This application provides a data processing method performed a computer device. The method includes: generating an initial predicted lane change acceleration corresponding to a target vehicle in a current lane; generating target predicted position information corresponding to the target vehicle according to a predicted lane change time duration taken for the target vehicle to change from the current lane to a target lane, the target lane being a lane to which the target vehicle is expected to change to; determining a target obstacle vehicle in the target lane and adjacent to the target vehicle according to the target predicted position information; determining, according to a predicted position relationship between the target obstacle vehicle and the target vehicle, a target predicted lane change acceleration; and controlling, according to the target predicted lane change acceleration, the target vehicle to change from the current lane to the target lane.

[Problem] To provide an automatic driving robot control device and control method that enable a vehicle to be operated smoothly while also being caused to conform to a command vehicle speed with high accuracy.

[Solution] The present invention provides an automatic driving robot (drive robot) 4 control device 10 that controls the automatic driving robot 4, which is installed in a vehicle 2 and causes the vehicle 2 to run, such that the vehicle 2 runs in accordance with a defined command vehicle speed, wherein the automatic driving robot 4 control device 10 is provided with: a running state acquisition unit 22 that acquires a running state of the vehicle 2 including a vehicle speed and the command vehicle speed; an operation content inference unit 31 that infers, on the basis of the running state, an operation sequence, which is a sequence of operations of the vehicle 2 at a plurality of times in the future that causes the vehicle 2 to run in accordance with the command vehicle speed, by using an operation inference learning model 40 that was trained by machine learning to infer the operation sequence; and a vehicle operation control unit 23 that extracts, from each of the operation sequences inferred a plurality of times in the past, the operations corresponding to a control time for subsequently controlling the automatic driving robot 4, calculates a weighted sum of these extracted plurality of operations to calculate a final operation value, generates, on the basis of the final operation value, a control signal for controlling the automatic driving robot 4, and transmits the control signal to the automatic driving robot 4.

The present invention is to obtain a control device and a control method capable of appropriately assisting driving of a straddle-type vehicle by a rider.

In a control device (12) and a control method of the present invention, an acquisition section of the control device (12) configured to control an operation of a straddle-type vehicle (10) acquires prediction information about a future lane change by a preceding vehicle that travels ahead of the straddle-type vehicle (10), and a control section of the control device (12) causes the straddle-type vehicle (10) to execute a safety operation (for example, causes a notification device (15) to issue a warning of the lane change to the rider), when the prediction information satisfies a determination criterion during a slipping-through traveling of the straddle-type vehicle (10).

Disclosed are a drunk driving prevention system and a drunk driving prevention method using the system that includes a sensor module measuring the alcohol content in exhaled breath of a driver at the time of breath-checking of the driver and a control module configured to check an intoxication state of the driver based on the alcohol content measured by the sensor module to determine whether or not a breath-checking is complete and block an engine start when the breath-checking fails, wherein the control module includes a bypass control unit switching a vehicle into a drivable state when the breath-checking fails.

According to the present disclosure, a drunk driving prevention system including: an alcohol detection unit configured to detect a driver's inebriation through the breath test device provided in a vehicle; a computation unit configured, when the driver is detected to be in a drunk state by the alcohol detection unit, to compute a driving-possible time at which the drunk state is resolved in the future so that driving is possible; and a notification unit configured to output the driving-possible time or whether or not driving is possible through an infotainment system of the vehicle or a driver's terminal is disclosed.

A method for providing a prediction of a radius of a motorcycle turn, the method may include determining that the motorcycle is about to turn; predicting values of multiple radius of turn impacting (RTI) parameters; wherein the multiple RTI parameters are selected out of a group of parameters, wherein the selection was made during a machine learning training process, and the group of parameters comprises motorcycle kinematic parameters; determining, based on the determined values of the multiple RTI parameters, the estimated radius of the motorcycle turn; and performing a driving related operation based on the estimated radius of the motorcycle turn.

Methods and systems are provided for controlling an autonomous vehicle. In one embodiment, a method includes: identifying, by a processor, at least one constraint on a longitudinal dimension of an upcoming road; defining, by the processor, constraint activation logic based on a type of the at least one constraint; performing, by the processor, the constraint activation logic to determine a state of the constraint to be at least one of active and inactive; when the state of the constraint is active, validating, by the processor, a motion plan of the autonomous vehicle based on the constraint; and selectively controlling the autonomous vehicle based on the validating of the motion plan.

A method may include obtaining input information relating to an environment in which an autonomous vehicle (AV) operates, the input information describing at least one of: a state of the AV, an operation of the AV within the environment, a property of the environment, or an object included in the environment. The method may include identifying a first object in the vicinity of the AV based on the obtained input information. The method may include determining a first object rule corresponding to the first object, the first object rule indicating suggested driving behavior for interacting with the first object. The method may include determining a first decision that follows the first object rule and sending an instruction to a control system of the AV, the instruction describing a given operation of the AV responsive to the first object rule according to the first decision.

A pedestrian tracking system includes: a buffer or a memory configured to store a trajectory sequence of a pedestrian; a step attention module and a control module. The step attention module iteratively performs a step attention process to predict states of the pedestrian. Each iteration of the step attention process includes the step attention module: learning the stored trajectory sequence to provide time-dependent hidden states, reshaping each of the time-dependent hidden states to provide two-dimensional tensors; condensing the two-dimensional tensors via convolutional networks to provide convolutional sequences; capturing global information of the convolutional sequences to output a set of trajectory patterns represented by a new sequence of tensors; learning time-related patterns in the new sequence and decoding the new sequence to provide one or more of the states of the pedestrian; and modifying the stored trajectory sequence to include the predicted one or more of the states of the pedestrian.

An autonomous vehicle safety system may activate to prevent collisions by detecting that a planned trajectory may result in a collision. If the safety system is overly sensitive, it may cause false positive activations, and if the system isn't sensitive enough the collision avoidance system may not activate and prevent a collision, which is unacceptable. It may be impossible or prohibitively difficult to detect false positive activations of a safety system and it is unacceptable to risk a false negative, so tuning the safety system is notoriously difficult. Tuning the safety system may include detecting near-miss events using surrogate metrics, and tuning the safety system to increase or decrease a rate of near-miss events as a stand-in for false positives.