Systems and methods for dynamically adjusting a vehicle trajectory according to deviations of a driver from expected inputs

Patent metadata

Field	Value
Publication number	US-10059336-B2
Application number	US-201715400580-A
Country	US
Kind code	B2
Filing date	Jan 6, 2017
Priority date	Jan 6, 2017
Publication date	Aug 28, 2018
Grant date	Aug 28, 2018

Abstract

System, methods, and other embodiments described herein relate to dynamically adjusting a vehicle trajectory according to driver deviations. In one embodiment, a method includes generating expected inputs for controlling the vehicle along a segment of a roadway on which the vehicle is traveling by analyzing a present context of the vehicle using a driver model. The expected inputs as controls for operating the vehicle to maintain a preferred trajectory along the segment. The method includes computing a variance of received inputs from the expected inputs by comparing the expected inputs with the received inputs. The method includes controlling the vehicle based, at least in part, on the expected inputs when the deviation score satisfies a deviation threshold indicating that the received inputs are inadequate to maintain the vehicle along the preferred trajectory.

First claim

What is claimed is:

1. An adaptive control system of a vehicle, comprising:
one or more processors;
a memory communicably coupled to the one or more processors and storing:
a deviation module including instructions that when executed by the one or more processors cause the one or more processors to generate expected inputs for controlling the vehicle along a segment of a roadway on which the vehicle is traveling by analyzing a present context of the vehicle using a driver model, wherein the expected inputs are controls for operating the vehicle to maintain a preferred trajectory along the segment, wherein the preferred trajectory defines a path along the segment of the roadway to safely operate the vehicle, wherein the deviation module maintains the expected inputs in a queue for successive points along the segment,
wherein the deviation module includes instructions to compute a variance of received inputs from the expected inputs by comparing the expected inputs with the received inputs, wherein the received inputs are electronic control signals received in response to a driver operating one or more input devices of the vehicle, and
wherein the deviation module includes instructions to update the preferred trajectory to account for the variance including the expected inputs in the queue and to adjust the preferred trajectory to provide for rollout of the vehicle past a current location; and
a control module including instructions that when executed by the one or more processors cause the one or more processors to control the vehicle based, at least in part, on the expected inputs when the variance satisfies a deviation threshold indicating that the received inputs are inadequate to maintain the vehicle along the preferred trajectory for the segment of the roadway.

2. The adaptive control system of claim 1 , wherein the control module includes instructions to control the vehicle including instructions to at least partially modify the received inputs using the expected inputs according to a degree of deviation from the expected inputs as indicated by the variance, wherein the control module includes instructions to at least partially modify the received inputs including instructions to blend the received inputs together with the expected inputs into a control output that at least partially automates control of the vehicle,
wherein the expected inputs include at least a steering position, a brake pedal position, and an accelerator pedal position, and wherein the one or more input devices include a steering wheel, a brake pedal, and an accelerator pedal of the vehicle.

3. The adaptive control system of claim 1 , wherein the control module includes instructions to dynamically select the deviation threshold according to at least the present context and a driver profile that indicates a level of driving skill for the driver, and wherein the control module includes instructions to determine that the deviation threshold is satisfied when the variance indicates that the received inputs will control the vehicle to deviate from the preferred trajectory to an extent that increases risks to the vehicle,
wherein the control module includes the instruction to control the vehicle including instructions to ignore the received inputs and control the vehicle according to the expected inputs when the variance satisfies a maximum threshold, and wherein the maximum threshold indicates a maximum variance at which the received inputs are inadequate for safely controlling the vehicle.

4. The adaptive control system of claim 1 , wherein the driver model is a parameterized function that accepts inputs correlating with the present context including sensor inputs, and wherein parameters within the driver model are defined according to learned probabilities accumulated from analyzing sensor inputs from driving within similar contexts to the present context.

5. The adaptive control system of claim 1 , wherein the deviation module includes the instructions to generate the expected inputs including instructions to continuously adjust the preferred trajectory and update the expected inputs in the queue to account for changes in position and velocity embodied by the variance.

6. The adaptive control system of claim 1 , wherein the deviation module includes instructions to compute the variance as a deviation score to characterize an attentiveness of the driver and an ability of the driver to maintain the preferred trajectory, and wherein the control module includes instructions to select the deviation threshold with a dead band for the deviation score where the control module controls the vehicle using the received inputs without modification.

7. The adaptive control system of claim 1 , wherein the deviation module includes instructions to collect sensor inputs from one or more sensors within the vehicle to generate the present context that is comprised of information about the segment of the roadway, surroundings of the vehicle, and current operating characteristics of the vehicle, and wherein the deviation module includes instructions to collect the sensor inputs including instructions to collect data from at least a global position system (GPS) sensor and a radar.

8. The adaptive control system of claim 1 , wherein the segment of the roadway is a portion of a predicted route of the vehicle that extends a defined distance ahead of the vehicle, and wherein the deviation module includes instructions to determine the predicted route from analyzing the present context in relation to past trips of the vehicle.

9. A non-transitory computer-readable medium storing instructions that when executed by one or more processors cause the one or more processors to:
generate expected inputs for controlling a vehicle along a segment of a roadway on which the vehicle is traveling by analyzing a present context of the vehicle using a driver model, wherein the expected inputs are controls for operating the vehicle to maintain a preferred trajectory along the segment, wherein the preferred trajectory defines a path along the segment of the roadway to safely operate the vehicle, and wherein the instructions to generate the expected inputs maintain the expected inputs in a queue for successive points along the segment;
compute a variance of received inputs from the expected inputs by comparing the expected inputs with the received inputs, wherein the received inputs are electronic control signals received in response to the driver operating one or more input devices of the vehicle, and wherein the instructions to generate the expected inputs include instructions to update the preferred trajectory to account for the variance including the expected inputs in the queue and to adjust the preferred trajectory to provide for rollout of the vehicle past a current location; and
control the vehicle according to the expected inputs when the variance satisfies a deviation threshold indicating that the received inputs are inadequate to maintain the vehicle along the preferred trajectory for the segment of the roadway.

10. The non-transitory computer-readable medium of claim 9 , wherein the instructions to control the vehicle include instructions to at least partially modify the received inputs using the expected inputs according to a degree of deviation from the expected inputs as indicated by the variance, wherein the instructions to at least partially modify the received inputs include instructions to blend the received inputs together with the expected inputs into a control output that at least partially automates control of the vehicle,
wherein the expected inputs include at least a steering position, a brake pedal position, and an accelerator pedal position, and wherein the one or more

Assignees

• Toyota Res Inst Inc

Inventors

• Mcgill Jr Stephen G

Classifications

• B60W60/0013

  specially adapted for occupant comfort · CPC title

• B60W30/10 Primary

  Path keeping {(cruise control for automatically following a preceding vehicle B60W30/165)} · CPC title

• B60W2710/20

  Steering systems · CPC title

• B60W2510/20

  Steering systems · CPC title

• B60W2540/10

  Accelerator pedal position · CPC title