Abstract: A method and processor for controlling steering of a Self-Driving Car (SDC) are disclosed. The method includes: acquiring SDC state data associated with vertices in a graph-structure, using the SDC state data for building a polynomial curve, using the polynomial curve for simulating a candidate trajectory of the SDC as if the SDC is steered in accordance therewith and such that a closest allowed steering wheel position to a non-allowed steering wheel position is used instead of the non-allowed steering wheel position, determining an offset between the simulated state and a target state of the SDC, selecting candidate steering profile as a target steering profile of the SDC based on the offset, and using the target steering profile of the SDC for controlling steering of the SDC. A method of training a Machine Learning Algorithm for predicting steering wheel positions to control steering of the SDC is also disclosed.

Abstract: A method for compensating for a temperature drift of an accelerometer for measuring the lateral tilt of a motorbike. When the vehicle is in the “bike upright” condition, and the temperature of the accelerometer is at least 30° C. above its reference temperature, a reading is taken of the acceleration values. These values are then processed in order to identify the coefficient of the slope of the straight line for correcting the offset of each axis of the accelerometer. A processing operation involves verifying the strict monotony of the coefficients in at least two successive readings and ensuring that the mean value thereof is included between determined limits. The mean coefficient that is finally obtained then can be used to correct the temperature of accelerations read over the entire operating range of the accelerometer. Thus, the computation of the tilt angle of the motorbike is more precise.

Abstract: Methods and systems may provide for technology to predict a future increase in power demand on a fuel cell based on route data associated with a vehicle powered by the fuel cell and reduce an operating temperature of the fuel cell prior to the future increase in power demand. The technology may also provide supplemental power from a battery to the vehicle while the operating temperature of the fuel cell is being reduced.

Abstract: A vehicular control system includes an electronic control unit (ECU) that includes (i) a next stack activation size hardware register and (ii) a hardware memory initializer configured to initialize memory. The ECU determines a maximum stack size of a vehicle control function called by a root function. The vehicle control function controls a system of the equipped vehicle. The next stack activation size hardware register stores a value equivalent to the determined maximum stack size of the first function. The ECU, prior to executing the vehicle function and while executing the root function, triggers execution of the hardware memory initializer. The hardware memory initializer initializes memory in parallel with execution of the root function based on the next stack activation size hardware register. The ECU executes the vehicle control function responsive to receiving an indication of completion from the hardware memory initializer indicating the memory initialization is complete.

Abstract: A dynamic obstacle avoidance method based on real-time local grid map construction includes: acquiring and inputting Red-Green-Blue-RGBD image data of a real indoor scene into a trained obstacle detection and semantic segmentation network to extract obstacles of different types and semantic segmentation results in the real indoor scene and generate 3D point cloud data with semantic information; according to the 3D point cloud data, extracting and inputting state information of a dynamic obstacle to a trained dynamic obstacle trajectory prediction model, and predicting a dynamic obstacle trajectory in the real indoor scene to build a local grid map; and based on a dynamic obstacle avoidance model, sending a speed instruction in real time to the mobile robot to avoid various obstacles during the navigation process.

Abstract: Aspects of the disclosure relate to controlling a vehicle having an autonomous driving mode. This may include receiving, by one or more processors of the vehicle, first information identifying a current relative humidity measurement within a sensor housing of a vehicle having an autonomous driving mode. The relative humidity measurement and pre-stored environmental map information may be used by the one or more processors to estimate a condition of a sensor within the sensor housing at a future time. This estimated condition may be used by the one or more processors to control the vehicle.

Abstract: An embodiment provides a laser scanning device, which includes a lens fixture, a lens and a light path regulation mechanism. The lens is arranged on the lens fixture, and one side of the lens faces incident light. The light path regulation mechanism is connected with the lens fixture and includes a distance regulation component and a rotation driving component, the distance regulation component is configured to regulate a position of the lens fixture, the distance regulation component regulates the position of the lens fixture to correspondingly regulate an eccentric distance of the lens relative to the incident light, the rotation driving component is configured to drive the lens to rotate around a set rotation axis that is parallel to an optical axis of the lens. Another embodiment discloses a laser radar.

Abstract: Techniques to predict object behavior in an environment are discussed herein. For example, such techniques may include determining a trajectory of the object, determining an intent of the trajectory, and sending the trajectory and the intent to a vehicle computing system to control an autonomous vehicle. The vehicle computing system may implement a machine learned model to process data such as sensor data and map data. The machine learned model can associate different intentions of an object in an environment with different trajectories. A vehicle, such as an autonomous vehicle, can be controlled to traverse an environment based on object's intentions and trajectories.

Abstract: A platooning system for causing multiple vehicles to travel in a platoon includes: a management device configured to set an order of the vehicles in the platoon; a transmission device mounted on each vehicle and configured to transmit driving information regarding a driving state of the vehicle; a reception device mounted on each vehicle and configured to receive the driving information of at least one of the vehicles; and a control device mounted on each vehicle and configured to control an operation of the vehicle based on the driving information, wherein the management device is configured to arrange the vehicles from a front end to a rear end with respect to a travel direction in an ascending order of driving performances of the vehicles.

Abstract: Embodiments herein can determine an optimal route for an autonomous electric vehicle. The system may score viable routes between the start and end locations of a trip using a numeric or other scale that denotes how viable the route is for autonomy. The score is adjusted using a variety of factors where a learning process leverages both offline and online data. The scored routes are not based simply on the shortest distance between the start and end points but determine the best route based on the driving context for the vehicle and the user.

Abstract: 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.

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.

Abstract: A method, a computer program, an apparatus, a transportation vehicle, and a traffic entity for updating an environmental model at a transportation vehicle. The method for a traffic entity and for updating a first environmental model at a transportation vehicle includes receiving information related to the first environmental model from the transportation vehicle wherein the first environmental model has at least first information on an object in an environment of the transportation vehicle and the first environmental model includes confidence information related to the first information. The method also includes obtaining information related to a second environmental model of the transportation vehicle at the traffic entity wherein at least second information on the object in the environment of the transportation vehicle and the second environmental model includes confidence information related to the second information.

Abstract: Systems, apparatuses and methods may provide for technology that generates, via a first neural network such as a grid network, a first vector representing a prediction of future behavior of an autonomous vehicle based on a current vehicle position and a vehicle velocity. The technology may also generate, via a second neural network such as an obstacle network, a second vector representing a prediction of future behavior of an external obstacle based on a current obstacle position and an obstacle velocity, and determine, via a third neural network such as a place network, a future trajectory for the vehicle based on the first vector and the second vector, the future trajectory representing a sequence of planned future behaviors for the vehicle. The technology may also issue actuation commands to navigate the autonomous vehicle based on the future trajectory for the vehicle.

Abstract: The disclosure describes embodiments for modifying a whether an ego vehicle changes lanes to a target lane at a target time based on a payload of a Vehicle-to-Everything (V2X) message originated by a remote vehicle. In some embodiments, a method includes determining, based on the payload, whether the remote vehicle is changing lanes to the target lane at the target time. The method includes determining that the ego vehicle is changing lanes to the target lane at approximately the target time. The method includes estimating that the ego vehicle and the remote vehicle will collide at the target lane at the target time. The method includes modifying an operation of a vehicle component of the ego vehicle so that the ego vehicle does not change lanes to the target lane at the target time.

Abstract: A method and system for providing a companion autonomous vehicle are described. In one embodiment, a method includes linking a companion autonomous vehicle to at least one vehicle, device, or user. The companion autonomous vehicle is tethered to the at least one vehicle, device, or user such that the companion autonomous vehicle is configured to stay within a predetermined range of the at least one vehicle, device, or user. The method further includes operating the companion autonomous vehicle to travel along with the tethered at least one vehicle, device, or user within the predetermined range.

Abstract: A movable object for responding to an object includes a first passive infrared sensor having a first detection range and a first field of view, and one or more second passive infrared sensors each having a second detection range and a second field of view. The second detection range is longer than the first detection range and the second field of view is smaller than the first field of view. The movable object further includes one or more processors configured to recognize the object based on one or more heat signals received from at least one of the first passive infrared sensor or the one or more second passive infrared sensors, and perform a flight response measure to control the movable object based on the recognized object.

Abstract: Vehicle systems include features for performing remote park assist (RePA) operations. One system include a feature where a user provides a continuous input via a touchscreen on a mobile device. The mobile device transmits a message and a vehicle autonomously traverses a calculated parking path while the message is being received by the vehicle. Another system include a feature where the vehicle autonomously move to a parking space based on data received from the mobile device. The mobile device receives user inputs on a display showing representations of the vehicle and its surrounding areas to generate the data. Another system include a feature where the mobile device determines whether the user is a first time user of a RePA application. The mobile device operates in a certain training mode based on the determination.

Abstract: A method for detecting and processing the carriageway condition of a carriageway on which a vehicle is driven, by means of at least one noise sensor provided on the vehicle, in particular by means of at least one mechanical vibration sensor, wherein noise signals travelling through the vehicle are sensed by a noise sensor and conclusions as to the carriageway condition are drawn from the sensed noise signals. According to said method, the section of route on which the vehicle is currently being driven is determined, the determined carriageway condition is assigned to the section of route, said section of route and the carriageway condition that has been determined and assigned to the section of route are transmitted to a computer network, in particular to a cloud-based computing service, and the information relating to the carriageway condition assigned to a section of route is made available via the computer network.

Abstract: Systems and methods are provided for receiving location data for a first location and a second location and generating a plurality of candidate routes to travel from the first location to the second location, based on the location data, each candidate route comprising a plurality of segments. The systems and methods further generate a safety score for each segment of each candidate route of the plurality of candidate routes, generate a safety score for each candidate route based on safety scores generated for each segment associated with each candidate route, select a best candidate route using the safety score associated with each of the candidate routes, and provide a recommendation for a travel route comprising the best candidate route.