Abstract: Techniques and methods for providing additional safety for interactions with pedestrians. For instance, a vehicle may identify a region through which the vehicle and agent (such as a pedestrian) pass. The vehicle may then use a first state of the vehicle and predicted positions for the agent to determine a first collision metric between the vehicle and the agent within the region. Additionally, the vehicle may use the first collision metric to determine a maneuver for the vehicle. Next, the vehicle may simulate a state of the vehicle at a second time, where the state if based on the maneuver. The vehicle may then determine a second collision metric between the vehicle and the agent within the region using the state and the predicted positions of the agent. Additionally, the vehicle may use the second collision metric to determine another maneuver for the vehicle.

Abstract: Methods and systems of crowd-sourced magnetic fingerprinting for mobile device indoor navigation with neural network re-training are described. In an example, at multiple locations, magnetic input parameters in accordance with a magnetic infrastructure profile of an indoor area are determined. Further, from a mobile device positioned at a first location, measured magnetic parameters at respective ones of multiple locations are received. A route segment similarity factor for the mobile device based on the measured magnetic parameters of a corresponding route segment accessible from the magnetic fingerprint dataset is computed. If the similarity factor exceeds a threshold, the magnetic measured parameters are added to the magnetic fingerprint dataset. For at least a second location along the route, another set of magnetic measured parameters is received from the mobile device.

Abstract: 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.

Abstract: Disclosed is a control authority transfer apparatus of an autonomous vehicle, including a memory storing data on a plurality of users, and at least one processor setting driving operation priorities based on the data, wherein, in the state in which at least a part of autonomous driving control has failed, upon determining that a main user is in a state of being incapable of performing driving operation, the processor selects a first sub-user among a plurality of sub-users as a driving operation user according to the driving operation priorities, and selects a first device matching the first sub-user as a driving operation device.

Abstract: A system and a method for adjusting a yielding space of a platoon are provided. The system can include camera modules, sensors, interface circuitry, processing circuitry, and memory. The sensors can detect one or more behaviors of one or more vehicles adjacent to the platoon. The processing circuitry can determine one or more triggering events between the one or more vehicles and the platoon based on the one or more behaviors. The processing circuitry can adjust the yielding space of the platoon.

Abstract: A method for an early accident detection in transportation vehicles that includes recording the local acceleration at different distributed locations in a transportation vehicle using acceleration sensors installed at different locations; ascertaining local effect information for the different locations based on the measured accelerations; jointly evaluating the effect information for the different locations and deriving accident information, and outputting the accident information.

Abstract: A prediction control device controls an actuator for automatic driving of a vehicle including: a command value generation unit generating an operation amount for the actuator and an operation amount candidate as a predicted value; an output prediction unit outputting a control amount candidate as a predicted value corresponding to the actuator output by using an operation model; an evaluation function calculation unit expressing constraint conditions for the automatic driving; a situation degree detection obtaining a measure of giving priority to ride comfort or giving priority to danger avoidance of an own vehicle while traveling; and a responsiveness adjusting unit obtaining a next operation amount candidate from the situation degree from the situation degree detection unit. The operation command value generation unit generates an operation amount for the actuator, and the responsiveness adjusting unit adjusts the output of the evaluation function according to the situation degree.

Abstract: Techniques relating to training a model for detecting that a vehicle is likely to perform a cut-in maneuver are described. Computing device(s) can receive log data associated with vehicles in an environment and can detect an event in the log data, wherein an event corresponds to a cut-in maneuver performed by a vehicle. In an example, the computing device(s) can generate training data based at least in part on converting a portion of the log data that corresponds to the event into a top-down representation of the environment and inputting the training data into a model, wherein the model is trained to output an indication of whether another vehicle is likely to perform another cut-in maneuver.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer -storage media, for swarming technology. In some implementations, the system can be modeled on the spatial reasoning process found in rodents and other mammals. A plurality of synaptic weights can be formed within a neural network. The neural network along with additional data of a system can be used to determine motion vectors for one or more devices within a group of devices or swarm. The motion vectors can help determine where the devices within a group of devices are located at a given time. Motion vectors can direct devices to areas of high activity in a similar manner to how spatial cells in a brain direct animals in accordance with high activity rates of particular cells within their brain.

Abstract: A vehicle control apparatus includes: a road recognizer that recognizes a road form around a vehicle; a second-vehicle recognizer that recognizes a state of another vehicle around the vehicle; and a driving controller that allows the vehicle to travel by controlling one or both of steering and acceleration/deceleration of the vehicle and that prevents, upon passing of the vehicle through an intersection, passing of the vehicle through the intersection based on a presence of the other vehicle recognized by the second-vehicle recognizer, wherein in a case where the driving controller recognizes, by the road recognizer, that a plurality of lanes are present in a road of a right/left turn destination of the vehicle and recognizes, by the second-vehicle recognizer, that the other vehicle, which was an opposing vehicle approaching from a direction opposing the vehicle, has entered a lane on a rear side in a view from the vehicle among the plurality of lanes in the road of the right/left turn destination, the drivin

Abstract: A method comprises obtaining one or more parameters of an autonomous vehicle, the parameters including any of a position, path, and/or speed of the autonomous vehicle. The method further includes identifying, based on the one or more parameters of the autonomous vehicle, a region of interest from a plurality of regions surrounding the autonomous vehicle. The method further includes controlling, based on the region of interest, one or more sensors mounted on a surface of the autonomous vehicle to capture sensor data of the region of interest and not capture sensor data from the one or more other regions of the plurality of regions surrounding the autonomous vehicle. The method further includes providing the captured sensor data to a processor, the processor being capable of facilitating, based on the captured sensor data of the region of interest, one or more autonomous vehicle driving actions.

Abstract: A construction machine for building or finishing a road, such as a road finisher, comprises at least a working equipment, a display unit and a plurality of sensors. Each sensor is adapted to measure a value of an operating parameter of the construction machine. The sensors are adapted to output data corresponding to the measured values to the display unit, and the display unit is adapted to output a representation of at least a part of the construction machine together with the measured values of the operating parameters.

Abstract: A tractor trailer monitoring system includes a network having a server and a database; a first computing device; a monitoring platform to be accessible from the first computing device; a tractor trailer system, having a tractor unit; an air supply control system to control air supply to a brake system of the trailer, the air supply control system having a CPU to receive commands from the first computing device; the first computing device and monitoring platform are to receive an identifying code from a user to activate air supply to the brake system of the trailer.

Abstract: Upon determining a first vehicle is moving on a two-way road in a first direction of travel in an only lane of the two-way road, vehicle sensor data is input to a first neural network that identifies a yield area along the two-way road via image segmentation. A second vehicle is detected traveling toward the first vehicle on the only lane of the two-way road. Then, upon determining the first vehicle is to yield to the second vehicle, one or more vehicle components are actuated to move the first vehicle to the yield area.

Abstract: A steer-by-wire steering system, including: a two-system reaction force applying device including two reaction force controllers and configured to obtain operation information and apply an operation reaction force; a two-system steering device including two steering controllers and configured to steer a wheel; an operation information obtaining device; an auxiliary steering device capable of changing a direction of a vehicle; two dedicated communication lines one of which information-transmittably and information-receivably connects one of the two reaction force controllers and one of the two steering controllers to each other, and the other of which information-transmittably and information-receivably connects the other of the two reaction force controllers and the other of the two steering controllers to each other; and a first communication bus to which the operation information obtaining device is at least information-transmittably connected and to which the two steering controllers and the auxiliary stee

Abstract: The present disclosure relates to a robot provided in a vehicle capable of performing a function related to the vehicle. The robot includes a body, a head positioned above the body, an actuator configured to apply an external force to allow the head to move relative to the body, a camera disposed on the head to capture an image, a communication unit configured to perform communications with one or more devices provided in the vehicle, and a processor configured to control the actuator so that the camera is directed toward an inside or outside of the vehicle based on information received via the communication unit.

Abstract: A parking robot for a transportation vehicle having at least two wheel axles and a method for operating a parking robot. The parking robot includes a main robot part and a secondary robot part which each have a pair of wheel support arms on two opposite sides. The two-part parking robot then moves under the transportation vehicle with respective folded-in wheel support arms and disconnects the secondary robot part from the main robot part to position the main robot part and the secondary robot part each in a region of one of the wheel axles beneath the transportation vehicle and to lift up respective wheels of the respective wheel axle of the transportation vehicle by folding out the respective pairs of wheel support arms.

Abstract: A computer is programmed to identify a target vehicle to be monitored and to identify first and second virtual boundaries on a roadway based on a position of the target vehicle. The computer is further programmed to determine a first constraint value based on (1) a first boundary approach velocity and (2) a first boundary approach acceleration and a second constraint value based on (1) a second boundary approach velocity and (2) a second boundary approach acceleration. The computer is further programmed to identify a maneuver of the target vehicle based on whether the first and second constraint values violate respective thresholds or a position of the target vehicle relative to the first and second virtual boundaries violates a threshold and to adjust a path of a host vehicle according to the identified maneuver.

Abstract: A method for operating an autonomously operable motor vehicle comprising: receiving location data relating to a planned location of a motor vehicle; determining whether the motor vehicle is authorized to approach the planned location according to the location data by using at least one of the following: a) personal data about at least one person using the motor vehicle; b) a number of persons using the motor vehicle; c) load data about a load that is being or is to be transported by the motor vehicle.

Abstract: A vehicle includes a drive device for traveling, and a control device configured to control the drive device so that the vehicle travels with a target driving force based on an accelerator operation amount. The control device is configured to set the target driving force such that a change in the target driving force with respect to a change in the accelerator operation amount is gentler in a case where steady traveling is desired as compared with a case where the steady traveling is not desired. Therefore, in a case where the steady traveling is desired, a variation of a vehicle speed with respect to a slight variation of the accelerator operation amount can be gentle and continuous steady traveling can be facilitated.