Abstract: A system uses a machine learning based model to determine attributes describing states of mind and behavior of traffic entities in video frames captured by an autonomous vehicle. The system classifies video frames according to traffic scenarios depicted, where each scenario is associated with a filter based on vehicle attributes, traffic attributes, and road attributes. The system identifies a set of video frames associated with ground truth scenarios for validating the accuracy of the machine learning based model and predicts attributes of traffic entities in the video frames. The system analyzes video frames captured after the set of video frames to determine actual attributes of the traffic entities. Based on a comparison of the predicted attributes and actual attributes, the system determines a likelihood of the machine learning based model making accurate predictions and uses the likelihood to generate a navigation action table for controlling the autonomous vehicle.

Abstract: A method for simulation of an autonomous vehicle includes preparing a setting of a parameter and an initial value configured to determine a driving condition of the autonomous vehicle and a driving condition of an event to be performed by a surrounding vehicle to implement a simulation environment of the autonomous vehicle. The method further includes performing a normal driving in which the surrounding vehicle travels at a speed and a position that match a predetermined condition set in the parameter to perform the event given, and performing an event driving in which the surrounding vehicle performs the event given based on a setting value of the parameter.

Abstract: An example method includes identifying a degraded visual environment corresponding to a phase of a route followed by the vehicle. The method includes determining, based on the phase of the route, a first segment of a trajectory of the vehicle along which to search for a location with an improved navigation environment. The method includes causing the vehicle to follow the first segment until: (i) identifying the improved navigation environment, or (ii) reaching an end of the first segment without identifying the improved navigation environment. The method includes determining a second segment of the trajectory based on whether the improved navigation environment has been identified. The method includes causing the vehicle to follow the second segment.

Abstract: When an automatic operation is finished, a detection process for detecting a ground contactable range where a work implement can be set is carried out on a basis of terrain profile information acquired by laser scanners, and, when the ground contactable range is detected, an automatic operation command signal for placing the work implement in contact with the ground contactable range is generated, whereas when the ground contactable range is not detected, an automatic operation command signal for placing the work implement in a predetermined standby posture is generated. As a result, a suitable standby posture can be taken according to the surrounding conditions when the automatic operation is finished.

Abstract: An autonomous vehicle receives geographic location data defined via a mobile computing device operated by a user. The geographic location data is indicative of a device position of the mobile computing device. The autonomous vehicle also receives image data generated by the mobile computing device. The image data is indicative of a surrounding position nearby the device position. The surrounding position is selected from an image captured by a camera of the mobile computing device. A requested vehicle position (e.g., a pick-up or drop-off location) is set for a trip of the user in the autonomous vehicle based on the geographic location data and the image data. A route from a current vehicle position of the autonomous vehicle to the requested vehicle position for the trip of the user in the autonomous vehicle is generated. Moreover, the autonomous vehicle can follow the route to the requested vehicle position.

Abstract: The image recognition method includes: obtaining an image data stream, wherein the image data frame includes a current frame; performing image recognition on an object in the current frame to generate a first box corresponding to the current frame; detecting movement of the object to generate a second box corresponding to the current frame; and determining the object as a tracking target according to the first box and the second box.

Abstract: To determine a path through a pose configuration space, trajectories of poses may be evaluated in parallel based at least on translating the trajectories along at least one axis of the pose configuration space (e.g., an orientation axis). A trajectory may include at least a portion of a turn having a fixed turn radius. Turns or turn portions that have the same turn radius and initial orientation can be translatively shifted along and processed in parallel along the orientation axis as they are translated copies of each other, but with different starting points. Trajectories may be evaluated based at least on processing variables used to evaluate reachability as bit vectors with threads effectively performing large vector operations in synchronization. A parallel reduction pattern may be used to account for dependencies that may exist between sections of a trajectory for evaluating reachability, allowing for the sections to be processed in parallel.

Abstract: A system for controlling operation of a vehicle during a turning maneuver includes an object detection sensor, a vehicle turning angle sensor, and a processor. A memory is communicably coupled to the processor and stores a turning alert zone module configured to determine if a speed of the vehicle is within a predetermined range of speeds and, if the speed of the vehicle is within the predetermined range of speeds, determine if a vehicle turning angle is above a predetermined threshold value. If the turning angle is above the predetermined threshold value, and using the turning angle, a turning alert zone is determined. The system may then determine if at least a portion of an object resides in the turning alert zone and, if at least a portion of an object resides in the turning alert zone, control an operation of the vehicle (for example, a braking operation).

Abstract: A driving control apparatus and method may include collecting driving information related to a subject vehicle, wherein the driving information related to the subject vehicle includes a driving lane and a vehicle width of the subject vehicle, and driving information related to another vehicle, wherein the driving information related to another vehicle includes a driving lane and a vehicle width of at least one another vehicle around the subject vehicle, generating one or more imaginary lines indicating positions in a corresponding driving lane of the another vehicle based on the driving information related to the another vehicle, determining a deflection value by which the subject vehicle needs to be deflected in the driving lane of the subject vehicle based on the imaginary line, and determining a driving path of the subject vehicle based on the determined deflection value.

Abstract: Image data are input to a machine learning program. The machine learning program is trained with a virtual boundary model based on a distance between a host vehicle and a target object and a loss function based on a real-world physical model. An identification of a threat object is output from the machine learning program. A subsystem of the host vehicle is actuated based on the identification of the threat object.

Abstract: A system comprises a sensor system comprising a sensor and an analysis engine configured to determine whether the sensor is uncalibrated. The system further comprises an error handling system configured to determine whether to perform a recalibration in response to the sensor system determining that the sensor is uncalibrated. The error handling system further comprises a recalibration engine configured to perform a recalibration.

Abstract: A global multi-vehicle decision making system is disclosed for providing real-time motion planning and coordination of one or multiple connected and automated and/or semi-automated vehicles (CAVs) in an interconnected traffic network that includes one or multiple non-controlled vehicles (NCVs), one or multiple conflict zones and one or multiple conflict-free road segments. The system includes a receiver configured to acquire infrastructure sensing signals, at least one memory configured to store map and programs, and at least one processor configured to perform steps of formulating a global mixed-integer programming (MIP) problem using the infrastructure sensing signals, computing a motion plan for each CAV and each NCV in the traffic network by solving the global MIP problem, computing an optimal sequence of entering/exiting times and a sequence of average velocities for each CAV and each NCV, and computing a velocity profile and/or one or multiple planned stops for each CAV.

Abstract: Sensor data identifying an emergency vehicle approaching the autonomous vehicle may be received. A predicted trajectory for the emergency vehicle may be received. Whether the autonomous vehicle is impeding the emergency vehicle may be determined based on the predicted trajectory and map information identifying a road on which the autonomous vehicle is currently traveling. Based on a determination that the autonomous vehicle is impeding the emergency vehicle, the autonomous vehicle may be controlled in an autonomous driving mode in order to respond to the emergency vehicle.

Abstract: Provided is a work support apparatus for a work machine including a lower traveling body, an upper turning body mounted on the lower traveling body, and a work device attached to the upper turning body. The work support apparatus, which provides a captured image for supporting work by the work machine, includes a flying object capable of flying over the air, an image capture device, a flight mode designation unit, and a flight control unit. The image capture device is mounted on the flying object and acquires the captured image. The flight mode designation unit designates a specific flight mode from among a plurality of flight modes set in advance for the flight action of the flying object. The flight control unit performs a flight control for making the flying object make a flight action corresponding to the flight mode designated by the flight mode designation unit.

Abstract: The present disclosure is directed toward the use of two or more autonomous vehicles, working in cooperation, to deliver an item between a source location and a destination location. For example, an autonomous ground based vehicle may transport an item from a source location to a transfer location and an autonomous aerial vehicle will transport the item from the transfer location to the destination location. The transfer location may be at any location along a navigation path between the source location and the destination location. In some examples, the transfer location may be adjacent the destination location such that the autonomous aerial vehicle is only transporting the item a short distance.

Abstract: Systems, methods and computer-readable media for selecting a trajectory for an autonomous vehicle are disclosed that include computing a current vehicle state for the autonomous vehicle based on observations by a sensing system; computing respective collision probability scores for a plurality of candidate trajectories based on the current vehicle state; computing respective information gain scores for the plurality of candidate trajectories based on the current vehicle state, the information gain score for each candidate trajectory indicating an respective information gain for a next planning horizon interval that is subsequent to the current planning horizon interval; and selecting a planned trajectory from the plurality of candidate trajectories based on the respective collision probability scores and respective information gain scores.

Abstract: An aerodynamic deflector on the vehicle is repositionable. An actuator is coupled with the aerodynamic deflector. A controller configured to: detect a performance mode of operation of the vehicle; determine a requested lateral acceleration; calculate a control adjustment of the aerodynamic deflector to generate a downforce to achieve the requested lateral acceleration and maximize lateral grip of the vehicle; and operate the actuator to effect the control adjustment of the aerodynamic deflector to generate the downforce on the vehicle.

Abstract: A control apparatus includes an acquisition unit that acquires captured data in which an object around a moving object is captured by an imaging unit, where the moving object is one of a moving object that is irradiated with spontaneous emission light and a moving object that moves with a predetermined pattern, and a determination unit that determines that the object is an obstacle if the captured data acquired by the acquisition unit includes a specific pattern.

Abstract: Techniques for determining a warped occupancy grid fit to a vehicle trajectory are discussed herein. In some examples, a portion of memory may be allocated to an occupancy grid. Further, a warped occupancy grid can be warped and associated with an environment that an autonomous vehicle is traversing according to a trajectory and/or throughway. A transformation maybe be determined between the warped occupancy grid and the memory allocated to the occupancy grid. Sensor data can be received from a sensor associated with the autonomous vehicle and may be associated with the warped occupancy grid and stored in the occupancy grid. The autonomous vehicle may be controlled according to the warped occupancy grid by identifying sensor data returns in cells of the warped occupancy grid that may indicate a detection of an object in a path of travel of the vehicle.

Abstract: A method of determining whether a planned trajectory of a first vehicle over a road along which the first vehicle and a second vehicle are traveling, is invalid, comprising: obtaining the planned trajectory, comprising a first state of the first vehicle for each of a plurality of time instants; obtaining a second state of the second vehicle for each time instant; determining, for each time instant, a respective lateral range extending from the second vehicle; and determining that the planned trajectory is invalid where, for the first and second states at one or more of the time instants: the first vehicle is within the lateral range and within a lane boundary region of the road; and a direction of a lateral velocity of the first vehicle is towards the second vehicle and a lateral acceleration of the first vehicle away from the second vehicle is smaller than a predetermined threshold.