Abstract: A mobile robot of the present disclosure includes: a traveling unit configured to move a main body; a lidar sensor configured to acquire terrain information outside the main body; a camera sensor configured to acquire an image outside the main body; and a controller configured to fuse the image and a detection signal of the lidar sensor to select a front edge for the next movement and set a target location of the next movement at the front edge to perform mapping travelling. Therefore, in a situation where there is no map, the mobile robot can provide an accurate map with a minimum speed change when travelling while drawing the map.

Abstract: A vehicle includes a storage device configured to store an estimation algorithm configured to output a degree of deterioration of a component mounted on the vehicle in response to an input of a value of a parameter related to the component, a sensor configured to detect the value of the parameter, and a control device. The control device is configured to execute a performance test by autonomous driving of the vehicle, acquire data indicating performance of the component during the performance test, and update the estimation algorithm by using the data acquired during the performance test.

Abstract: A manager installed in a vehicle includes: a first accepting unit that accepts a plurality of kinematic plans from a plurality of ADAS applications; an arbitration unit that arbitrates the kinematic plans; a calculation unit that calculates a motion request based on an arbitration result by the arbitration unit; and a distribution unit that distributes the motion request to at least one actuator system, wherein the first accepting unit accepts information relating to the actuator system to which the distribution unit distributes the motion request from the ADAS applications, along with the kinematic plans.

Abstract: Described herein relates to a system and method for system of and method for optimizing real-time workplace safety monitoring by facilitating hazard avoidance within an industrial environment. In an embodiment, the global access protection (hereinafter “GAP”) system may comprise a computing device comprising at least one processor, such that the computing device may be communicatively coupled to at least one Global Positioning System (hereinafter “GPS”) system. Additionally, in this embodiment, the computing device may be integrated within the at least one beacon and/or the at least one receiver. In this manner, the at least one beacon and/or at least one receiver may be configured to output and/or input a GPS, RTK GPS, and/or any positioning system known in the art, such that the GAP system may be configured to determine a distance between the at least one beacon and the at least one receiver within the industrial environment.

Abstract: Techniques for determining a safety area for a vehicle are discussed herein. In some cases, a first safety area can be based on a vehicle travelling through an environment and a second safety area can be based on a steering control or a velocity of the vehicle. A width of the safety areas can be updated based on a position of a bounding box associated with the vehicle. The position can be based on the vehicle traversing along a trajectory. Sensor data can be filtered based on the sensor data falling within the safety area(s).

Abstract: Methods, systems, and programs are presented for detecting impaired views in monitoring cameras. One method includes training a rotation classifier with unsupervised learning utilizing a first set of images. The rotation classifier is configured to receive an input image and generate a rotation feature embedding for the input image. In addition, the method includes training an impairment classifier with supervised learning utilizing a second set of images, impairment labels for each of the second set of images, and the rotation feature embedding, generated by the rotation classifier, for each of the second set of images. The method further includes accessing a vehicle image captured by a camera on a vehicle, and providing the vehicle image to the impairment classifier as input, and the impairment classifier outputs a camera impairment from a set of camera impairment categories. Further, the vehicle image and the camera impairment are presented on a user interface.

Abstract: The disclosure relates to a lane departure warning method and a lane departure warning system. The lane departure warning method of the disclosure includes: a warning area calculation step in which a warning area for lane departure of a vehicle is calculated based on information about the vehicle and information around the vehicle; a decision making step in which a current position of the vehicle is compared with the warning area calculated in the warning area calculation step, to determine whether the vehicle is located in the warning area and output a decision instruction; and a warning step in which a warning action is performed based on the decision instruction. According to the disclosure, a lane departure status of the vehicle can be more accurately estimated and timely warning can be performed when there is a tendency for lane departure.

Abstract: A communication device includes a target locating unit configured to locate a position of a target having a risk of approaching a moving body. The communication device includes a transmission unit configured to transmit request information including positional information of an external terminal, for which the positional information is requested, based on the position of the target located by the target locating unit. The communication device includes a reception unit configured to receive response information with respect to the request information. The transmission unit is configured to transmit warning information based on the positional information of the external terminal included in the response information.

Abstract: In a method and control device for providing feedback to a vehicle occupant, a signal corresponding to current and/or upcoming movements of the vehicle is obtained when the vehicle is in an autonomous driving mode. The obtained signal is provided to a control device located within the cabin of the vehicle. The control device is moved corresponding to the provided signal. In an embodiment, an input of the occupant for an autonomous driving unit of the vehicle via the control device is received and a signal corresponding to the received input is submitted to the autonomous driving unit. The input may correspond to a maneuver request and/or to a selection of one of several autonomous driving-modes.

Abstract: This disclosure describes systems and methods used in the development and validation of autonomous vehicles ability to track objects with sensors. This application describes a self-propelled autonomous platform and methods for carrying a pedestrian, cyclist or vehicular type target in a predetermined pattern during one or more testing runs. The self-propelled autonomous platform includes a sensor configured to retract within a platform housing of the self-propelled autonomous platform when being driven over during a test run.

Abstract: An apparatus for determining sections for map update includes a processor configured to calculate a score indicating the degree of improvement of drivers' convenience provided by generating or updating map information regarding two or more road sections selected from road sections where the map information is unavailable, based on handover costs between autonomous driving and manual driving, calculate the score while replacing one or more of the two or more selected road sections with one or more unselected road sections, and identify the two or more selected road sections corresponding to a score for the case where the degree of improvement of drivers' convenience is the highest among the scores calculated before the score satisfies a predetermined end condition, as target road sections for generating or updating the map information.

Abstract: A device may receive a first type of data identifying measurements associated with user devices and/or base stations of a mobile radio environment, and a second type of data identifying spatiotemporal behavior associated with the user devices. The device may train a first model, with the first type of data, to generate a trained first model that yields dimensionality-reduced spatiotemporal characteristics of the first type of data, and may train a second model, with the second type of data and the dimensionality-reduced spatiotemporal characteristics, to generate a trained second model. The device may receive particular data identifying measurements associated with a user device and/or base stations, and may process the particular data, with the trained first model, to generate a dimensionality-reduced spatiotemporal characteristic of the particular data.

Abstract: A system comprises a computer including a processor and a memory. The memory includes instructions such that the processor is programmed to: receive intermediate concept constraints at a neural network and train the neural network with training data, training labels, and the at least one of the data constraint, the feature constraint, or the intermediate concept constraint.

Abstract: A system 100 for remote assistance of an autonomous agent can include and/or interface with any or all of: a sensor suite 110, a computing system 120, a communication interface 130, and/or any other suitable components. The system can further optionally include a set of infrastructure devices 140, a teleoperator platform 150, and/or any other suitable components. The system 100 functions to enable information to be exchanged between an autonomous agent and a tele-assist. Additionally or alternatively, the system 100 can function to operate the autonomous agent (e.g., based on remote inputs received from a teleoperator, indirectly, etc.) and/or can perform any other suitable functions.

Abstract: Methods and devices for generating data for controlling a Self-Driving Car (SDC) are disclosed. The method includes: receiving a section of a road map corresponding to surroundings of the SDC and at least one object, generating predicted trajectories including potential future location points of the at least one object, mapping the potential future location points on the section of the road map, computing a score for each of the potential future location points, computing an aggregated score from the scores corresponding to the potential future location points, and based on the aggregated score, determining a predicted location of the at least one object at the future instance of time.

Abstract: The techniques and systems herein enable robot management in populated areas. Specifically, a robot management system receives, from a robot system, a requested route and time for the robot system to travel. A dynamic map that includes dynamic and temporal information about an area of the requested route is then used to determine whether the requested route and time are approved, approved with a modified route or time, or disapproved. An approval message, a modified approval message, or a disapproval message is then generated and sent to the robot system. By using the described techniques, municipalities can monitor, manage, and regulate robots across various operators and locations. Doing so may prevent a high density of robots along various routes, disruptions to the services of such robots, and/or disruptions to surrounding pedestrians and vehicles.

Abstract: An autonomous driving control apparatus for a vehicle includes: a processor that determines whether a current driving condition of the vehicle is a limit situation during an autonomous driving control. When the limit situation is determined, the processor demands to transfer a control authority to a user of the vehicle, and if the control authority is not transferred to the user, the processor starts a minimum risk maneuver and controls engagement of an electronic parking brake device when the vehicle is stopped after the minimum risk maneuver ends. The autonomous driving control apparatus further includes a storage configured to store driving condition data of the vehicle and a set of instructions executed by the processor.

Abstract: Upon determining that a vehicle is operating at an off-road location, a control parameter for the vehicle can be adjusted to compensate for data from a vehicle sensor affected by operating at the off-road location. The vehicle can then be operated at the off-road location according to the adjusted control parameter.

Abstract: In one embodiment, a method includes receiving sensor data associated with an object external to a vehicle. The sensor data includes a sequence of data packets. Each data packet corresponds to a time frame in a sequence of time frames. The method includes determining a classification of the object based at least on the sensor data, determining that a particular data packet corresponding to a particular time frame in the sequence of time frames is corrupt or missing, generating a replacement data packet based on one or more data packets that correspond to one or more time frames adjacent to the particular time frame, generating a sequence of visual representations of the object corresponding to the sequence of time frames. At least one visual representation in the sequence of visual representations corresponding to the particular time frame is generated based on the replacement data packet.

Abstract: In one embodiment, a method includes receiving sensor data from a sensor array of a vehicle while traveling on a road. The method includes determining a confidence score for a classification of an object based on the sensor data. The method includes generating an object graphic corresponding to the object based on the confidence score for the classification of the object. The method includes retrieving, from one or more third-party systems, third-party data associated with an environment in proximity to the object and associated with the road based on the classification. The method includes generating an overlay graphic corresponding to the environment in proximity to the object based on the third-party data. The method includes providing for display the object graphic rendered in association with the overlay graphic corresponding to the environment.

Abstract: Provided is a vehicle control device including: a storage device storing a program; and a hardware processor executing the program stored in the storage device to: recognize a surrounding situation of a vehicle; determine whether or not the surrounding situation includes a road division line; control steering and acceleration/deceleration of the vehicle; determine a driving mode of the vehicle as any one of a plurality of driving modes including a first driving mode and a second driving mode; and set, when the vehicle is traveling in the second driving mode, the surrounding situation is determined not to include a road division line, and a preceding vehicle is recognized within a first predetermined distance in a traveling direction of the vehicle, a longer traveling continuation distance in the second driving mode using the map information.

Abstract: An example operation includes detecting, by a vehicle, a location of a first potential passenger proximate to a road; determining, by the vehicle, a first road safety level of a pick-up for the first potential passenger; denying, by the vehicle, the pick-up for the first potential passenger when the determined first road safety level is below a threshold; determining, by the vehicle, a second road safety level of a pick-up for a second potential passenger; and picking up, by the vehicle, the second potential passenger, when the second road safety level is above the threshold.

Abstract: The present disclosure relates to a method for controlling a control system of a vehicle having a first driver support module (e.g. ADAS feature) and a second driver support module (e.g. “under-development” ADS feature). The first driver support module and the second driver support module are capable of operation within an overlapping operational design domain (ODD). The method includes obtaining sensor data including information about a surrounding environment of the vehicle and determining fulfilment of the overlapping ODD based on the obtained sensor data. Further, if the overlapping ODD is fulfilled, the method includes switching between a first configuration where the first driver support module is active and the second driver support module is inactive, and a second configuration where the first driver support module is inactive and the second driver support module is active.

Abstract: A traveling control apparatus includes at least one processor. The at least one processor is configured to function as a driving assistance controller. The driving assistance controller is configured to delay a change in a lateral position of a preceding vehicle traveling ahead of the vehicle to obtain a delay lateral position of the preceding vehicle, and provide steering control that causes the vehicle to track the preceding vehicle on a basis of the delayed lateral position of the preceding vehicle.

Abstract: A method for controlling movement of a robot on a plurality of tracks laid out on a frame structure forming a grid includes detecting a current speed and an angular position for one wheel in a pair of wheels of the robot; tracking a current position of the robot relative to at least a portion of the frame structure; and setting a driving sequence for the pair of wheels, based on a position information of the robot.

Abstract: One example method includes gathering, by a domain adversarial neural network model deployed in an autonomous vehicle operating in a domain, a dataset that comprises unsegmented and unlabeled image data about the domain, sampling the dataset to create an adapted domain dataset, detaching a domain classifier from the domain adversarial neural network, using the domain classifier as a domain change detector model to predict a class of the unsegmented and unlabeled image data in the adapted domain dataset, and based on the class, either: determining that the domain is changed or is unknown; or, determining that the domain has not changed.

Abstract: Disengagement of an autonomous driving mode based on vehicle operating conditions, including: receiving, from a steering torque sensor, torque sensor data indicating an amount of torque applied to a steering system of an autonomous vehicle; determining a predicted torque based on one or more motion attributes of the steering system of the autonomous vehicle; determining an estimated operator-provided torque as a differential between the predicted torque and the amount of torque; selecting a threshold from a plurality of thresholds, wherein each threshold of the plurality of thresholds corresponds to a different possible operating condition of the autonomous vehicle; and disengaging an autonomous driving mode of the autonomous vehicle based on the differential exceeding the threshold.

Abstract: A vehicle control device includes: a recognizer configured to recognize a surrounding situation of a vehicle; a driving controller; an acquirer configured to acquire map information including lane information near the vehicle and reference information for identifying a position of the vehicle; and an identifier configured to identify a traveling lane of the vehicle out of one or more lanes included in a road on which the vehicle is traveling from the map information. The identifier is configured to set a reference lane on which the vehicle travels based on the number of lanes acquired from the map information and type information of lane markings near the vehicle recognized or information of an object capable of identifying a lane position and to identify the traveling lane of the vehicle based on the set reference lane, behavior of the vehicle, and an increase or decrease in the number of lanes.

Abstract: Aspects of the invention relate generally to autonomous vehicles. The features described improve the safety, use, driver experience, and performance of these vehicles by performing a behavior analysis on mobile objects in the vicinity of an autonomous vehicle. Specifically, the autonomous vehicle is capable of detecting nearby objects, such as vehicles and pedestrians, and is able to determine how the detected vehicles and pedestrians perceive their surroundings. The autonomous vehicle may then use this information to safely maneuver around all nearby objects.

Abstract: A system for filtering RADAR data includes one or more graphical processing units (GPUs) for performing steps of a filtering process in parallel. For example, a first GPU or first portion of GPU circuitry calculates a threshold parabola for a tensor of RADAR data. In parallel, a second GPU or second portion of GPU circuitry separately reduces and indexes the tensor for comparison to the threshold parabola. The threshold parabola is compared to reduced and indexed data to filter the RADAR data. Importance sampling can also be used to reduce data, e.g., if the RADAR data includes four dimensions (range, Doppler, azimuth, and elevation).

Abstract: Approaches for top speed dependent operational parameter configuration are disclosed. An operational parameter to be used by an autonomous vehicle is received. Operational modes and corresponding operational regions are determined based on the received operational parameter. A first set of autonomous vehicle parameters are determined and set based on the received operational parameter. A second set of autonomous vehicle parameters are determined and set based on the first set of autonomous vehicle parameters.

Abstract: Techniques for generating a prediction about a vehicle environment and for controlling the vehicle based on the prediction are described herein. In some cases, a prediction about a vehicle environment can be determined based on at least one of contextual data associated with the vehicle environment, object state data associated with an object (e.g., another vehicle) in the vehicle environment, or image data associated with the object.

Abstract: An embodiment apparatus for controlling a driving mode of a robo-taxi includes a communication device configured to provide a communication interface with a master key and a controller configured to change the driving mode of the robo-taxi based on a control signal from the master key. An embodiment method of controlling a driving mode of a robo-taxi includes receiving a control signal from a master key and changing the driving mode of the robo-taxi based on the control signal from the master key.

Abstract: Mobile computing network programming for queried content capture is performed by receiving, from a client device, a query for a target content of data capturable by a fleet of mobile computing networks, the query including a target content identifier that identifies the target content, programming a task to capture the target content, the task programmed to be executed by each mobile computing network using available resources of the mobile computing network, transmitting the task to each mobile computing network; and receiving data including the target content from each mobile computing network among the fleet of mobile computing networks.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for agent trajectory prediction using vectorized inputs.

Abstract: A robot is provided. The robot includes a driving part, a three dimensional (3D) depth sensor, a memory storing instructions, and a processor connected to the driving part, the 3D depth sensor, and the memory. The processor is configured to execute the instructions to acquire a depth image of a driving surface photographed by the 3D depth sensor while the robot is driving in a space, acquire, based on the acquired depth image, location information of a boundary area where tilt information of the driving surface is changed, acquire type information corresponding to an outside area of the boundary area based on the acquired location information of the boundary area and the changed tilt information, and control the driving part based on the acquired type information.

Abstract: A system including a vehicle having a network comprising a plurality of end points and a controller, where the controller includes an automation definition circuit, an automation management circuit, and an automation execution circuit. The automation definition circuit is structured to interpret an automation description. The automation management circuit is structured to provide an automated action plan in response to the automation description, and to store the automated action plan as a data file on a data storage communicatively coupled to the controller. The automation execution circuit is structured to provide an automation command in response to the automated action description, where an end point of the plurality of end points is responsive to the automation command to implement an automated vehicle response.

Abstract: A vehicle for performing an autonomous parking function, the vehicle including: at least one camera configured to acquire a surrounding image of a vehicle; a display; a storage configured to store a HD map of a parking lot including an autonomous parking preparation zone; and at least one process configured to, based on the surrounding image of the vehicle being processed, generate a surround view image, based on an upper end of a road mark defining the autonomous parking preparation zone being recognized in the surround view image, track a position of the upper end of the road mark, upon the vehicle being stopped while a part of the road mark is recognized, correct a starting point on the HD map of the parking lot based on the position of the upper end of the road mark, and upon a user input for performing an autonomous parking function being received, perform the autonomous parking function based on the correct starting point.

Abstract: The technology relates to camera systems for vehicles having an autonomous driving mode. An example system includes a first camera mounted on a vehicle in order to capture images of the vehicle's environment. The first camera has a first exposure time and being without an ND filter. The system also includes a second camera mounted on the vehicle in order to capture images of the vehicle's environment and having an ND filter. The system also includes one or more processors configured to capture images using the first camera and the first exposure time, capture images using the second camera and the second exposure time, use the images captured using the second camera to identify illuminated objects, use the images captured using the first camera to identify the locations of objects, and use the identified illuminated objects and identified locations of objects to control the vehicle in an autonomous driving mode.

Abstract: Provided are a method, a server, and a computer program for creating a road network map to design a driving plan for an autonomous driving vehicle. A method of creating a road network map to design a driving plan for an autonomous driving vehicle is performed by a computing device and includes: generating road network data for an area; generating lattice road network data for a short-term driving plan for an autonomous driving vehicle using the generated road network data; and generating a crossable dipole graph for a long-term driving plan for the autonomous driving vehicle using the generated lattice road network data.

Abstract: Aspects of the disclosure provide for controlling a vehicle in an autonomous driving mode. For instance, sensor data for an object as well as a plurality of predicted trajectories may be received. Each predicted trajectory may represent a plurality of possible future locations for the object. A grid including a plurality of cells, each being associated with a geographic area, may be generated. Probabilities that the object will enter the geographic area associated with each of the plurality of cells over a period of time into the future may be determined based on the sensor data in order to generate a heat map. One or more of the plurality of predicted trajectories may be compared to the heat map. The vehicle may be controlled in the autonomous driving mode based on the comparison.

Abstract: A control signal related to a road segment is received by a processor of a vehicle from a remote server. Using at least a portion of the control signal, a cruise control parameter for controlling the vehicle is obtained. Responsive to determining that a cruise control module of the vehicle is enabled, the cruise control module is configured to use the cruise control parameter. The cruise control module operates to maintain the cruise control parameter for the vehicle.

Abstract: Aspects of the disclosure provide for determining when to provide and providing secondary disengage alerts for a vehicle having autonomous and manual driving modes. For instance, while the vehicle is being controlled in the autonomous driving mode, user input is received at one or more user input devices of the vehicle. In response to receiving the user input, the vehicle may be transitioned from the autonomous driving mode to a manual driving mode and provide a primary disengage alert to an occupant of the vehicle regarding the transition. Whether to provide a secondary disengage alert may be determined based on at least circumstances of the user input. After the transition, the secondary disengage alert may be provided based on the determination.

Abstract: A method of determining a vehicle travel trajectory, an electronic device, a storage medium and a vehicle, which relate to a field of an artificial intelligence technology, in particular to a field of autonomous driving and intelligent transportation. A specific implementation solution includes: determining an initial path information for a vehicle; optimizing the initial path information to generate a target optimized path information; determining an optimized mapping relationship for velocity according to the target optimized path information and a first energy consumption constraint parameter; and determining an optimized trajectory for the vehicle according to the target optimized path information and the optimized mapping relationship for velocity.

Abstract: Mobile computing network queried content capture is performed by receiving, from a server, a task executable by a mobile computing network, and a retention policy, executing the task using the mobile computing network to capture target content, assigning, to a first instance of captured target content, a probability of reducing based on the retention policy, reducing, in response to an amount of available storage becoming equal to or lower than a threshold amount, at least one of the first instance and a portion of other stored data based on the probability of reducing, and transmitting, in response to connecting to a wide area network, each instance of captured target content.

Abstract: Devices, systems and methods for remote safe driving of an autonomous vehicle are described. One exemplary method includes selecting, based on a classification of driver behavior, at least one of a set of driving actions and transmitting, to a vehicle over a secure communication channel, the at least one of the set of driving actions.

Abstract: A method for terminating an automated driving function of a vehicle involves deactivating the driving function by a steering intervention of a driver of the vehicle in a steering system, which includes a steering column and a steering wheel. In order to determine the steering intervention, a steering column torque at the steering column is measured and a steering wheel angle is measured. A manual torque acting on the steering wheel is estimated based on the measured steering column torque and the measured steering wheel angle. The estimation is based on a model equation of the steering system, which takes into consideration a moment of inertia of the steering wheel and a frictional torque in the steering system.

Abstract: A vehicle control system includes a driving controller that switches between autonomous driving an manual driving of a vehicle, a seat whose form is changed between a form during autonomous driving and a form during manual driving that are different from each other, and a seat controller that controls motion of the seat when a form of the seat is changed. If the seat is in a form during autonomous driving, the driving controller does not switch autonomous driving to manual driving when controlling the vehicle.

Abstract: According to one embodiment, an unmanned transport vehicle includes: a moving body capable of autonomously traveling on a floor surface and having a docking portion connecting to the object; a detection sensor capable of detecting an approach side support leg, wherein, of the plurality of support legs in the object, a pair of support legs located on a docking side of the moving body are designated as approach side support legs, and a pair of support legs located on a side opposite to a docking side in a traveling direction of the moving body is used as depth side support legs; and a control device connected to the moving body and a first detection sensor. The moving body has a height capable of entering a bottom space surrounded by a lower surface of the load plate of the object, the plurality of support legs, and the floor surface.

Abstract: A system and method for completing continual multi-agent trajectory forecasting with a graph-based conditional generative memory system that include receiving data associated with a surrounding location of an ego agent and inputting the data associated with the surrounding location of the ego agent to at least one episodic memory buffer and processing scene graphs associated with the surrounding location of the ego agent that are associated with the plurality of time steps. The system and method additionally include aggregating the data associated with the surrounding location of the ego agent associated with the plurality of time steps into mixed data and training a generative memory and a predictor with the mixed data. The system and method further include predicting future trajectories associated with traffic agents that are located within the surrounding location of the ego agent based on the training of the generative memory and the predictor.