Examples disclosed herein involve a computing system configured to (i) receive sensor data associated with a vehicle's period of operation in an environment including (a) trajectory data associated with the vehicle and (b) at least one of trajectory data associated with one or more agents in the environment or data associated with one or more static objects in the environment, (ii) determine that at least one of (a) the one or more agents or (b) the one or more static objects is relevant to the vehicle, (iii) identify one or more times when there is a change to the one or more agents or the one or more static objects relevant to the vehicle, (iv) designate each identified time as a boundary point that separates the period of operation into one or more scenes, and (v) generate a representation of the one or more scenes based on the designated boundary points.

A lifeform transmission system is used to locate a lifeform wanting to be identified as a lifeform for collision avoidance. The lifeform transmission system comprises a lifeform vitals detector, a GPS transmitter and various other electrical circuits. The lifeform transmitter is worn on a limb or neck of the lifeform. If the lifeform does not wear a transmitter no signal is emitted. The collision avoidance system is housed inside the vehicle and receives communication from invention. If any lifeform is positioned in the path or approaching the path that the ground vehicle is traveling, the vehicle's collision avoidance system is advised to avoid the collision to enhance the accuracy of the collision avoidance system. This invention complements the existing collision avoidance system and enhances the accuracy of vehicle systems by providing an input from the lifeform, making detection easier.

Apparatuses, systems, and techniques to identify objects in view of a camera associated with a vehicle. In at least one embodiment, objects with which a vehicle may collide are identified, based on, for example, a difference between a size of an image of the objects detected at a first point in time and a size of an image of the objects detected at a subsequent point in time.

A vehicle control system includes a direction detector configured to detect a direction of a face or line of sight of an occupant of a host vehicle; an automated driving controller configured to execute automated driving; and a switching controller configured to switch an automated driving mode executed by the automated driving controller to any one of a plurality of automated driving modes including a first automated driving mode in which a predetermined task is required of the occupant or a predetermined automation rate is set and a second automated driving mode in which a level of the task required of the occupant is lower than in the first automated driving mode or an automation rate is lower than in the first automated driving mode, wherein the switching controller includes the direction detected by the direction detector being a predetermined direction in switching conditions for switching from the second automated driving mode to the first automated driving mode.

An autonomous vehicle uses machine learning based models to predict hidden context attributes associated with traffic entities. The system uses the hidden context to predict behavior of people near a vehicle in a way that more closely resembles how human drivers would judge the behavior. The system determines an activation threshold value for a braking system of the autonomous vehicle based on the hidden context. The system modifies a world model based on the hidden context predicted by the machine learning based model. The autonomous vehicle is safely navigated, such that the vehicle stays at least a threshold distance away from traffic entities.

An execution of a second task of a driver is assisted in cooperation with a user interface in an autonomous driving state in which a vehicle is an execution entity of a driving task. The second task is extracted, which is properly executable within task possible time estimated as time in which the second task is executable in a route to a destination of the vehicle. The second task extracted by the second task extracting unit is suggested through the user interface.

A vehicle drive assist apparatus for a vehicle includes a surrounding-condition-information acquiring unit that acquires surrounding condition information, a vehicle-state-information acquiring unit that acquires vehicle state information, a traveling control processor that executes traveling control in accordance with traffic lane designation, a DDI detector, and a control switch. The DDI detector detects a DDI in a front region of the vehicle on the basis of the surrounding condition information and determines whether the vehicle is entering or exiting from the DDI on the basis of the surrounding condition information and the vehicle state information. The control switch switches the traveling control from standard traveling control to non-standard traveling control when the vehicle entering the DDI is detected, and from the non-standard traveling control to the standard traveling control when the vehicle exiting from the DDI is detected on the basis of the result of the DDI determination.

An in-vehicle driving assistance apparatus that can execute driving assistance on the basis of any one of a plurality of control modes having mutually-different degrees of driving assistance, the apparatus comprising a receiving unit configured to receive a transition instruction of the control mode, a setting unit configured to set the control mode based on the transition instruction, a determining unit configured to determine whether or not a transition scheme for the control mode indicated by the transition instruction has a pre-registered detail, and a suppressing unit configured to suppress the setting of the control mode by the setting unit when the transition scheme for the control mode indicated by the transition instruction does not have the pre-registered detail.

Disclosed is a method of providing a scenario-based overlay torque request signal in a steer torque manager (1) during driver-override of an auxiliary steering assistance system (2) function in a road vehicle (3) having an EPAS system (4). The steer torque manager (1) has a wheel angle controller (1b) for providing an assistance torque request related signal, and a driver-in-the-loop functionality (1a) for determining driver-override and providing a driver-override related signal. The method comprises receiving signals related to: assistance torque request; driver-override; road vehicle velocity; steering pinion angle; distance to an adjacent lane marker (5a, 5b); and distance to an adjacent potential threat object (6), and producing, from the received signals, during ongoing driver-override, a signal representative of a resistance torque request corresponding to one of a finite number of pre-defined scenarios for different signal combinations, and producing the scenario-based steering wheel overlay torque request signal through combining the assistance torque request and the resistance torque request signals.

A system for data-driven, modular decision making and trajectory generation includes a computing system. A method for data-driven, modular decision making and trajectory generation includes: receiving a set of inputs; selecting a learning module such as a deep decision network and/or a deep trajectory network from a set of learning modules; producing an output based on the learning module; repeating any or all of the above processes; and/or any other suitable processes. Additionally or alternatively, the method can include training any or all of the learning modules; validating one or more outputs; and/or any other suitable processes and/or combination of processes.