Abstract: A system and method for providing social-stage spatio-temporal multi-modal future forecasting that include receiving environment data associated with a surrounding environment of an ego vehicle and implementing graph convolutions to obtain attention weights that are respectively associated with agents that are located within the surrounding environment. The system and method also include decoding multi modal trajectories and probabilities for each of the agents. The system and method further include controlling at least one vehicle system of the ego vehicle based on predicted trajectories associated with each of the agents and the rankings associated with probabilities that are associated with each of the predicted trajectories.

Abstract: Provided is a mobile device that acquires the section information of an automatic driving section and a manual driving section on a traveling route, and estimates the time to reach each section and transmits the estimated time to an information terminal. The information terminal receives the transmission data from the mobile device, and outputs the section information of the automatic driving section and the manual driving section and the display data by which a time to reach each section is confirmable. Moreover, the mobile device determines notification timing of a manual driving recovery request notification on the basis of an arousal level, a position, or the like of a driver and transmits the determined notification timing to the information terminal, and the information terminal executes the manual driving recovery request notification at appropriate notification timing.

Abstract: Provided is a driving assistance apparatus (a control unit (100)) for a vehicle capable of hands-off driving that lets a driver take his or her hands off the steering wheel. The driving assistance apparatus includes a processor (10) configured to determine, on the basis of sensor information indicating a state of the driver, whether or not the driver is in a state unsuitable for the surrounding monitoring of the vehicle during the hands-off driving, warn the driver through a notification device when it is determined that the driver is in a state unsuitable for the surrounding monitoring, and notify the driver, through the notification device, of a request for holding the steering wheel.

Abstract: A controller for a vehicle is configured to determine the position of the accelerator pedal with respect to a reference accelerator pedal position (aref); and either determine a torque output in dependence on an acceleration pedal map if the position of the accelerator pedal is greater than the reference accelerator pedal position (aref); and, determine a torque output in dependence on a deceleration pedal map if the position of the accelerator pedal is less than the reference accelerator pedal position (aref).

Abstract: A passenger seat for commercial vehicles and rail systems, having at least: a massage pad for increasing the ergonomics in the waist section of the passenger and applying massage; a compressor for inflating the massage pad; cooling pads for cooling the passenger; a heating pad for heating the upper portion of the seat and the backrest contacting the passenger; a presence sensor for determining whether there is a passenger on the passenger seat; a belt sensor for determining whether the passenger fastens the safety belt; a wireless charging unit for the passenger to charge a mobile device without using a connection cable; a manual control panel for the heating pad, cooling pad and the massage pad; a wireless connection module for the heating pad, cooling pad and the massage pad; and a control unit where the data collected from the presence sensor and belt sensor are transmitted.

Abstract: An autonomous vehicle uses machine learning based models such as neural networks to predict hidden context attributes associated with traffic entities. The hidden context represents behavior of the traffic entities in the traffic. The machine learning based model is configured to receive a video frame as input and output likelihoods of receiving user responses having particular ordinal values. The system uses a loss function based on cumulative histogram of user responses corresponding to various ordinal values. The system identifies user responses that are unlikely to be valid user responses to generate training data for training the machine learning mode. The system identifies invalid user responses based on response time of the user responses.

Abstract: A system for facilitating transfers of control includes an input module configured to acquire a set of user preferences relating control states to contexts, the control states including at least a manual control state, and an autonomous and/or semi-autonomous control state. The system includes a processing device configured to automatically perform, during operation of a semiautonomous system, generating a transfer of control (TOC) policy based on the set of user preferences and a current context state, the TOC policy prescribing transitions between control states in response to actions. The processing device is also configured to perform, based on an action performed by the user or a control system, determining whether to perform a transition from a current control state to a second control state, and in response to the TOC policy prescribing the transition, transitioning from the current control state to the second control state.

Abstract: Provided is a driving assistance apparatus (a control unit (100)) for a vehicle capable of hands-off driving that lets a driver take his or her hands off the steering wheel. The driving assistance apparatus includes a processor (10) configured to determine, on the basis of sensor information indicating a state of the driver, whether or not the driver is in a state unsuitable for the surrounding monitoring of the vehicle during the hands-off driving, warn the driver through a notification device when it is determined that the driver is in a state unsuitable for the surrounding monitoring, and notify the driver, through the notification device, of a request for holding the steering wheel.

Abstract: A driver assistance system for a motor vehicle for automated driving with automated longitudinal guidance, wherein when automated longitudinal guidance is active in an automatic mode, automated longitudinal guidance is brought about taking into account a predefinable setpoint speed. The system includes a first detection unit, configured to detect a defined stationary state situation which is set on the basis of a preceding automated braking process of the motor vehicle to the stationary state, a second detection unit, configured to detect accelerator pedal activation, and an evaluation and control unit, configured to actuate a manual mode when actuator pedal activation is detected during a defined stationary state situation.

Abstract: Disclosed herein are methods and systems for determining an attribute of an object at a pre-determined time point. Data representing a respective property of the object and a plurality of further objects at a plurality of time points different from the pre-determined time point are determined, and the data is arranged in an image-like data structure. The image-like data structure has a plurality of columns and a plurality of rows. The data is arranged in the image-like data structure such that each of one of the rows or the columns corresponds to respective properties of the object or of one of the plurality of further objects and each of the other of the rows or the columns corresponds to respective properties at one of the plurality of time points. The attribute is then determined using a pre-determined rule based on the image-like data structure.

Abstract: Systems and methods for predicting travel patterns of a vehicle or one or more occupants in the vehicle are provided. A transceiver may receive data indicative of at least one of passenger information, vehicle occupancy, vehicle status, and vehicle location from at least one of a voice recognition device, IoT sensors such as seat sensors, vehicle status sensors, or a GPS system. A processor may determine travel patterns based on the data, predict travel patterns based on the determined travel patterns, and generate a database comprising the predicted travel patterns. In addition, the processor may generate an alert if the determined travel pattern deviates from the predicted travel patterns.