LSTM NEURAL NETWORK BASED LONGITUDINAL VEHICLE SPEED PREDICTION FOR SLIP DETECTION

1 . A method, comprising:

receiving, by a processing device of a vehicle, a plurality of real-time measurements related to at least one current vehicle condition;

providing, by the processing device, the plurality of real-time measurements to a long short-term memory (LSTM) machine learning model;

predicting, by the processing device and using the LSTM machine learning model, a longitudinal speed of the vehicle based on the plurality of real-time measurements;

determining, by the processing device, a longitudinal slip ratio of each axle or of each wheel based on the predicted longitudinal speed; and

initiating, by the processing device based on the determination of the slip ratio, one or more vehicle actions to compensate for the slip ratio.

2 . The method of claim 1 , wherein the plurality of real-time measurements includes one or more of:

a torque measurement of at least one motor of the vehicle;

a longitudinal acceleration of the vehicle;

a front axle speed of a front axle of the vehicle; or

a rear axle speed of a rear axle of the vehicle.

3 . The method of claim 2 , wherein the longitudinal slip ratio is determined for each axle based on the predicted longitudinal speed of the vehicle provided by the LSTM machine learning model, the front axle speed, and the rear axle speed.

4 . The method of claim 2 , wherein the front axle speed and the rear axle speed are determined as 0.5× a sum of front wheel speeds and rear wheel speeds, respectively.

5 . The method of claim 1 , wherein the LSTM machine learning model includes at least one LSTM cell.

6 . The method of claim 5 , wherein the at least one LSTM cell includes:

a forget gate;

an input gate;

an update gate; and

an output gate,

wherein the update gate linearly creates new cell candidate values via a linear activation function.

7 . The method of claim 6 , further comprising:

updating, by the processing device, a cell state of the LSTM cell using the new cell candidate values;

linearly outputting, by the processing device, the updated cell state via another linear activation function; and

combining, via a sigmoid function, the output updated cell state with an output of the output gate.

8 . The method of claim 1 , wherein the one or more vehicle actions includes a torque control action or a brake control action.

9 . The method of claim 1 , wherein the LSTM machine learning model is trained using a linear regression loss function and based on ground truth vehicle speeds provided by a vehicle speed sensor to adjust various weights and biases of the LSTM machine learning model.

10 . The method of claim 9 , wherein the LSTM machine learning model is further trained using training data related to a plurality of traction surfaces.

11 . An electric vehicle, comprising:

one or more vehicle component sensors;

a memory storing a long short-term memory (LSTM) machine learning model; and

a processing device communicatively connected to the memory and the one or more vehicle component sensors, wherein the processing device is configured to:

receive a plurality of real-time measurements related to at least one current vehicle condition;

provide the plurality of real-time measurements to the LSTM machine learning model;

predict, using the LSTM machine learning model, a longitudinal speed of the electric vehicle based on the plurality of real-time measurements;

determine a longitudinal slip ratio of each axle or of each wheel based on the predicted longitudinal speed; and

initiate, based on the determination of the slip ratio, one or more vehicle actions to compensate for the longitudinal slip ratio.

12 . The electric vehicle of claim 11 , wherein the plurality of real-time measurements includes one or more of:

a torque measurement of at least one motor of the electric vehicle;

a longitudinal acceleration of the electric vehicle;

a front axle speed of a front axle of the electric vehicle; or

a rear axle speed of a rear axle of the electric vehicle.

13 . The electric vehicle of claim 12 , wherein the longitudinal slip ratio is determined for each axle based on the predicted longitudinal speed of the electric vehicle provided by the LSTM machine learning model, the front axle speed, and the rear axle speed.

14 . The electric vehicle of claim 12 , wherein the front axle speed and the rear axle speed are determined as 0.5× a sum of front wheel speeds and rear wheel speeds, respectively.

15 . The electric vehicle of claim 11 , wherein the LSTM machine learning model includes at least one LSTM cell.

16 . The electric vehicle of claim 15 , wherein the at least one LSTM cell includes:

a forget gate;

an input gate;

an update gate; and

an output gate,

wherein the update gate linearly creates new cell candidate values via a linear activation function.

17 . The electric vehicle of claim 16 , wherein the processing device is further configured to:

update a cell state of the LSTM cell using the new cell candidate values;

linearly output the updated cell state via another linear activation function; and

combine, via a sigmoid function, the output updated cell state with an output of the output gate.

18 . The electric vehicle of claim 11 , wherein the one or more vehicle actions includes a torque control action or a brake control action.

19 . The electric vehicle of claim 11 , wherein the LSTM machine learning model is trained using a linear regression loss function and based on ground truth vehicle speeds provided by a vehicle speed sensor to adjust various weights and biases of the LSTM machine learning model.

20 . The electric vehicle of claim 19 , wherein the LSTM machine learning model is further trained using training data related to a plurality of traction surfaces.