Autonomous automotive vehicle lateral motion control system

Abstract

An autonomous vehicle (101) lateral motion control system (100), comprising: a trajectory planner (102) configured to generate a target trajectory for the vehicle); and a trajectory controller (104) configured to receive the target trajectory from the trajectory planner and generate as an output a steering control signal for controlling the lateral motion of the vehicle. The trajectory controller comprises a control circuit (104a), the control circuit comprising one or more neural network adaptive controllers (110, 112, 114). Each neural network adaptive controller comprises: a feedback loop controller (116) which receives an input signal dependent on a parameter of the target trajectory and which is configured to minimize an error value indicative of the difference between the actual trajectory of the vehicle and the input signal based on one or more of a P gain, I gain and D gain term; and a neural network (118) configured to determine one or more of the P gain, I gain and the D gain terms used by the feedback loop controller.

Claims

1. An autonomous vehicle lateral motion control system, comprising:a trajectory planner configured to generate a target trajectory for the vehicle; anda trajectory controller configured to receive the target trajectory from the trajectory planner and generate as an output a steering control signal for controlling the lateral motion of the vehicle,wherein the trajectory controller comprises a control circuit, the control circuit comprising one or more neural network adaptive controllers, each comprising:a feedback loop controller which receives an input signal dependent on a parameter of the target trajectory and which is configured to minimise an error value indicative of the difference between the actual trajectory of the vehicle and the input signal based on one or more of a P gain, I gain and D gain term; anda neural network configured to determine one or more of the P gain, I gain and the D gain terms used by the feedback loop controller.

2. A motion control system according to claim 1, wherein the one or more neural network adaptive controllers include a lane position neural network adaptive controller configured to perform one or more of P, I, and D control of the lane position of the trajectory of the vehicle.

3. A motion control system according to claim 1 or claim 2, wherein the one or more neural network adaptive controllers include a course angle neural network adaptive controller configured to perform one or more of P, I, and D control of the course angle of the trajectory of the vehicle.

4. A motion control system according to claim 2 and claim 3, wherein:the lane position neural network adaptive controller is configured to receive as an input a target lane position parameter and generate an output control signal;the course angle neural network adaptive controller is configured to receive as an input a sum of the lane position neural network adaptive controller output control signal and a target course angle parameter.

5. A motion control system according to any preceding claim, wherein the trajectory controller further comprises a curvature controller configured to perform one or more of P, I, and D control of the curvature of the trajectory of the vehicle.

6. A motion control system according to claim 5, wherein the curvature controller uses pre-determined and / or vehicle motion variable dependent P gain, I gain and / or D gain terms.

7. A motion control system according to claim 5, wherein the curvature controller is a neural network adaptive controller having a neural network configured to provide P gain, I gain and / or D gain terms.

8. A motion control system according to any of claims to 5 to 7, when also dependent on claim 4, wherein:the curvature controller is configured to receive as an input a target curvature parameter and generate as an output a curvature control signal;the trajectory controller is configured to determine the sum of the curvature control signal and the output of the course angle neural network adaptive controller to provide the steering control signal output of the trajectory controller.

9. A motion control system according to any preceding claim, wherein each of the neural networks provided in the trajectory controller comprises an input layer of neurons, at least one hidden layer of neurons, and an output layer comprising at least one output neuron, wherein each neural network comprises a feedforward neural network that receives at the input layer of input neurons the error value associated with a respective trajectory parameter and the control signal output by the respective controller, and outputs the gain values at respective nodal values within the hidden layer of the neural network.

10. A motion control system according to claim 9, wherein each of the neural networks are further configured to receive as a feedforward term at least one environmental variable.

11. A motion control system according to claim 10, wherein the environmental variable comprises at least one of the following commonly found in a vehicle motion control system:-the speed of the vehicle for most of the vehicle motion control,5   - road / traffic measurements such as the curvature, heading and speed limit etc.- vehicle acceleration / reaction force- the motor rotation speed / angle for the current / torque control- steering torque or angle-vehicle turn signal condition, e.g. turn indicated or turn not indicated 1012. A motion control system according to any of claims 9 to 11, wherein during use of the control system the weights of the neural network(s) are updated by a gradientdescent backpropagation scheme each time a new set of input values is supplied to the neural network, and the updated weights combined with the input values are used to 15 update the neurons.

13. An autonomous automotive vehicle comprising the motion control system of any preceding claim.

Images