Methods and systems for driver in the loop curve velocity control
Methods and systems for providing driving assistance in a vehicle. In one embodiment, a method includes: determining, by a processor, a trajectory of the vehicle along a roadway; determining, by the processor, a confidence score based on a predicted lateral acceleration and an actual lateral acceleration at a point along the trajectory; determining, by the processor, longitudinal velocity data based on the confidence score; and generating, by the processor, control signals to vehicle actuators to control the vehicle based on the longitudinal velocity data.
1 . A method for providing driving assistance in a vehicle, the vehicle comprising an autonomous vehicle, and the method comprising:
obtaining, via one or more cameras of the vehicle, camera data as to lane markings on a roadway in which the vehicle is travelling;
determining, by a processor of the vehicle, a trajectory of the vehicle along the roadway based on a location of the lane markings and a type of the lane markings;
determining, by the processor, one or more radial points along the trajectory, along with one or more look ahead points along the trajectory ahead of the vehicle based on the one or more radial points:
determining, by the processor, a confidence score based on a predicted lateral acceleration and an actual lateral acceleration at the one or more look ahead points along the trajectory;
determining, by the processor, longitudinal velocity data based on the confidence score; and
generating, by the processor, control signals to vehicle actuators to control the vehicle based on the longitudinal velocity data and further based on the confidence score, including by:
automatically providing, via the processor, a first level of acceleration for the vehicle based on the longitudinal velocity being shaped according to a velocity profile that is optimum, when it is determined that the confidence score is within a high range:
automatically providing, via the processor, a second level of acceleration for the vehicle based on the longitudinal velocity being shaped according to the velocity profile being partially limited, when it is determined that the confidence score is within a medium range that is less than the high range; and
automatically providing, via the processor, a third level of acceleration for the vehicle based on the longitudinal velocity being shaped according to the velocity profile that is fully limited, when it is determined that the confidence score is within a low range that is less than the medium range.
2 . The method of claim 1 , wherein when the lane markings are not identified from the camera data, the determining the confidence score comprises decreasing the confidence score.
3 . The method of claim 1 , wherein the determining the confidence score is based on a difference between the predicted lateral acceleration and the actual lateral acceleration at the one or more look ahead points along the trajectory, wherein when the difference is above a threshold, the confidence score is decreased, and wherein when the difference is below the threshold, the confidence score is increased.
4 . The method of claim 1 , further comprising determining the actual lateral acceleration based on steering data at the one or more look ahead points.
5 . The method of claim 1 , wherein the determining the longitudinal velocity data is based on a velocity profile defined by a current velocity, a set velocity, and a desired velocity.
6 . The method of claim 1 , wherein the radial points, denoted as (r0, r1, and r2), are determined by the processor by sweeping the trajectory based on the following relationship:
r
=
❘
"\[LeftBracketingBar]"
y
(
x
¨
l
a
)
❘
"\[RightBracketingBar]"
[
1
+
(
y
(
x
.
l
a
)
)
2
]
3
/
2
,
wherein y (x)=c 0 +c 1 x+c 2 x 2 +c 3 x 3 , and wherein la represents look ahead.
7 . The method of claim 1 , wherein the lateral acceleration is predicted by the processor based on the relationship:
a
y
=
V
x
(
t
)
2
r
,
where r represents the curvature at the one or more look ahead points, and V x (t) represents the longitudinal velocity at a time t.
8 . The method of claim 1 , wherein the longitudinal velocity is computed by the processor based on the relationship:
V
x
(
t
)
=
∫
0
t
la
a
x
(
t
)
dt
+
C
,
wherein ax represents a longitudinal acceleration, and wherein C represents a compensation value determined from a currently applied velocity profile.
9 . The method of claim 1 , further comprising:
determining, via the processor, if any compensation of the lateral acceleration is needed based on the longitudinal velocity profile being executed.
10 . The method of claim 9 , further comprising: when the current longitudinal velocity profile requires longitudinal deceleration due to another vehicle being detected in the lane, the predicted lateral acceleration is compensated via the processor to account for the expected deceleration.
11 . A system in a vehicle for providing driving assistance, the vehicle comprising an autonomous vehicle, and the system comprising:
one or more cameras of the vehicle that are configured to obtain camera data as to lane markings on a roadway in which the vehicle is travelling; and
a processor of the vehicle that is coupled to the one or more cameras and that is configured to:
determine a trajectory of the vehicle along the roadway based on a location of the lane markings and a type of the lane markings;
determine one or more radial points along the trajectory, along with one or more look ahead points along the trajectory ahead of the vehicle based on the one or more radial points;
determine a confidence score based on a predicted lateral acceleration and an actual lateral acceleration at the one or more look ahead points along the trajectory;
determine longitudinal velocity data based on the confidence score; and
generate control signals to vehicle actuators to control the vehicle based on the longitudinal velocity data and further based on the confidence score, including by:
automatically providing, via the processor, a first level of acceleration for the vehicle based on the longitudinal velocity being shaped according to a velocity profile that is optimum, when it is determined that the confidence score is within a high range;
automatically providing, via the processor, a second level of acceleration for the vehicle based on the longitudinal velocity being shaped according to the velocity profile being partially limited, when it is determined that the confidence score is within a medium range that is less than the high range; and
automatically providing, via the processor, a third level of acceleration for the vehicle based on the longitudinal velocity being shaped according to the velocity profile that is fully limited, when it is determined that the confidence score is within a low range that is less than the medium range.
12 . The system of claim 11 , wherein when the lane markings are not identified from the camera data, the processor is configured to determine the confidence score by decreasing the confidence score.
13 . The system of claim 11 , wherein the processor is configured to determine the confidence score based on a difference between the predicted lateral acceleration and the actual lateral acceleration at the one or more look ahead points along the trajectory, wherein when the difference is above a threshold, the processor is configured to decrease the confidence score, and wherein when the difference is below the threshold, the processor is configured to increase the confidence score.
14 . The system of claim 11 , wherein the processor is further configured to determine the actual lateral acceleration based on steering data at the one or more look ahead points.
15 . The system of claim 11 , wherein the processor is configured to determine the longitudinal velocity data based on a plurality of velocity profiles, each defined by a current velocity, a set velocity, and a desired velocity, determine the longitudinal velocity data based on a comparison of the confidence score to a plurality of ranges, and select a velocity profile from the plurality of velocity profiles based on the comparison.
16 . A vehicle comprising:
a sensor system configured to sense an environment of the vehicle, the sensor system including one or more cameras that are configured to obtain camera data as to lane markings on a roadway in which the vehicle is travelling;
an actuator system; and
a controller for implementing a driver assistance system, the controller comprising a processor that is coupled to the one or more cameras and that is configured to:
determine a trajectory of the vehicle along the roadway based on a location of the lane markings and a type of the lane markings;
determine one or more radial points along the trajectory, along with one or more look ahead points along the trajectory ahead of the vehicle based on the one or more radial points;
determine a confidence score based on a predicted lateral acceleration and an actual lateral acceleration at the one or more look ahead points along the trajectory;
determine longitudinal velocity data based on the confidence score; and
generate control signals to vehicle actuators to control the vehicle based on the longitudinal velocity data and further based on the confidence score, including by:
automatically providing, via the processor, a first level of acceleration for the vehicle based on the longitudinal velocity being shaped according to a velocity profile that is optimum, when it is determined that the confidence score is within a high range;
automatically providing, via the processor, a second level of acceleration for the vehicle based on the longitudinal velocity being shaped according to the velocity profile being partially limited, when it is determined that the confidence score is within a medium range that is less than the high range; and
automatically providing, via the processor, a third level of acceleration for the vehicle based on the longitudinal velocity being shaped according to the velocity profile that is fully limited, when it is determined that the confidence score is within a low range that is less than the medium range.