US 11,760,349 B2 · Parallel computing method for man-machine coordinated steering control of smart vehicle based on risk assessment

Abstract

A parallel computing method for man-machine coordinated steering control of a smart vehicle based on risk assessment is provided, comprising the following steps: building a lateral kinetic equation model of a vehicle; building a target function by targeting at minimizing an offset distance of a vehicle driving track from a lane center line and making a change in a front wheel steering angle and a longitudinal acceleration as small as possible in a driving process; building a parallel computing architecture of a prediction model and the target function, and employing a triggering parallel computing method; solving and computing a gradient with a manner of back propagation and using a gradient descent method to obtain an optimal control amount of the front wheel steering angle and an optimal control amount of the longitudinal acceleration; and computing a driving weight, obtaining a desired front wheel steering angle and completing real time control.

A parallel computing method for a man-machine coordinated steering control of a smart vehicle based on a risk assessment, wherein the parallel computing method comprises the following steps:

S1:
building a lateral kinetic equation model of a vehicle and obtaining a system discrete model of the vehicle;
S2:
taking a road center line as an ideal driving track to minimize an offset distance of a vehicle driving track from a lane center line, and building a target function by targeting at making a change in a front wheel steering angle and a longitudinal acceleration as small as possible in a driving process;
S3:
building a parallel computing architecture of a prediction model and the target function, and employing a triggering parallel computing method by the parallel computing architecture to synchronously compute the prediction model and the target function;
S4:
solving and computing a gradient with a manner of a back propagation and using a gradient descent method to optimize a control amount of the front wheel steering angle and the control amount of the longitudinal acceleration to obtain an optimal control amount of the front wheel steering angle and the optimal control amount of the longitudinal acceleration;
and
S5:
computing a driving weight based on fuzzy logic, obtaining a desired front wheel steering angle according to the driving weight and completing a real time control over man-machine coordinated steering of the smart vehicle
in the parallel computing architecture of the prediction model and the target function in the step S3, a symbol indicating that solution of the prediction model and the target function in a present computing step has been completed is used as the symbol of starting a prediction computing at a next step, thereby realizing a parallel computing of the prediction model and the target function;
a recurrence relationship between the lateral kinetic equation model and the target function is:
i
=
0
J
0
=
∑
i
=
0
N
-
1
Δ
⁢
U
(
k
+
i
|
k
)
⁢
R
⁢
Δ
⁢
U
(
k
+
i
|
k
)
T
x
(
k
+
1
|
k
)
=
f
⁡
(
x
(
k
|
k
)
,
U
(
k
|
k
)
)
i
=
1
J
1
=
J
0
+
(
Y
(
k
+
1
|
k
)
-
r
(
k
+
1
)
)
⁢
Q
⁡
(
Y
(
k
+
1
|
k
)
-
r
(
k
+
1
)
)
T
x
(
k
+
2
|
k
)
=
f
⁢
(
x
(
k
+
1
|
k
)
,
U
(
k
+
1
|
k
)
)
⋮
i
=
N
-
1
J
N
-
1
=
J
N
-
2
+
(
Y
(
k
+
N
-
1
|
k
)
-
r
(
k
+
1
)
)
⁢
Q
⁡
(
Y
(
k
+
N
-
1
|
k
)
-
r
(
k
+
1
)
)
T
x
(
k
+
N
|
k
)
=
f
⁢
(
x
(
k
+
N
+
1
|
k
)
,
U
(
k
+
N
-
1
|
k
)
)
i
=
N
J
=
J
N
-
1
+
(
Y
(
k
+
N
|
k
)
-
r
(
k
+
1
)
)
⁢
P
⁡
(
Y
(
k
+
N
|
k
)
-
r
(
k
+
1
)
)
T
,
wherein J is the target function to be optimized, f is a lateral kinetic equation model, P is a weight matrix of a terminal, Q is a state weight matrix, R is a weight matrix of the control amount, ΔU(k+i|k) is a changing amount of the control amount in a step i at a moment k, x(k+i|k) is a state amount prediction value in the step i at the moment k, U(k+i|k) is a control amount prediction value in the step i at the moment k, and r(k+1) is a yaw velocity in a step k+1;
Y is a vehicle lateral displacement.

293 more elements

Parallel computing method for man-machine coordinated steering control of smart vehicle based on risk assessment

Life of this patent

Parallel computing method for man-machine coordinated steering control of smart vehicle based on risk assessment

Life of this patent

Abstract

Claims9