Abstract: In one or more embodiments, a method comprises receiving, at a processor, sensor data from a sensor at a vehicle that is moving while in an autonomous mode. A position and an orientation of the vehicle based on the sensor data is determined at the processor. A lateral deviation of the vehicle from a planned path based on the position and the orientation of the vehicle while the vehicle is moving in the autonomous mode is calculated at the processor. In response to the lateral deviation exceeding a predefined lateral deviation threshold, the autonomous mode is disengaged.

Abstract: In various examples, live perception from sensors of a vehicle may be leveraged to detect and classify intersections in an environment of a vehicle in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute various outputs—such as bounding box coordinates for intersections, intersection coverage maps corresponding to the bounding boxes, intersection attributes, distances to intersections, and/or distance coverage maps associated with the intersections. The outputs may be decoded and/or post-processed to determine final locations of, distances to, and/or attributes of the detected intersections.

Abstract: A model calculation unit for calculating an RBF model is described, including a hard-wired processor core designed as hardware for calculating a fixedly predefined processing algorithm in coupled functional blocks, the processor core being designed to calculate an output variable for an RBF model as a function of one or multiple input variable(s) of nodes V[j,k], of length scales (L[j,k]), of weighting parameters p3[j,k] predefined for each node, the output variable being formed as a sum of a value calculated for each node V[j,k], the value resulting from a product of a weighting parameter p3[j,k] assigned to the particular node V[j,k], and a result of an exponential function of a value resulting from the input variable vector as a function of a square distance of the particular node (V[j,k]), weighted by the length scales (L[j,k]), the length scales (L[j,k]) being provided separately for each of the nodes as local length scales.

Abstract: Systems and methods for generating motion forecast data for actors with respect to an autonomous vehicle and training a machine learned model for the same are disclosed. The computing system can include an object detection model and a graph neural network including a plurality of nodes and a plurality of edges. The computing system can be configured to input sensor data into the object detection model; receive object detection data describing the location of the plurality of the actors relative to the autonomous vehicle as an output of the object detection model; input the object detection data into the graph neural network; iteratively update a plurality of node states respectively associated with the plurality of nodes; and receive, as an output of the graph neural network, the motion forecast data with respect to the plurality of actors.

Abstract: A method includes receiving, iteratively over time, sets of data including vehicle dynamics data, image data, sound data, third-party data, and wind speed sensor data, each detected at an autonomous vehicle and associated with a time period. The method also includes estimating a first wind speed and a first wind direction for each time period, in response to receiving the sets of data and based on the sets of data, via a processor of the autonomous vehicle. The method also includes iteratively modifying a lateral control and/or a longitudinal control of the autonomous vehicle based on the estimated first wind speed and the estimated first wind direction, via the processor of the autonomous vehicle and during operation of the autonomous vehicle.

Abstract: An in-vehicle life detection system and detection method thereof are provided. The system includes a processor, an electromagnetic wave detection module, and a warning module. The method includes following steps: vehicle condition identifying step, life form detecting step, and warning step. Upon receiving an engine off signal and a driver absence signal, the processor emits a detection activation signal, activating the electromagnetic wave detection module to emit an electromagnetic wave for detecting a life form. When the life form is detected, the warning module sends a warning signal, indicating that the life form is left in the vehicle when the vehicle is in the engine off status with the doors closed. Thus, the tragedy of a life form remaining inside the vehicle incapable of calling for help is avoided.

Abstract: A visiting destination prediction device includes: a user position information acquiring unit configured to acquire user position information indicating a position of a user; a stationary position deriving unit configured to derive a stationary position of the user on the basis of the acquired user position information; and a visiting POI estimating unit configured to estimate a visiting POI which is a visiting destination of the user on the basis of a relationship between the derived stationary position of the user and a predetermined POI position of a POI which is able to be the visiting destination of the user. The stationary position deriving unit derives the stationary position which is expressed by an area on the basis of an error and a degree of dispersion of a series of pieces of the acquired user position information.

Abstract: A controlled intersection employs video analytics to identify incoming vehicles coupled with autonomous driving capabilities in the vehicle to selectively provide intervention for collision avoidance. A camera image of an approaching vehicle is used to identify a range and speed, and to compute whether intervention is appropriate based on a detected distance and speed from the intersection. A vehicle approaching a stop signal (e.g. “red light”) at an unsafe rate of speed triggers an invocation of on-board autonomous systems in the vehicle that provide appropriate warnings and ultimately, forced braking if warnings go unheeded. A registration system maintains a local grouping of vehicles in proximity to an intersection for minimizing latency in vehicle identification for commencing intervention. In this manner, on-board vehicle collision avoidance systems collaborate with complementary traffic control logic at a controlled intersection for preventing inadvertent or intentional disregard of a red signal.

Abstract: A device for controlling a hybrid vehicle includes a storage storing a map in which an on reference value and an off reference value of an engine are recorded, a navigation device setting a route from a current location to a destination, a transceiver receiving a speed profile for each section on the route, and a controller dividing the route into a plurality of sections and correcting the map based on the received speed profile for each section to correct a map for determining an on time point and an off time point of an engine based on the speed profile most similar to the driving style of a driver.

Abstract: Embodiments provide a vehicle computer coupled to a vehicle. The vehicle computer may be configured to compute (e.g., generate) a first (e.g., regular, main) trajectory and a second (e.g., fail-safe, minimal risk maneuver) trajectory for the vehicle. Embodiments may provide techniques for incorporating sensor input into the response for managing a minimal risk maneuver. The low-resolution sensor data may be received from a low-resolution sensor having integrated object detection processing such as an automotive radar sensor. The safety processor may modify the second trajectory using the low-resolution sensor data to avoid any new hazards along the second trajectory. Embodiments may also provide, in addition to the low-resolution radar sensor data, pre-computed analysis of the low-resolution radar sensor data from the main processor to the safety processor to reduce the false positives (e.g., false positive object detections) along the second trajectory.

Abstract: Systems and methods for a materials handling vehicle to navigate a vehicle transit surface in a warehouse environment including a navigation subsystem configured to cooperate with a traction control unit, a braking system, a steering assembly, and an obstacle detection subsystem to: determine whether the materials handling vehicle is approaching, or has arrived at, a potentially contested intersection; associate with the intersection pre-positioned warehouse object data, a set of road rules, and obstacle data; and navigate the materials handling vehicle through the intersection utilizing warehouse navigation maneuvers in combination with the associated set of road rules, obstacle avoidance maneuvers, or both, the warehouse navigation maneuvers accounting for the associated pre-positioned warehouse object data and the obstacle avoidance maneuvers accounting for the obstacle data derived from the obstacle detection subsystem.

Abstract: A user-generated graphical representation can be sent into a generative network to generate a synthetic image of an area including a road, the user-generated graphical representation including at least three different colors and each color from the at least three different colors representing a feature from a plurality of features. A determination can be made that a discrimination network fails to distinguish between the synthetic image and a sensor detected image. The synthetic image can be sent, in response to determining that the discrimination network fails to distinguish between the synthetic image and the sensor-detected image, into an object detector to generate a non-user-generated graphical representation. An objective function can be determined based on a comparison between the user-generated graphical representation and the non-user-generated graphical representation.

Abstract: Techniques and methods for training and/or using a machine learned model that identifies unsafe events. For instance, computing device(s) may receive input data, such as vehicle data generated by one or more vehicles and/or simulation data representing a simulated environment. The computing device(s) may then analyze features represented by the input data using one or more criteria in order to identify potential unsafe events represented by the input data. Additionally, the computing device(s) may receive ground truth data classifying the identified events as unsafe events or safe events. The computing device(s) may then train the machine learned model using at least the input data representing the unsafe events and the classifications. Next, when the computing device(s) and/or vehicles receive input data, the computing device(s) and/or vehicles may use the machine learned model to determine if the input data represents unsafe events.

Abstract: A system for preventing abnormal acceleration of a vehicle includes a device configured such that in a state in which the vehicle is stopped while the vehicle is turned on, the device is configured to determine whether abnormal acceleration prevention is necessary based on a final destination or a current position of the vehicle before the vehicle is turned off to thereby limit a vehicle speed. The system and a method for preventing abnormal operation of the vehicle can prevent a vehicle accident due to the abnormal acceleration caused by misoperation by a driver, such as misoperation of an accelerator pedal of the vehicle.

Abstract: The disclosed embodiments include a onboard driver distraction determination system. The determination system includes a onboard sensing and computing system(s), which includes inertial sensor(s), internal sensor(s), and external sensor(s). The onboard system samples data from the sensor(s) during a driving session to determine steering activity metrics and driver behavior. A steering activity metric is a representation of the steering inputs by the driver during the driving session. Driver behavior is a representation of how distracted the driver is during the driving session. By performing the above mentioned steps, the system can provide an analysis of driver distraction and optionally, take control of the vehicle to avoid aberrant behavior.

Abstract: A method includes detecting, via a processor of an autonomous vehicle, an upcoming downhill road segment of a route on which the autonomous vehicle is currently travelling. The detection is based on map data, camera data, and/or inertial measurement unit (IMU) data. In response to detecting the upcoming downhill road segment, a descent plan is generated for the autonomous vehicle. The descent plan includes a speed profile and a brake usage plan. The brake usage plan specifies a non-zero amount of retarder usage and an amount of foundation brake usage for a predefined time period. The method also includes autonomously controlling the autonomous vehicle, based on the descent plan, while the autonomous vehicle descends the downhill road segment.

Abstract: This disclosure relates to method and system for providing personalized driving or navigation assistance. The method may include receiving sensory data with respect to a vehicle from a plurality of sensors and multi-channel input data with respect to one or more passengers inside the vehicle from a plurality of onboard monitoring devices, performing fusion of the sensory data and the multi-channel input data to generate multimodal fusion data, determining one or more contextual events based on the multi-modal fusion data using a machine learning model, wherein the machine learning model is trained using an incremental learning process and comprises a supervised machine learning model and an unsupervised machine learning model, analysing the one or more contextual events to generate a personalized driving recommendation, and providing the personalized driving recommendation to a driver passenger or a navigation device.

Abstract: Systems and methods are provided for learning world graphs to accelerate hierarchical reinforcement learning (HRL) for the training of a machine learning system. The systems and methods employ or implement a two-stage framework or approach that includes (1) unsupervised world graph discovery, and (2) accelerated hierarchical reinforcement learning by integrating the graph.

Abstract: A method of using an adaptive fault diagnostic system for motor vehicles is provided. A diagnostic tool collects unlabeled data associated with a motor vehicle, and the unlabeled data is transmitted to a central computer. An initial diagnostic model and labeled training data associated with previously identified failure modes and known health conditions are transmitted to the central computer. The central computer executes a novelty detection technique to determine whether the unlabeled data is novelty data corresponding with a new failure mode or normal data corresponding with one of the previously identified failure modes or known health conditions. The central computer selects an informative sample from the novelty data. A repair technician inputs a label for the informative sample, and the central computer propagates the label from the informative sample to the associated novelty data. The central computer updates the labeled training data to include the labeled novelty data.

Abstract: Disclosed are a system, a method, and an apparatus for controlling a suspension using image data captured by an image sensor. The suspension control apparatus includes at least one image sensor mounted to an own vehicle to capture image data of the surrounding environment of the own vehicle, and a controller configured to control the own vehicle based on the image data captured by the at least one image sensor, wherein the controller receives the image data from the at least one image sensor, extracts suspension control reference information including at least one of road environment information, own vehicle surrounding object information, and own vehicle state information based on the image data and/or an in-vehicle sensor of the own vehicle, and generates a control signal for controlling the height of a suspension according to the suspension control reference information.