Estimating risk of a yaw instability of a vehicle
A computer-implemented method for handling yaw instability of a vehicle is provided. The method includes a use of separate prediction models for a short-term time period and a long-term time period for predicting future steering angle information and a future longitudinal motion of the vehicle for the respective periods. The method also includes, based on the respective predicted future steering angle information and future longitudinal motion of the vehicle, estimating a respective short-term and long-term risk for yaw instability of the vehicle. The method also includes, on the basis of the estimated short-term risk and long-term risk, respectively, determining whether or not to trigger an alert and/or to trigger a preventive action for preventing a yaw instability of the vehicle.
1 . A computer-implemented method for handling yaw instability of a vehicle, comprising:
by a processor device of a computer system, using separate prediction models for a short-term time period and a long-term time period for predicting future steering angle information for the short-term time period, future steering angle information for the long-term time period, a future longitudinal motion of the vehicle for the short-term time period and a future longitudinal motion of the vehicle for the long-term time period, wherein the short-term time period is shorter than the long-term time period,
wherein predicting the future steering angle information and respective future longitudinal motion of the vehicle for the short-term time period is based on current and/or historical steering angle information and/or longitudinal motions of the vehicle, and wherein predicting the future steering angle information and/or the future longitudinal motion for the short-term time period comprises estimating a rate of change in the current steering angle information based at least partly on the historical steering angle information and/or a rate of change in the current longitudinal motion based at least partly on the historical longitudinal motion of the vehicle, and predicting the future steering angle information and/or the future longitudinal motion based on the estimated rate of change,
by the processor device, based on the respective predicted future steering angle information and future longitudinal motion of the vehicle, estimating a respective short-term and long-term risk for yaw instability of the vehicle, and
by the processor device, on the basis of the estimated short-term risk and long-term risk, respectively, determining whether or not to trigger an alert and/or to trigger a preventive action for preventing a yaw instability of the vehicle.
2 . A computer-implemented method according to claim 1 , wherein predicting the future steering angle information and/or the future longitudinal motion for the short-term time period comprises predicting that the future steering angle information and/or the future longitudinal motion is within a predefined range of the current and historical steering angle information and/or longitudinal motion.
3 . A computer-implemented method according to claim 1 , wherein predicting the future steering angle information and the respective future longitudinal motion of the vehicle for the long-term time period is based at least partly on road map data for one or more road segments which the vehicle is expected to drive on.
4 . A computer-implemented method according to claim 3 , wherein the road map data indicates a road curvature and/or a slope for the one or more road segments.
5 . A computer-implemented method according to claim 3 , wherein predicting the future steering angle information and/or respective future longitudinal motion of the vehicle for the long-term time period is based at least partly on a pre-defined behavior of the vehicle and/or based at least partly on a pre-defined behavior of a driver of the vehicle, when the vehicle is driving on the one or more road segments indicated by the road map data.
6 . A computer-implemented method according to claim 3 , wherein predicting the future steering angle information of the vehicle for the long-term time period comprises predicting a distance between the vehicle and a road centerline, and predicting a future vehicle orientation of the vehicle.
7 . A computer-implemented method according to claim 1 , wherein the vehicle comprises at least one trailer, and wherein estimating a respective short-term and long-term risk for yaw instability of the vehicle comprises estimating a respective short-term and long-term risk for jack-knifing and/or trailer swing of the vehicle.
8 . A computer-implemented method according to claim 1 , wherein determining whether or not to trigger the alert and/or to trigger the preventive action is based on comparing the respective short-term and long-term risk to at least one respective threshold.
9 . A computer-implemented method according to claim 8 , wherein each of the respective short-term and long-term risk is compared with a respective warning threshold, and wherein it is determined to trigger the alert when any one or both of the respective warning thresholds are exceeded.
10 . A computer-implemented method according to claim 8 , wherein each of the respective short-term and long-term risk is compared with a respective intervention threshold, and wherein it is determined to trigger the preventive action when any one or both of the respective intervention thresholds are exceeded.
11 . A computer-implemented method according to claim 1 , further comprising:
by the processor device, when determined to trigger an alert, triggering the alert, wherein the alert indicates that the vehicle is in risk of yaw instability.
12 . A computer-implemented method according to claim 11 , wherein an alert level of the triggered alert is based on a combination of the short-term risk and the long-term risk.
13 . A computer-implemented method according to claim 1 , further comprising:
by the processor device, when determined to trigger a preventive action, triggering the preventive action, which preventive action causes the vehicle to prevent a yaw instability of the vehicle.
14 . A computer-implemented method according to claim 13 , wherein triggering the preventive action causes the vehicle to adjust a steering wheel angle and/or a longitudinal motion of the vehicle.
15 . A computer-implemented method according to claim 13 , wherein triggering the preventive action causes the vehicle to reduce a speed of the vehicle.
16 . A computer-implemented method according to claim 13 , wherein triggering the preventive action comprises:
when a high short term risk is estimated, re-distributing a brake force and/or propulsion force of the vehicle, but
when a high long term risk is estimated and a low short term risk is estimated, decreasing a speed of the vehicle, or preventing an increase of speed of the vehicle.
17 . A computer-implemented method according to claim 13 , wherein triggering the preventive action comprises:
when a high short term risk for jack-knifing is estimated, increase brake force of at least one trailer of the vehicle, but
when a high short term risk for a trailer swing is estimated, decrease brake force of the at least one trailer of the vehicle.
18 . A computer-implemented method according to claim 1 , wherein the separate prediction models for the short-term time period and the long-term time period further predicts a future lateral motion for the short-term period, and a future lateral motion for the long-term period, and wherein estimating the respective short-term and long-term risk for yaw instability of the vehicle is further based on the respective future lateral motion.
19 . A computer-implemented method according to claim 1 , wherein the separate prediction models for the short-term time period and the long-term time period further predicts a future yaw motion for the short-term period and a future yaw motion for the long-term period, and wherein estimating the respective short-term and long-term risk for yaw instability of the vehicle is based on the respective future yaw motion.
20 . A vehicle comprising a processor device configured to perform the method of claim 1 .
21 . A vehicle according to claim 20 comprising at least one trailer.
22 . A computer program product comprising program code for performing, when executed by the processor device, the method of claim 1 .
23 . A control system comprising one or more control units configured to perform the method according to claim 1 .
24 . A non-transitory computer-readable storage medium comprising instructions, which when executed by the processor device, cause the processor device to perform the method of claim 1 .