Abstract: An autonomous vehicle or self-driving vehicle can protect persons from accidents. When the occupants of a vehicle exit the vehicle, those occupants can be endangered by the driving environment. Thus, while the occupants are outside the vehicle, the vehicle can continue to monitor the environment and provide warnings or intercept other vehicles or objects that may impact the occupants. Once all occupants have exited the vehicle, the vehicle's systems can continue to track each person around the vehicle and may engage, in limited maneuvers, to shield the pedestrians around the vehicle.

Abstract: In one aspect, a system for operating an agricultural harvester may include a sensor assembly having a base member pivotably coupled to a first row divider of the harvester. The sensor assembly may also include first and second arms extending outwardly from the base member along opposite sides of a centerline of the first row divider. The system may further include a controller communicatively coupled to the sensor assembly. The controller may be configured to monitor the distance between the first and second arms based on measurement signals received from the sensor assembly. Furthermore, the controller may be further configured to switch the harvester from a first operating mode to a second operating mode when it is determined that the monitored distance has exceeded a predetermined distance threshold.

Abstract: Systems, methods, and non-transitory computer readable media may be configured to facilitate prioritization of vehicle navigation. One or more vehicles in an environment of a priority vehicle may be identified. Priorities of the vehicle(s) and the priority vehicle may be determined. A desired navigation of the priority vehicle in the environment may be determined based on the priorities of the vehicle(s) and the priority vehicle. An instruction may be provided to at least one of the vehicle(s) based on the desired navigation of the priority vehicle in the environment. The instruction may characterize one or more maneuvers to be performed by the at least one of the vehicle(s) to facilitate the desired navigation of the priority vehicle.

Abstract: A method of controlling an active seatbelt includes checking whether a seatbelt is fastened, collecting driving information from a sensor or driving assist/safety system installed in a vehicle, determining a safety state of the vehicle based on the driving information, checking whether an airbag is deployed, and outputting a motor control signal for restraint control of the seatbelt in response to the safety state when the airbag is not deployed.

Abstract: An autonomous vehicle controlled based upon the output of a trained object classifier is described herein. The object classifier is trained using labeled training data generated by a pipeline configured to assign labels to unlabeled sensor data. The pipeline includes transmitting sensor signal data capturing an object to individual computing devices for indications of an object type, wherein a label is assigned to the object based on the indications and provided to a data store as labeled training data. A learning system receives the labeled training data and generates a trained object classifier (e.g., a neural network) that is deployed in an autonomous vehicle to control operation of a mechanical system based on an output thereof.

Abstract: An information presentation apparatus is provided. A light emission device and a HCU are mounted on a vehicle as the information presentation apparatus. The light emission device is arranged on an instrument panel, and displays at least one light emission spot in a linear light emission area arranged to extend in a width direction of the vehicle. The HCU acquires monitoring information including at least position information of the risk target detected by the peripheral monitoring device, and calculates a risk level of the risk target, detected in a traveling direction of the vehicle, based on the monitoring information. When detecting a plurality of the risk targets, the HCU selects one of the risk targets having a highest risk level as a highest risk target, and displays the light emission spot, indicative of a direction of the highest risk target, in the linear light emission area.

Abstract: A set of sensor information may include first sensor information generated based on a first sensor of a first vehicle and second sensor information generated based on a second sensor of a second vehicle. Individual sensor information may characterize positions of objects in an environment of individual sensors. Relevant sensor information for a vehicle may be determined based on the set of sensor information and a position of the vehicle. The relevant sensor information may characterize positions of objects in a maneuver environment of the vehicle. A desired navigation of the vehicle in the maneuver environment of the vehicle may be determined based on the relevant sensor information. An instruction may be provided to the vehicle based on the desired navigation of the vehicle. The instruction may characterize one or more maneuvers to be performed by the vehicle to execute the desired navigation.

Abstract: Various technologies described herein pertain to generating an occupancy grid movie for utilization in motion planning for the autonomous vehicle. The occupancy grid movie can be generated for a given time and can include time-stepped occupancy grids for future times that are at predefined time intervals from the given time. The time-stepped occupancy grids include cells corresponding to regions in an environment surrounding the autonomous vehicle. Probabilities can be assigned to the cells specifying likelihoods that the regions corresponding to the cells are occupied at the future times. Moreover, cached query objects that respectively specify indices of cells of a grid occupied by a representation of an autonomous vehicle at corresponding orientations are described herein. An occupancy grid for the environment surrounding the autonomous vehicle can be queried to determine whether cells of the occupancy grid are occupied utilizing a cached query object from the cache query objects.