3/044 Recurrent networks, e.g. Hopfield networks
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06N 3/088 Non-supervised learning, e.g. competitive learning
• CPC Class Codes: G06V 10/82 using neural networks
• CPC Class Codes: G06V 20/13 Satellite images

Abstract

The present disclosure provides a method in a data processing system that includes at least one processor and at least one memory. The at least one memory includes instructions executed by the at least one processor to implement a driving encounter recognition system. The method includes receiving information, from one or more sensors coupled to a first vehicle, determining first trajectory information associated with the first vehicle and second trajectory information associated with a second vehicle, extracting a feature vector, providing the feature vector to a trained classifier, the classifier trained using unsupervised learning based on a plurality of feature vectors, and receiving, from the trained classifier, a classification of the current driving encounter in order to facilitate the first vehicle to perform a maneuver based on the current driving encounter.

Claims

1. A method in a data processing system comprising at least one processor and at least one memory, the at least one memory comprising instructions executed by the at least one processor to implement a driving encounter recognition system, the method comprising:

receiving an information from a one or more sensors coupled to a first vehicle;

determining, based on the information received from the one or more sensors coupled to a first vehicle, a first trajectory information associated with the first vehicle and a second trajectory information associated with a second vehicle;

extracting, based on a current driving encounter comprising the first trajectory information and the second trajectory information, a feature vector;

providing the feature vector to a trained classifier, wherein the classifier was trained using unsupervised learning based on a plurality of feature vectors corresponding to driving encounters; and

receiving, from the trained classifier, a classification of the current driving encounter in order to facilitate the first vehicle to perform a maneuver based on the current driving encounter.

2. The method of claim 1, wherein the method further comprises determining that the first vehicle and the second vehicle are within a predetermined distance of each other in order to start receiving the information.

3. The method of claim 1, wherein the method further comprises receiving the information for a predetermined time.

4. The method of claim 3, wherein the predetermined time is about 5 to about 20 seconds.

5. The method of claim 1, wherein the classifier was trained using a clustering technique.

6. The method of claim 5, wherein the classifier was trained using k-means clustering.

7. The method of claim 5, wherein the clustering technique has a number of clusters selected in order maximize between-cluster distance and minimize within-cluster distance.

8. The method of claim 1, wherein the method further comprises normalizing the first trajectory information and the second trajectory information to a predetermined number of data points.

9. The method of claim 8, wherein the predetermined number of data points is about 50 to about 400 data points.

10. The method of claim 1, wherein the feature vector is extracted using an autoencoder, and the plurality of feature vectors were extracted using the autoencoder.

11. The method of claim 10, wherein the autoencoder is one of:

a long-short term memory autoencoder, a normalized Euclidean distance long-short term memory autoencoder, or a dynamic time warping convolutional autoencoder.

12. The method of claim 1, wherein the feature vector is extracted using a distance-based formula, and the plurality of feature vectors were extracted using the distance-based formula.

13. The method of claim 12, wherein the distance-based formula uses dynamic time warping or normalized Euclidean distance.

14. A method for training an autonomous vehicle, comprising:

obtaining trajectories of a plurality of vehicles;

identifying each pair of vehicles from the plurality of vehicles with a between-vehicle-distance that is less than a threshold;

normalizing the trajectories of each pair of vehicles;

learning features of each normalized trajectory;

clustering each trajectory based on the learned features; and

training the autonomous vehicle based on the learned features.

15. The method of claim 14, wherein the clustering further comprises k-means clustering.

16. The method of claim 14, wherein the clustering further comprises clustering each trajectory into one of a plurality of clusters, the plurality of clusters comprising a number of clusters selected in order maximize between-cluster distance and minimize within-cluster distance.

17. The method of claim 14, wherein the learning further comprises learning the features of each normalized trajectory using an autoencoder selected from:

a long-short term memory autoencoder, a normalized Euclidean distance long-short term memory autoencoder, or a dynamic time warping convolutional autoencoder.

18. The method of claim 17, wherein the learning further comprises extracting features from a hidden layer of the autoencoder.

19. The method of claim 14, wherein the learning further comprises unsupervised learning based on a plurality of feature vectors corresponding to driving encounters, the plurality of feature vectors being extracted by the driving encounter feature extractor.

20. The method of claim 14, wherein the threshold is about 100 meters.