Abstract: A computer-implemented method for localizing a vehicle can include accessing, by a computing system comprising one or more computing devices, a machine-learned retrieval model that has been trained using a ground truth dataset comprising a plurality of pre-localized sensor observations. Each of the plurality of pre-localized sensor observations has a predetermined pose value associated with a previously obtained sensor reading representation. The method also includes obtaining, by the computing system, a current sensor reading representation obtained by one or more sensors located at the vehicle. The method also includes inputting, by the computing system, the current sensor reading representation into the machine-learned retrieval model.

Abstract: A vehicular driving assist system includes a camera disposed at a vehicle equipped with the vehicular driving assist system and viewing forward of the vehicle, the camera capturing image data. An electronic control unit (ECU) includes electronic circuitry and associated software. The electronic circuitry of the ECU includes an image processor for processing image data captured by the camera. The ECU, responsive to processing by the image processor of image data captured by the camera, determines presence of a leading vehicle traveling in front of the equipped vehicle and in the same traffic lane as the equipped vehicle. The ECU, responsive to determining presence of the leading vehicle, determines presence of a pothole in front of the vehicle and in the same traffic lane as the equipped vehicle.

Abstract: Apparatus for controlling dynamics of a vehicle determines a current course angle (?) of the vehicle. A desired course angle (?psi) is defined and assigned to a first point on a temporal profile of a desired driving line. The first point is on the desired driving line at a first preview time from a location assigned to an instantaneous vehicle position. A course angle deviation of the current course angle (?) from the desired course angle (?psi) is determined. A target angle (?ta) is defined and assigned to a second point on the temporal profile of the desired driving line. The second point is on the desired driving line at a distance of a second preview time from the location. A steering wheel angle (?) is determined as a total of the target angle (?ta) reinforced with a first parameter and the course angle deviation reinforced with a second parameter.

Abstract: A detection system for determining an articulation angle between two sub-vehicles of a vehicle combination connected in an articulated manner includes a detection device configured to detect an environment, wherein the detection device is arranged on one of the sub-vehicles of the vehicle combination and a detection region of the detection device on a sub-region of a sub-vehicle connected to the one sub-vehicle in an articulated manner is oriented so that detection signals, which characterize the sub-region on the other sub-vehicle, can be generated by the detection device and output. The detection system further includes a processing unit configured to receive the detection signals and determine the articulation angle between the two sub-vehicles based on the detection signals and a projection device designed to image a predetermined pattern onto the sub-region on the other sub-vehicle to create a pattern image on the other sub-vehicle.

Abstract: Methods and apparatus to provide accident avoidance information to passengers of autonomous vehicles are disclosed. An example apparatus includes a safety analyzer to determine an autonomously controlled vehicle is in a safe situation at a first point in time and in a dangerous situation at a second point in time. The example apparatus also includes a user interface generator to: generate user interface data to define content for a user interface to be displayed via a screen, the user interface to include a graphical representation of the vehicle, the user interface to graphically indicate the vehicle is in the safe situation at the first point in time; and modify the user interface data so that the user interface graphically indicates the vehicle is in the dangerous situation at the second point in time.

Abstract: Various technologies described herein pertain to causing presentation on a user interface of an immediate portion of a navigation route of an autonomous vehicle. A computing system of the autonomous vehicle determines whether an object detected by sensor(s) of the autonomous vehicle proximate to the immediate portion of the navigation route are of a type and relative position defined as one of consequential and inconsequential for a human passenger. In response to determining that an object has both a type and relative position defined as consequential, the computing system causes presentation on the user interface a representation of the object relative to the immediate portion of the navigation route to provide a confidence engendering indication that the autonomous vehicle has detected the object. Otherwise if inconsequential, presentation on the user interface of any representation of the object is not caused by the computing system to avoid creating a confusing presentation.

Abstract: An object-tracking method includes using the velocity of a track for tracking an object, generated from a point cloud related to the object, in a current recognition period to obtain a current velocity-based heading angle of the track. The method includes accumulating scores associated with information about the current velocity-based heading angle and incorporating the accumulated scores into a heading history having regions sectioned for respective heading angles of the track. The method includes obtaining a history-based heading angle of the track using the heading history, correcting the history-based heading angle using information about the shape of the track, and determining the result of correction to be a final heading angle in the current recognition period.

Abstract: A process for calibrating a distance and range measurement device coupled to an industrial vehicle comprises taking a first measurement of an emission from the device at a first yaw angle relative to a roll axis of the device. A second measurement of the emission at a second yaw angle relative to the roll axis is taken. The second yaw angle is within an angular tolerance of the first yaw angle but in an opposite direction. The device is calibrated relative to the roll axis when the first and second measurements are within a tolerance of each other. A third measurement of the distance and range measurement device beam emitted from the distance and range measurement device at a pitch angle is taken. If the third measurement and a virtual emission length are within a tolerance, then the device is calibrated with respect to the pitch axis.

Abstract: Methods and systems for determining an action for a vehicle. The system includes an electronic controller configured to determine a planned route of the vehicle, determine local astronomical data based upon the planned route, compare the local astronomical data to the planned route of the vehicle to determine a probability of completion of the planned route, and if the probability of completion is below a threshold, generate a command indicating an action for the vehicle.

Abstract: An autonomous driving system for an autonomous vehicle includes an automated driving controller wirelessly connected to a towing taxi. The automated driving controller determines the autonomous driving system is non-functional. In response to determining the autonomous driving system is non-functional, the automated driving controller generates a notification indicating the autonomous driving system is non-functional. The automated driving controller receives, from the towing taxi, a current data string including a data point corresponding to a current point in time in combination with a predicted data point for each of one or more predicted points of time in the future. The current data string is compared with a previous data string recorded at a previous point in time. In response to determining the current data string matches the previous data string, the automated driving controller determines one or more driving maneuvers for the autonomous vehicle based on the current data string.

Abstract: Systems and methods for initializing a robot to autonomously travel a route are disclosed. In some exemplary implementations, a robot can detect an initialization object and then determine its position relative to that initialization object. The robot can then learn a route by user demonstration, where the robot associates actions along that route with positions relative to the initialization object. The robot can later detect the initialization object again and determine its position relative to that initialization object. The robot can then autonomously navigate the learned route, performing actions associated with positions relative to the initialization object.

Abstract: A light detection and ranging device associated with an autonomous vehicle scans through a scanning zone while emitting light pulses and receives reflected signals corresponding to the light pulses. The reflected signals indicate a three-dimensional point map of the distribution of reflective points in the scanning zone. A hyperspectral sensor images a region of the scanning zone corresponding to a reflective feature indicated by the three-dimensional point map. The output from the hyperspectral sensor includes spectral information characterizing a spectral distribution of radiation received from the reflective feature. The spectral characteristics of the reflective feature allow for distinguishing solid objects from non-solid reflective features, and a map of solid objects is provided to inform real time navigation decisions.

Abstract: A vehicular vision system includes a plurality of cameras including a rear camera disposed at a rear portion of a vehicle and having at least a rearward field of view and a front camera disposed at a front portion of the vehicle and having at least a forward field of view. Responsive to processing at an electronic control unit of provided vehicle data, the vehicular vision system determines a vehicle motion vector during maneuvering of the vehicle. Responsive to image processing at the electronic control unit of frames of captured image data, the vehicular vision system determines an object present in the field of view of a camera of the plurality of cameras and determines movement of the object relative to the vehicle. The vehicular vision system compares the determined relative movement of the object to the determined vehicle motion vector to determine misalignment of the camera.

Abstract: The present disclosure describes systems and methods for providing driver assistance. A current vehicle state of a vehicle at a current timestep and an environment map representing an environment of the vehicle at least at the current timestep are obtained. Augmented reality feedback is generated including a virtual vehicle representing a predicted future vehicle state, where the predicted future vehicle state is predicted for a given future timestep based on at least one of the current vehicle state or the current environment. The generated augmented reality feedback including the virtual vehicle is outputted to be displayed by a display device.

Abstract: A mobile robot includes: a drive unit that changes a moving speed and a travel direction; a detection unit that detects a plurality of detection target objects 11; and a control unit 27 that acquires a distance Z and a direction ? to the detection target object unit, calculates a travel direction in which the distance and the direction to the detection target object satisfy a predetermined relationship, and drives and controls the drive unit on the basis of the calculated travel direction. The control unit calculates a distance x in a direction orthogonal to the movement route between the detection target object and a current position of the mobile robot and the direction to the detection target object, calculates a difference ?x between the distance x and a certain distance Xref, and executes drive control for the drive unit to cause the difference ?x to be 0 (zero).

Abstract: Disclosed are methods, devices, and computer-readable media for detecting lanes and objects in image frames of a monocular camera. In one embodiment, a method is disclosed comprising receiving a sample set of image frames; detecting a plurality of markers in the sample set of image frames using a convolutional neural network (CNN); fitting lines based on the plurality of markers; detecting a plurality of vanishing points based on the lines; identifying a best fitting horizon for the sample set of image frames via a RANSAC algorithm; computing an inverse perspective mapping (IPM) based on the best fitting horizon; and computing a lane width estimate based on the sample set of image frames using the IPM in a rectified view and the parallel line fitting.

Abstract: A vehicular vision system includes a vehicular camera disposed at a vehicle and operable to capture frames of image data. The vehicular vision system is operable to detect, via processing by an image processor of multiple frames of captured image data, when multiple objects are viewed by the vehicular camera. During a driving maneuver, and when multiple objects are detected, the vehicular vision system determines which detected object of the multiple detected objects is closest to the vehicle, and determines movement of at least the determined closest object relative to the vehicle. During the driving maneuver, and based at least in part on the determined relative movement of the determined closest object, the vehicular vision system determines whether the determined relative movement is indicative of the determined closest object being in or moving toward a position where collision may occur between the determined closest object and the vehicle.

Abstract: Methods and systems are provided for adjusting noise, vibration, and harshness (NVH) limits for a vehicle based on an occupancy level of the vehicle. The occupancy level is inferred based on a number of occupants and their position within a vehicle, and further based on a degree of interaction of a primary occupant with vehicle controls. As the occupancy level decreases, NVH constraints for operating the vehicle are reduced and one or more vehicle operating parameters nay be based on the reduced NVH constraints.

Abstract: In one embodiment, a method includes receiving sensor data corresponding to an environment external of a vehicle. The sensor data include data points. The method includes determining one or more subsets of the data points. The method includes comparing the one or more subsets of the data points to one or more predetermined data patterns. Each of the one or more predetermined data patterns corresponds to an object classification. The method includes computing a confidence score for each subset of data points of the one or more subsets of the data points as corresponding to each of the one or more predetermined data patterns based on the comparison. The method includes generating a classification for an object in the environment external of the vehicle based on the confidence score.

Abstract: Methods, systems, and apparatuses related to autonomous vehicle object detection are described. An autonomous vehicle can capture an image corresponding to an unknown object disposed within a sight line of the autonomous vehicle. Processing resources available to a plurality of memory devices associated with the autonomous vehicle can be reallocated in response to capturing the image and an operation involving the image corresponding to the unknown object to classify the unknown object can be performed using the reallocated processing resources.

Abstract: A vehicle computing system may implement techniques to determine relevance of objects detected in an environment to a vehicle operating in the environment (e.g., whether an object could potentially impact the vehicle's ability to safely travel). The techniques may include determining an initial location and trajectory associated with a detected object and determining whether the detected object may intersect a path polygon (e.g., planned path with a safety buffer) of the vehicle. A path intersection may include the detected object intersecting the path polygon or sharing a road segment with the vehicle at a substantially similar height as the vehicle (e.g., on a similar plane). Based on a determination that the detected object does not intersect the planned path of the vehicle, the vehicle computing system may determine that the detected object is irrelevant to the vehicle and may disregard the detected object in vehicle control planning considerations.

Abstract: The technology relates to using on-board sensor data, off-board information and a deep learning model to classify road wetness and/or to perform a regression analysis on road wetness based on a set of input information. Such information includes on-board and/or off-board signals obtained from one or more sources including on-board perception sensors, other on-board modules, external weather measurement, external weather services, etc. The ground truth includes measurements of water film thickness and/or ice coverage on road surfaces. The ground truth, on-board and off-board signals are used to build the model. The constructed model can be deployed in autonomous vehicles for classifying/regressing the road wetness with on-board and/or off-board signals as the input, without referring to the ground truth.

Abstract: Sensing systems for agricultural equipment and related methods may be configured for detecting the operating state of rotating elements in agricultural implements. The sensing systems for an agricultural implement may include a rotating element and a monitoring center equipped with an alert mechanism. The sensing systems may include an inertial sensor, a microprocessor, a communication element, and a power supply. The sensing system may be a single element fixed directly to the rotating element.

Abstract: In one embodiment, a LIDAR device of an autonomous driving vehicle (ADV) includes an array of light emitters to emit a number of light beams to sense a physical range associated with a target. The LIDAR device further includes a slope mirror having a slope surface and a flat surface supported by a rotatable platform. The rotatable platform is configured to rotate with respect to a vertical axis perpendicular to the flat surface. The light emitters are configured to project the light beams onto the slope surface of the slope mirror, which are deflected towards the target. The slope mirror rotates along with the rotatable platform while the array of light emitters remains steady. The LIDAR device further includes one or more light detectors to receive at least a portion of the light beams reflected from the target.

Abstract: A pool cleaner control system is provided. The pool cleaner control system includes a pool cleaner having an imaging device and a controller. The imaging device is configured to acquire at least one image of an aquatic environment. The controller is in communication with the imaging device. The controller identifies candidate debris from the at least one image, analyzes at least two potential candidate debris-containing pathways, and determines which of the at least two potential candidate debris-containing pathways is an optimal cleaning pathway.

Abstract: A system and method for identifying a type of vehicle occupant based on locations of a portable device that include receiving a plurality of communication signals from the portable device and evaluating received signal strength measurements of the plurality of communication signals to determine a tracking pattern that includes a tracked path of the portable device as a user approaches a vehicle, enters the vehicle, and is seated within a particular seat of the vehicle. The system and method also include identifying the user as a driver of the vehicle or a non-driving occupant of the vehicle based on the tracking pattern and controlling at least one vehicle system by executing vehicle settings associated with the driver of the vehicle and the non-driving occupant of the vehicle based on identifying the user as the driver of the vehicle or the non-driving occupant of the vehicle.

Abstract: In one implementation, a method of blind object tracking is performed at a device including one or more processors and non-transitory memory. The method includes obtaining a first three-dimensional scene model of a physical environment during a first time period including a first plurality of points, wherein each of the first plurality of points is associated with a set of coordinates in a three-dimensional space, wherein a subset of the first plurality of points is associated with a particular cluster identifier. The method includes obtaining a second three-dimensional scene model of the physical environment during a second time period subsequent to the first time period including a second plurality of points, wherein each of the second plurality of points is associated with a set of coordinates the three-dimensional space.

Abstract: A visualization device includes a camera for continuously detecting the surroundings and, when the camera is oriented towards the interior or the exterior shell of a real vehicle, generating a real vehicle image which can change depending on the camera orientation. A data storage unit stores at least one component data set. The data set contains data, on the basis of which the visual representation of at least one vehicle component is possible. A computing device is programmed to integrate the representation of the vehicle component into the real vehicle image while taking into consideration the scale and perspective and to generate a virtual vehicle image that represents the real vehicle together with the virtually installed vehicle component. A display device displays the virtual vehicle image. A method for visualizing the interior or exterior of a vehicle is also provided.

Abstract: A vaporized aerosol detection system is presented herein. The system can include a motion sensor that is configured to detect movement in a predetermined or desired area. Further, the motion sensor can be configured to generate a detection signal in response to one or more detected objects in the area. The system can also include a particle sensor electronically coupled to the motion sensor. The particle sensor can be configured to detect a particle count of the area when the objects are detected by the motion sensor. Further, the system can include a housing configured to enclose at least a portion of the motion sensor and particle sensor.

Abstract: Wireless communications are described. Cells may be grouped into a plurality of cell groups. A wireless device may determine that a secondary cell has an invalid scheduling request (SR) resource based on one or more conditions. The wireless device may send a preamble if the secondary cell has an invalid SR resource.

Abstract: A vehicle display device, that includes: a first display device provided inside a vehicle cabin; a second display device provided inside the vehicle cabin and separately from the first display device; a memory; and a processor connecting to the memory and being configured to: set a running plan of a vehicle, to display a scheduled action of the vehicle on the first display device based on the running plan, and to display the scheduled action on the second display device in a case in which at least one of a distance to, or a time interval until, the scheduled action has reached a prescribed value or less.

Abstract: A method, system and robot, wherein the robot includes two or more sensing devices, sensor A and sensor B, mounted thereon and moves forward along an axis parallel to the rows of plants, being autonomously steered by exerting angular corrections to place the robot as close as possible to the centerline between the rows of plants, wherein the method and system includes the following: (ii) dividing a two-dimensional grid of square cells into groups of cells; (iii) obtaining data points using sensor A and sensor B; (vii) moving the robot: (a) by turning right; or (b) by turning left; or (c) forward without turning, depending on whether each group of cells is calculated as low-activated, high-activated or not activated using the data points.

Abstract: Automated inventory management and material (or container) handling removes the requirement to operate fully automatically or all-manual using conventional task dedicated vertical storage and retrieval (S&R) machines. Inventory requests Automated vehicles plan their own movements to execute missions over a container yard, warehouse aisles or roadways, sharing this space with manually driven trucks. Automated units drive to planned speed limits, manage their loads (stability control), stop, go, and merge at intersections according human driving rules, use on-board sensors to identify static and dynamic obstacles, and human traffic, and either avoid them or stop until potential collision risk is removed. They identify, localize, and either pick-up loads (pallets, container, etc.) or drop them at the correctly demined locations. Systems without full automation can also implement partially automated operations (for instance load pick-up and drop), and can assure inherently safe manually operated vehicles (i.

Abstract: Aspects of the present disclosure relate to a vehicle for maneuvering an occupant of the vehicle to a destination autonomously as well as providing information about the vehicle and the vehicle's environment for display to the occupant.

Abstract: The disclosed technology provides solutions for detecting and localizing road signage, such as speed limit signs. A process of the disclosed technology can include steps for receiving a first set of sensor data comprising a signage feature, wherein the first set of sensor data is associated with a first location, receiving a second set of sensor data comprising the signage feature, wherein the second set of sensor data is associated with a second location, and determining a location of the signage feature based on the first location and the second location. Systems and machine-readable media are also provided.

Abstract: A method and apparatus for recognizing a sign language or a gesture by using a three-dimensional (3D) Euclidean distance matrix (EDM) are disclosed. The method includes a two-dimensional (2D) EDM generation step for generating a 2D EDM including information about distances between feature points of a body recognized in image information by a 2D EDM generator, a 3D EDM generation step for receiving the 2D EDM and generating a 3D EDM by using a first deep learning neural network trained with training data in which input data is a 2D EDM and correct answer data is a 3D EDM by a 3D EDM generator, and a recognition step for recognizing a sign language or a gesture based on the 3D EDM.

Abstract: Systems and methods to combine lights and cameras are disclosed. Exemplary implementations may carry a housing that holds both a lighting component and a video camera; receive instructions to operate the lighting component in at least one of two different lighting modes, including a landing lighting mode and a taxi lighting mode; control the video camera to capture video information at a particular frame rate; and control the lighting component to emit light in a manner that supports at least one particular lighting mode and that includes switching off or turning down the lighting component in synchrony with the particular frame rate to reduce glare and/or otherwise improve the captured video information.

Abstract: There is provided a method for detecting a lane marking using a processor including acquiring a drive image captured by an image capturing device of a vehicle which is running, detecting an edge corresponding to a lane marking from the acquired drive image and generating an edge image based on the detected edge, detecting a linear component based on the detected edge and generating a linearly processed edge image based on the detected linear component, detecting a lane marking point corresponding to the lane marking using the generated edge image and the linearly processed edge image, and detecting the lane marking based on the detected lane marking point.

Abstract: A moving apparatus that performs control to stop the moving apparatus at a position close to a user and to rotate the moving apparatus at a stop position, thereby making it easy to take out a product carried on the apparatus. The moving apparatus includes a control unit that executes traveling control of the moving apparatus, an upper unit that has an article storage unit, and a lower unit that houses a drive unit, in which the control unit inputs detection information of a sensor, and executes control to stop the moving apparatus at a position close to a user and rotate the moving apparatus at a stop position on the basis of input sensor detection information. The control unit performs display control of a traveling route recognition display line indicating a traveling route of the moving apparatus.

Abstract: The disclosure relates to a moving apparatus for cleaning, a collaborative cleaning system, and a method of controlling the same, the moving apparatus for cleaning including: a cleaner configured to perform cleaning; a traveler configured to move the moving apparatus; a communicator configured to communicate with an external apparatus; and a processor configured to identify an individual cleaning region corresponding to the moving apparatus among a plurality of individual cleaning regions assigned to the moving apparatus and at least one different moving apparatus based on current locations throughout a whole cleaning region, based on information received through the communicator, and control the traveler and the cleaner to travel and clean the identified individual cleaning region. Thus, the individual cleaning regions are assigned based on the location information about the plurality of cleaning robots, and a collaborative clean is efficiently carried out with a total shortened cleaning time.

Abstract: Systems and methods are provided that may to cause autonomous navigation of autonomous vehicles in the case of non-standard traffic flows such as police stops, emergency vehicle passing, construction sites, vehicle collision sites, and other non-standard road conditions. An entity associated with the non-standard traffic flow (e.g., an emergency vehicle, road sign, barrier, etc.) may transmit or broadcast a control signal to be received (or otherwise detected) at one or more autonomous vehicles. Each autonomous vehicle, upon receiving the control signal, may autonomously navigate in accordance with the control signal, thus mitigating or eliminating dangers associated with non-standard traffic flows.

Abstract: The present invention relates to a method for acquiring an object information, the method comprising: obtaining an input image acquired by capturing a sea; obtaining a noise level of the input image; when the noise level indicates a noise lower than a predetermined level, acquiring an object information related to an obstacle included in the input image from the input image by using a first artificial neural network, and when the noise level indicates a noise higher than the predetermined level, obtaining a noise-reduced image of which the environmental noise is reduced from the input image by using a second artificial neural network, and acquiring an object information related to an obstacle included in the sea from the noise-reduced image by using the first artificial neural network.

Abstract: A navigational system for a host vehicle may comprise at least one processing device. The processing device may be programmed to receive a first output and a second output associated with the host vehicle and identify a representation of a target object in the first output. The processing device may determine whether a characteristic of the target object triggers a navigational constraint by verifying the identification of the target object based on the first output and, if the at least one navigational constraint is not verified based on the first output, then verifying the identification of the target object based on a combination of the first output and the second output. In response to the verification, the processing device may cause at least one navigational change to the host vehicle.

Abstract: A processor-implemented method and system for determining a predictive occupancy grid map (OGM) for an autonomous vehicle are disclosed. The method includes: receiving a set of OGMs including a current predicted OGM and one or more future predicted OGMs, the current OGM associated with a current timestamp and each future predicted OGM associated with a future timestamp; generating a weight map associated with the current timestamp based on one or more kinodynamic parameters of the vehicle at the current time stamp, and one or more weight map associated with a future timestamp; generating a set of filtered predicted OGMs by filtering the current predicted OGM with the weight map associated the current timestamp and filtering each respective future predicted OGM associated with a future timestamp with the weight map associated with the respective future timestamp; and sending a single predicted OGM to a trajectory generator.

Abstract: There is provided a mobile robot that performs the obstacle avoidance, positioning and object recognition according to image frames captured by the same optical sensor. The mobile robot includes an optical sensor, a light emitting diode, a laser diode and a processor. The processor identifies an obstacle and a distance thereof according to image frames captured by the optical sensor when the laser diode is emitting light. The processor further performs the positioning and object recognition according to image frames captured by the optical sensor when the light emitting diode is emitting light.

Abstract: A method for road surface detection includes receiving ranging data including a plurality of ranging data points, extracting one or more ranging data points lying within a height range from the plurality of ranging data points, dividing the one or more ranging data points into one or more grid cells, setting a first horizontal position of a first cell point of a first grid cell of the one or more grid cells as being centered on the first grid cell, setting a first vertical position of the first cell point, and detecting the road surface based on the first vertical position and first horizontal position of the first cell point.

Abstract: A method and system for estimating surface roughness of a ground for an off-road vehicle to control ground speed comprises detecting motion data of an off-road vehicle traversing a field or work site during a sampling interval. A pitch sensor is adapted to detect pitch data of the off-road vehicle for the sampling interval to obtain a pitch acceleration. A roll sensor is adapted to detect roll data of the off-road vehicle for the sampling interval to obtain a roll acceleration. An electronic data processor or surface roughness index module determines or estimates a surface roughness index based on the detected motion data, pitch data and roll data for the sampling interval. The surface roughness index can be displayed on the graphical display to a user or operator of the vehicle, or applied to control or execute a ground speed setting of the vehicle.

Abstract: A vehicle receives sensor data from at least one of its sensors as it approaches an intersection and determines whether a traffic flow control device for the intersection is detected. When detected, a detected type, a detected state, or both of the traffic flow control device is determined. Using a type of the intersection, at least one of an existing type or an existing state of the traffic flow control device is determined, where the traffic flow control device is undetected or the detected type, the detected state, or both are determined with a detection confidence less than a defined level of detection confidence. The traffic flow control device is tagged with a label including its location and existing type, the existing state, or both within at least one control system for the vehicle. The vehicle is operated within vehicle transportation network using a control system that incorporates the label.

Abstract: Systems and methods for facilitating communication with autonomous vehicles are provided. In one example embodiment, a computing system can obtain a first type of sensor data (e.g., camera image data) associated with a surrounding environment of an autonomous vehicle and/or a second type of sensor data (e.g., LIDAR data) associated with the surrounding environment of the autonomous vehicle. The computing system can generate overhead image data indicative of at least a portion of the surrounding environment of the autonomous vehicle based at least in part on the first and/or second types of sensor data. The computing system can determine one or more lane boundaries within the surrounding environment of the autonomous vehicle based at least in part on the overhead image data indicative of at least the portion of the surrounding environment of the autonomous vehicle and a machine-learned lane boundary detection model.

Abstract: Systems and methods navigate a vehicle by determining a free space region in which the vehicle can travel. In one implementation, a system may include at least one processor programmed to receive from an image capture device, a plurality of images associated with the environment of a vehicle, analyze at least one of the plurality of images to identify a first free space boundary on a driver side of the vehicle and extending forward of the vehicle, a second free space boundary on a passenger side of the vehicle and extending forward of the vehicle, and a forward free space boundary forward of the vehicle and extending between the first free space boundary and the second free space boundary. The first free space boundary, the second free space boundary, and the forward free space boundary may define a free space region forward of the vehicle.