An apparatus for an electrically powered terrestrial vehicle applies electrical energy to front wheels and to rear wheels. A control system receives desired acceleration inputs and provides target torque requirements to a plurality of adaptive field-oriented motor control circuits. One or more three-phase alternating current synchronous motors receive voltage magnitude and voltage frequency to generate torque, which is applied through a reduction gear. One motor only may be powered during certain modes of operation.

A method of rocking a vehicle free, the vehicle having a drive-train (1) with a torque adjusting element (3) which transmits drive torque to a vehicle wheel (5). The adjusting element (3) is controlled as a function of an accelerator pedal position. In a rocking-free situation in which the vehicle wheel (5) is to be moved from a depression (6) by alternating deflection and release of the accelerator pedal (8), the driver produces a cyclically fluctuating drive torque at vehicle wheel (5). The accelerator pedal position is continually monitored and upon recognizing a beginning or imminently beginning reduction of the accelerator pedal deflection or a parameter derived therefrom, an imminent full release of the deflection of the accelerator pedal (8) is concluded and the adjusting element (3) is actuated in anticipation so that the vehicle wheel (5) is immediately freed from a drive torque that has been active until then.

A real-time assessment method of driving risk based on equivalent force includes: S1, collecting traffic environment information and various types of traffic environment use object information in a road environment in an area to be assessed; S2, inputting, into an electronic control unit of a vehicle, the traffic environment use object information and the environment information acquired in S1, wherein a road risk assessment model based on the equivalent force distribution is preset in the electronic control unit; S3, using the road risk assessment model, so as to acquire road traffic risk E of the vehicle i and equivalent force distribution F.sub.ij between the vehicle i and the object j in different traffic environments, wherein the object j represents any traffic element other than vehicle i in various traffic environment use object information. A real-time assessment device of driving risk based on equivalent force is further provided.

A path determination apparatus according to this disclosure includes a gate selecting unit that, when a vehicle is to pass through a tolling station having a plurality of gates, selects a gate to pass through from among the plurality of gates. The gate selecting unit is configured to make a judgement as to whether or not a road which the vehicle travels on until passing through the tolling station is an expressway, as one conditional judgement for selecting the gate to pass through.

A driving assistance apparatus includes: a determination processing unit to determine whether or not a vehicle is present around a target vehicle on the basis of detection information around the target vehicle; and a notification processing unit to notify information to a driver of the target vehicle, in which the notification processing unit notifies reference information of manual driving in a case where the determination processing unit determines that there is no vehicle ahead of the target vehicle.

Systems and methods for causing a vehicle to avoid an adverse action are described. In one aspect, a sensor on first vehicle may determine the existence and location of lane markers or objects, and use that information to cause a second vehicle to avoid exiting its lane or colliding with an object. Data transmitted from a first vehicle to a second vehicle may be used to determine a path for the second vehicle, such that it avoids an adverse action. This data may include information used to determine a pose of the second vehicle, kinematics of the second vehicle, determine dimensions of the second vehicle, and potential adverse actions. This data may be transmitted while the vehicles are platooning.

Systems and methods described herein relate to generating a task offloading strategy for a vehicular edge-computing environment. One embodiment simulates a vehicular edge-computing environment in which one or more vehicles perform computational tasks whose data is partitioned into segments and performs, for each of a plurality of segments, a Deep Reinforcement Learning (DRL) training procedure that includes receiving state-space information regarding the one or more vehicles and one or more intermediate network nodes; inputting the state-space information to a policy network; generating, from the policy network, an action concerning a current segment; and assigning a reward to the policy network for the action in accordance with a predetermined reward function. This embodiment produces, via the DRL training procedure, a trained policy network embodying an offloading strategy for segmentation offloading of computational tasks from vehicles to one or more of an edge server and a cloud server.

An electric vehicle includes a vehicle controller. The vehicle controller is capable of switching a traveling mode of the electric vehicle between a first traveling mode and a second traveling mode that applies driving-force maps for enhancing a rough-road capability from a rough-road capability in the first traveling mode. The vehicle controller is capable of switching the traveling mode to the second traveling mode in forward traveling and in backward traveling and is configured to apply, to the backward traveling in the second traveling mode, a first driving-force map of the driving-force maps, the first driving-force map having gentler characteristics than a second driving-force map of the driving-force map applied to the forward traveling in the second traveling mode.

Systems and methods described herein relate to generating a task offloading strategy for a vehicular edge-computing environment. One embodiment simulates a vehicular edge-computing environment in which one or more vehicles perform computational tasks whose data is partitioned into segments and performs, for each of a plurality of segments, a Deep Reinforcement Learning (DRL) training procedure that includes receiving state-space information regarding the one or more vehicles and one or more intermediate network nodes; inputting the state-space information to a policy network; generating, from the policy network, an action concerning a current segment; and assigning a reward to the policy network for the action in accordance with a predetermined reward function. This embodiment produces, via the DRL training procedure, a trained policy network embodying an offloading strategy for segmentation offloading of computational tasks from vehicles to one or more of an edge server and a cloud server.

A vehicle control device configured to control a self-vehicle, the vehicle control device comprising: a first detection unit configured to detect a direction change of an oncoming vehicle; a second detection unit configured to detect another vehicle on a diagonally rear side of the self-vehicle; and a control unit configured to control a notification unit on the basis of detection results of the first detection unit and the second detection unit, wherein the control unit controls the notification unit to notify the oncoming vehicle of presence of the other vehicle in a case where the direction change of the oncoming vehicle has been detected and the other vehicle has been detected.