ST-graph learning based decision for autonomous driving vehicle

1. A computer-implemented method to determine a path trajectory for an autonomous driving vehicle (ADV), the method comprising:

generating a station-time (ST) graph based on perception data obtained from one or more sensors of the ADV, the ST graph representing potential locations of an obstacle at different points in time;

obtaining a tensor based on the ST graph, the tensor including a plurality of layers, the plurality of layers including a first layer having data representing one or more obstacles on a path in which the ADV is moving;

applying a machine-learning model to the plurality of layers of the tensor to generate a plurality of numerical values, the plurality of numerical values defining a potential path trajectory of the ADV; and

determining a path trajectory of the ADV based on the plurality of numerical values.

2. The method of claim 1 , wherein the plurality of layers includes a second layer, the second layer having data representing one or more traffic rules.

3. The method of claim 2 , wherein the plurality of layers includes a third layer, the third layer having data representing one or more curvatures of the path in which the ADV is moving.

4. The method of claim 1 , wherein the plurality of numerical values includes a probability distribution.

5. The method of claim 4 , wherein the probability distribution includes a plurality of cells, each cell representing a probability that the ADV moves to a position as a function of time.

6. The method of claim 3 , wherein the machine-learning model includes a convolutional neural network.

7. The method of claim 6 , wherein the convolutional neural network outputs the plurality of numerical values.

8. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations, the operations comprising:

generating a station-time (ST) graph based on perception data obtained from one or more sensors of an autonomous driving vehicle (ADV), the ST graph representing locations of an obstacle at different points in time;

obtaining a tensor based on the ST graph, the tensor including a plurality of layers, the plurality of layers including a first layer having data representing one or more obstacles on a path in which ADV is moving;

applying a machine-learning model to the plurality of layers of the tensor to generate a plurality of numerical values, the plurality of numerical values defining a potential path trajectory of the ADV; and

determining a path trajectory of the ADV based on the plurality of numerical values.

9. The non-transitory machine-readable medium of claim 8 , wherein the plurality of layers includes a second layer, the second layer having data representing one or more traffic rules.

10. The non-transitory machine-readable medium of claim 9 , wherein the plurality of layers includes a third layer, the third layer having data representing one or more curvatures of the path in which the ADV is moving.

11. The non-transitory machine-readable medium of claim 8 , wherein the plurality of numerical values includes a probability distribution.

12. The non-transitory machine-readable medium of claim 11 , wherein the probability distribution includes a plurality of cells, each cell representing a probability that the ADV moves to a position as a function of time.

13. The non-transitory machine-readable medium of claim 10 , wherein the machine-learning model includes a convolutional neural network.

14. The non-transitory machine-readable medium of claim 13 , wherein the convolutional neural network outputs the plurality of numerical values.

15. A data processing system for an autonomous driving vehicle (ADV), the data processing system comprising:

a processor; and

a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations, the operations including:

generating a station-time (ST) graph based on perception data obtained from one or more sensors of the ADV, the ST graph representing locations of an obstacle at different points in time,

obtaining a tensor based on the ST graph, the tensor including a plurality of layers, the plurality of layers including a first layer having data representing one or more obstacles on a path in which the ADV is moving,

applying a machine-learning model to the plurality of layers of the tensor to generate a plurality of numerical values, the plurality of numerical values defining a potential path trajectory of the ADV, and

determining a path trajectory of the ADV based on the plurality of numerical values.

16. The data processing system of claim 15 , wherein the plurality of layers includes a second layer, the second layer having data representing one or more traffic rules.

17. The data processing system of claim 16 , wherein the plurality of layers includes a third layer, the third layer having data representing one or more curvatures of the path in which the ADV is moving.

18. The data processing system of claim 15 , wherein the plurality of numerical values includes a probability distribution.

19. The data processing system of claim 18 , wherein the probability distribution includes a plurality of cells, each cell representing a probability that the ADV moves to a position as a function of time.

20. The data processing system of claim 17 , wherein the machine-learning model includes a convolutional neural network and the convolutional neural network outputs the plurality of numerical values.