Automated control architecture that handles both grip driving and sliding
Systems and methods of autonomously controlling a vehicle across the grip driving and drift driving operating ranges, are provided. The contemplated autonomous control can be effectuated using a closed-loop control system. In some embodiments, closed-loop control may be accomplished by deriving control laws involving sideslip angle, yaw rate, wheel speed, and other vehicle states. These control laws may be used to control the vehicle in a stable drift condition.
1 . A computer-implemented method comprising:
determining a preference of a driver of a vehicle for drift driving;
obtaining first data associated with a current operational state of the vehicle and second data associated with a contextual environment in which the vehicle operates; and
based on the first data associated with the current operational state of the vehicle, the second data associated with the contextual environment in which the vehicle operates, and the determined preference for drift driving, determining to transition the vehicle from grip driving to drift driving, wherein determining to transition the vehicle from grip driving to drift driving comprises correlating the first data to a multi-dimensional graph or matrix of operational states of the vehicle partitioned into grip driving regions and drift driving regions.
2 . The computer-implemented method of claim 1 , further comprising:
effectuating the transition from grip driving to drift driving.
3 . The computer-implemented method of claim 2 , wherein the first data comprises a trajectory of the vehicle.
4 . The computer-implemented method of claim 3 , wherein effectuating the transition from grip driving to drift driving comprises:
planning a vehicle trajectory which includes a transition from grip driving to drift driving; and
executing the planned vehicle trajectory.
5 . The computer-implemented method of claim 4 , wherein executing the planned vehicle trajectory comprises:
receiving an error signal; and
converting the error signal into one or more control signals designed to reduce error.
6 . The computer-implemented method of claim 5 , wherein:
the error is a difference between the planned vehicle trajectory and vehicle trajectory determined based on the first data; and
the error signal is a function of the error.
7 . The computer-implemented method of claim 6 , wherein determining to switch the vehicle from grip driving to drift driving is based, in part, on correlating the first data associated with the current operational state of the vehicle, the second data associated with the contextual environment in which the vehicle operates, and the driver preference for drift driving, to trained machine learning models.
8 . The computer-implemented method of claim 1 , wherein the first data further comprises sideslip angle of the vehicle, linear velocity of the vehicle and yaw rate of the vehicle.
9 . The computer-implemented method of claim 1 , wherein the second data comprises road path and location of objects in proximity to the vehicle.
10 . The computer-implemented method of claim 1 , wherein the second data associated with the contextual environment in which the vehicle operates comprises at least one of:
data related to structural features of a road the vehicle is traversing;
data related to objects in proximity of a predicted trajectory of the vehicle; or
data related to ambient weather conditions in which the vehicle operates.
11 . The computer-implemented method of claim 10 , wherein the data related to the structural features of the road the vehicle is traversing comprises at least one of:
data related to a path of the road;
data related to a coefficient of friction between the vehicle's tires and a surface of the road; or
data related bank angle of the road.
12 . A computer-implemented method comprising:
receiving first data associated with a current operational state of a vehicle and second data associated with a contextual environment in which the vehicle operates;
based on the first data and the second data, planning a trajectory for the vehicle which involves a transition from grip driving to drift driving, wherein the planning comprises correlating the first data to a multi-dimensional graph or matrix of operational states of the vehicle partitioned into grip driving regions and drift driving regions; and
executing the planned trajectory for the vehicle.
13 . The computer-implemented method of claim 12 , wherein the first data comprises a sensed trajectory of the vehicle.
14 . The computer-implemented method of claim 13 , wherein executing the planned trajectory for the vehicle comprises:
receiving an error signal; and
converting the error signal into one or more control signal designed to reduce error.
15 . The computer-implemented method of claim 14 , wherein:
the error is a difference between the planned trajectory for the vehicle and the sensed trajectory of the vehicle; and
the error signal is a function of the error.
16 . The computer-implemented method of claim 15 , wherein planning the trajectory for the vehicle which includes the transition from grip driving to drift driving is based, in part, on correlating the first data and the second data to trained machine learning models.
17 . The computer-implemented method of claim 12 , wherein the computer-implemented method is performed by a closed-loop ECU in the vehicle.
18 . The computer-implemented method of claim 12 , wherein:
the grip driving regions comprise operational state regions in which the vehicle is operated within a peak frictional force of the vehicle's tires; and
the drift driving regions comprise operational state regions in which the vehicle is operated beyond the peak frictional force of the vehicle's tires.
19 . A vehicle comprising:
one or more processors including machine executable instructions in non-transitory memory to cause the vehicle to:
receive a data associated with a current operational state of the vehicle;
determine to transition the vehicle from grip driving to drift driving by correlating the data to a multi-dimensional graph or matrix of operational states of the vehicle partitioned into grip driving regions in which the vehicle is operated within a peak frictional force of the vehicle's tires and drift driving regions in which the vehicle is operated beyond the peak frictional force of the vehicle's tires; and
effectuate the transition between grip driving and drift driving by sending control signals to at least one of a steering-by-wire system, a throttle-by-wire system, a clutch-by-wire system, and a brake-by-wire system, each actualizing sent control signals.
20 . The vehicle of claim 19 , wherein the control signals sent to the clutch-by-wire system comprise instructions to disengage and then rapidly reengage the clutch in order to effectuate the transition between grip driving and drift driving.
21 . The vehicle of claim 20 , wherein the control signals sent to the brake-by-wire system comprise instructions to apply a parking brake while steering into a turn, in order to effectuate the transition between grip driving and drift driving.