The present teaching relates to method, system, medium, and implementation of human-like vehicle control for an autonomous vehicle. Information related to a target motion to be achieved by the autonomous vehicle is received, wherein the information includes a current vehicle state of the autonomous vehicle. A first vehicle control signal is generated with respect to the target motion and the given vehicle state in accordance with a vehicle kinematic model. A second vehicle control signal is generated in accordance with a human-like vehicle control model, with respect to the target motion, the given vehicle state, and the first vehicle control signal, wherein the second vehicle control signal modifies the first vehicle control signal to achieve human-like vehicle control behavior.

An apparatus for controlling a restricted mode is provided. The apparatus includes a controller that is configured to receive a first input from a primary driver corresponding to a request to change a vehicle from a fully operational mode to a restricted mode for a secondary driver. The controller is further configured to initiate a first timer for preventing the vehicle from exiting from the restricted mode to the fully operational mode if an occupant communication device belonging to the primary driver is detected by the vehicle prior to the first timer expiring.

Systems, methods, controllers and algorithms for controlling a vehicle to closely follow another vehicle safely using automatic or partially automatic control are described. The described control schemes are well suited for use in vehicle platooning and/or vehicle convoying applications, including truck platooning and convoying controllers. In one aspect, methods of initiating a platoon between a host vehicle and a platoon partner are described. In another aspect, a number of specific checks are described for determining whether a platoon controller is ready to initiate platoon control of the host vehicle. In another aspect, a platoon controller that includes a state machine that determines the state of the platoon controller is described. In another aspect, methods for generating braking alerts to a driver of a vehicle while the vehicle is being at least semi-automatically controlled by a platoon controller are described.

Enclosed are embodiments for sampling driving scenarios for training machine learning models. In an embodiment, a method comprises: assigning, using at least one processor, a set of initial physical states to a set of objects in a map for a set of simulated driving scenarios, wherein the set of initial physical states are assigned according to one or more outputs of a random number generator; generating, using the at least one processor, the set of simulated driving scenarios in the map using the initial physical states of the objects in the set of objects; selecting, using the at least one processor, samples of the simulated driving scenarios; training, using the at least one processor, a machine learning model using the selected samples; and operating, using a control circuit, a vehicle in an environment using the trained machine learning model.

Various examples of a controller, method and system for monitoring a tractor-trailer vehicle train are disclosed. In one example a tractor controller is manually-initiated or a user-initiated tractor controller and includes an electrical control port for receiving an electrical sync signal and an electrical start signal, and a communications port for receiving data. A processing unit of the tractor controller includes control logic and is in communication with the electrical control port. The control logic is capable of receiving a data signal at the communications port which includes a time value and a unique identification which corresponds to the towed vehicle in response to the electrical start signal. At a predetermined response time, the tractor controller determines the position of the towed vehicle in the tractor-trailer vehicle train based on the data received from the towed vehicles.

The present disclosure is directed to state-based autonomous-vehicle operations. In particular, the methods, devices, and systems of the present disclosure can: determine, based at least in part on one or more actions of a passenger associated with a trip of an autonomous vehicle, a current state of the trip from amongst a plurality of different predefined states of the trip; identify, based at least in part on the current state of the trip, one or more computing devices associated with the passenger; generate, based at least in part on the current state of the trip, data describing one or more interfaces for display by the computing device(s) associated with the passenger; and communicate, to the computing device(s) associated with the passenger, the data describing the interface(s) for display.

A method for populating a controller for a motor vehicle with data includes providing a controller with a storage device, and generating a projected mathematical model of at least one section of a powertrain, including a transmission. The projected mathematical model describes the section of the powertrain with a gear ratio of 1 and is applicable to different transmissions. The projected mathematical model is stored in the storage device of the controller. A motor vehicle is also provided and operated accordingly.

A system for interacting with a user in a vehicle includes a processing device including an input module configured to receive measurement data from one or more sensors, the measurement data related to features of the user. The system also includes a prompt design module configured to, in response to receiving an instruction to output a requested prompt to the user, determine a user state based on the measurement data, determine an activity state based on the measurement data and the user state, customize the requested prompt based on the user state and the activity state to generate a customized prompt, and output the customized prompt to the user.

Through-the-road (TTR) hybrid designs using control strategies such as an equivalent consumption minimization strategy (ECMS) or an adaptive ECMS are implemented at the supplemental torque delivering electrically-powered drive axle (or axles) in a manner that follows operational parameters or computationally estimates states of the primary drivetrain and/or fuel-fed engine, but does not itself participate in control of the fuel-fed engine or primary drivetrain. BSFC type data particular to the paired-with fuel-fed engine allows an ECMS implementation (or other similar control strategy) to adapt to efficiency curves for the particular fuel-fed engine and to improve overall efficiencies of the TTR hybrid configuration.

This disclosure is related to a method, a computer program code, and an apparatus for training a convolutional neural network for an autonomous driving system. The disclosure is further related to a convolutional neural network, to an autonomous driving system comprising a neural network, and to an autonomous or semi-autonomous vehicle comprising such an autonomous driving system. For training the convolutional neural network, in a first step real-world driving data are selected as training data. Furthermore, synthetic driving data are generated as training data. The convolutional neural network is then trained on the selected real-world driving data and the generated synthetic driving data using a genetic algorithm.