Abstract: A precise position correction method based on collaborative cognition in an autonomous vehicle includes: estimating object information on a road within a detection range on an autonomous vehicle; receiving a shared message from at least one of a first vehicle (another connected vehicle (CV) or automated vehicle (CAV)) and a road infrastructure device for V2X communication on the road, receiving the message including driving status information of the other CV when the first vehicle is the other CV, and receiving the driving status information of the other CAV and the message about a second vehicle, in which the V2X communication is not possible, recognized by the other CAV; calculating an estimated error by comparing the estimated object information with the message; and setting a radius based on the first vehicle corresponding to an estimated error application radius in consideration of a distance between the autonomous vehicle and the first vehicle.

Abstract: Disclosed herein are a deep network learning method using an autonomous vehicle and an apparatus for the same. The deep network learning apparatus includes a processor configured to select a deep network model requiring an update in consideration of performance, assign learning amounts for respective vehicles in consideration of respective operation patterns of multiple autonomous vehicles registered through user authentication, distribute the deep network model and the learning data to the multiple autonomous vehicles based on the learning amounts for respective vehicles, and receive learning results from the multiple autonomous vehicles, and memory configured to store the deep network model and the learning data.

Abstract: Disclosed are a device for multiple interactions between moving objects and autonomous vehicles and a driving method thereof. The device for multiple interactions between moving objects and autonomous vehicles includes memory in which a program for multiple interactions between moving objects and autonomous vehicles has been stored and a processor configured to execute the program. The processor confirms the status of the moving object including at least any one of a nearby vehicle, a pedestrian, and a mobility user and transmits a control command for a notification function that shares situation information.

Abstract: Disclosed is a processor which includes a camera image feature extractor that extracts a camera image feature based on a camera image, a LIDAR image feature extractor that extracts a LIDAR image feature based on a LIDAR image, a sampling unit that performs a sampling operation based on the camera image feature and the LIDAR image feature and generates a sampled LIDAR image feature, a fusion unit that fuses the camera image feature and the sampled LIDAR image feature and generates a fusion map, and a decoding unit that decodes the fusion map and generates a depth map. The sampling operation includes back-projecting a pixel location of the camera image feature on a camera coordinate system to generate a back-projection point, and projecting the back-projection point on a plane of the LIDAR image to calculate sampling coordinates.

Abstract: A method of filtering dynamic objects in radar-based ego-motion estimation includes converting measurement value at current time, measured by radar sensor, into point cloud, classifying the point cloud into points of a first object predicted as static object and points of a second object predicted as dynamic object, based on position value of dynamic object tracked at previous time, classifying the points of the first object into the points of the static object predicted as normal value and the points of the dynamic object predicted as outlier, based on outlier filtering algorithm, classifying the points of the second object into points of a candidate static object and points of a candidate dynamic object, based on velocity model of the static object, and tracking a position value of the dynamic object at current time, based on the points of the dynamic object and the points of the candidate dynamic object.

Abstract: Disclosed herein are an apparatus and method for evaluating a human motion using a mobile robot. The method may include identifying the exercise motion of a user by analyzing an image of the entire body of the user captured using a camera installed in the mobile robot, evaluating the pose of the user by comparing the standard pose of the identified exercise motion with images of the entire body of the user captured by the camera of the mobile robot from two or more target locations, and comprehensively evaluating the exercise motion of the user based on the pose evaluation information of the user from each of the two or more target locations.

Abstract: A method of predicting a possibility of an accident is provided. The method includes abstracting surrounding situation data and movement data of an ego-vehicle input from a sensor to generate abstracted driving situation data by using an abstraction module executed by a processor, calculating a digitized score of a possibility of an accident of the ego-vehicle by using a calculation module executed by the processor, based on the abstracted driving situation data, and generating action data of the ego-vehicle for decreasing the possibility of the accident by using an action generating module executed by the processor, based on the score.

Abstract: Disclosed is a processor which includes a camera image feature extractor that extracts a camera image feature based on a camera image, a LIDAR image feature extractor that extracts a LIDAR image feature based on a LIDAR image, a sampling unit that performs a sampling operation based on the camera image feature and the LIDAR image feature and generates a sampled LIDAR image feature, a fusion unit that fuses the camera image feature and the sampled LIDAR image feature and generates a fusion map, and a decoding unit that decodes the fusion map and generates a depth map. The sampling operation includes back-projecting a pixel location of the camera image feature on a camera coordinate system to generate a back-projection point, and projecting the back-projection point on a plane of the LIDAR image to calculate sampling coordinates.

Abstract: A method of filtering dynamic objects in radar-based ego-motion estimation includes converting measurement value at current time, measured by radar sensor, into point cloud, classifying the point cloud into points of a first object predicted as static object and points of a second object predicted as dynamic object, based on position value of dynamic object tracked at previous time, classifying the points of the first object into the points of the static object predicted as normal value and the points of the dynamic object predicted as outlier, based on outlier filtering algorithm, classifying the points of the second object into points of a candidate static object and points of a candidate dynamic object, based on velocity model of the static object, and tracking a position value of the dynamic object at current time, based on the points of the dynamic object and the points of the candidate dynamic object.

Abstract: A method for changing a route when an error occurs in an autonomous driving AI includes collecting error information of the AI when an error of the AI has occurred, extracting, from a storage, past error information about a same kind of AI as that of the AI based on the error information of the AI, generating an error analysis result based on the past error information, generating an error analysis result message based on the error analysis result, and determining whether the driving of the autonomous driving vehicle needs to be stopped based on the error analysis result message.

Abstract: Disclosed herein is a method for integrated anomaly detection. The method includes detecting a thing object and a human object in input video using a first neural network, and tracking the human object, and detecting an anomalous situation based on an object detection result and a human object tracking result.

Abstract: A method of automatically detecting a dynamic object recognition error in an autonomous vehicle is provided. The method includes parsing sensor data obtained by frame units from a sensor device equipped in an autonomous vehicle to generate raw data by using a parser, analyzing the raw data to output a dynamic object detection result by using a dynamic object recognition model, determining that detection of a dynamic object recognition error succeeds by using an error detector when the dynamic object detection result satisfies an error detection condition, and storing the raw data and the dynamic object detection result by using a non-volatile memory when the detection of the dynamic object recognition error succeeds.

Abstract: Disclosed herein are a cooperative driving method based on driving negotiation and an apparatus for the same. The cooperative driving method is performed by a cooperative driving apparatus for cooperative driving based on driving negotiation, and includes determining whether cooperative driving is possible in consideration of a driving mission of a requesting vehicle that requests cooperative driving with neighboring vehicles, when it is determined that cooperative driving is possible, setting a responding vehicle from which cooperative driving is to be requested among the neighboring vehicles, performing driving negotiation between the requesting vehicle and the responding vehicle based on a driving negotiation protocol, and when the driving negotiation is completed, performing cooperative driving by providing driving guidance information for vehicle control to at least one of the requesting vehicle and the responding vehicle.

Abstract: The interaction system includes: an infrastructure image sensor-based 3D cloud restoration module configured to create a 3D cloud point using a multi-view image received from an infrastructure sensor; a real-time 3D map creation and learning update module configured to generate subset data composed of point clouds into a 3D map using 3D point information received from the infrastructure image sensor-based 3D cloud restoration module; an object estimation module in a 3D space configured to recognize and track an object existing in a 3D space based on the 3D map received from the real-time 3D map creation and learning update module; and a dangerous situation recognition and interaction module in space configured to receive information on an object existing in the 3D space from the object estimation module in the 3D space, recognize a dangerous situation, and provide dangerous situation related information.

Abstract: The system for infrastructure dynamic object recognition information convergence processing in an autonomous vehicle according to an embodiment of the present invention includes a recognition unit configured to receive object information collected by a sensor of the autonomous vehicle to recognize an environment, a V2X reception message processing unit configured to receive object information collected by an InfraEdge system, and a determination and control unit configured to use the object information collected by the sensor and the object information collected by the InfraEdge system and perform a determination for autonomous driving in consideration of a convergence delay time which is a time difference between a time recorded according to message reception of the V2X reception message processing unit and a current time.

Abstract: Disclosed herein is a method of controlling an autonomous vehicle driving in a lane of a main line. The method may include determining whether the autonomous vehicle is driving in a target lane to accommodate merging traffic, determining whether a merge request message is received from a merging vehicle when the autonomous vehicle is determined to drive in the target lane, determining whether a collision with the merging vehicle will occur based on the merge request message when the merge request message is received, and sending a merge approval message to the merging vehicle when the collision with the merging vehicle is expected.

Abstract: Provided is a method of generating and controlling a driving path for an autonomous vehicle, the method including generating a driving path that matches a driving intention on the basis of sensing data acquired from a sensing module of the autonomous vehicle, determining steering angle information corresponding to the generated driving path, and controlling a steering angle of the autonomous vehicle.

Abstract: Disclosed herein are an apparatus and method for providing a seamless network service based on multiple heterogeneous networks. The method for providing a seamless network service based on multiple heterogeneous networks includes providing, by a multi-network management apparatus, a service transmitted from a server to a terminal over a primary network, synchronizing, by the multi-network management apparatus, service data transmitted over the primary network with a secondary network maintained in a standby state, changing, by the multi-network management apparatus, the secondary network to the primary network as a communication failure between the primary network and the terminal occurs, and providing, by the multi-network management apparatus, the service transmitted from the server to the terminal over the changed primary network.

Abstract: Disclosed herein are an apparatus and method for providing a customized traffic guidance service. The method may include acquiring data about one or more nearby objects, detecting surrounding traffic conditions based on the data about the nearby objects, determining whether to provide a customized traffic guidance service, selecting one or more target objects to which the customized traffic guidance service is to be provided and guidance information to be provided to each of the target objects, generating a customized traffic guidance message for the selected guidance information, and transmitting the customized traffic guidance message to the corresponding target object.

Abstract: Disclosed is a system performing a method for detecting intersection traffic light information including a traffic light detection module including an image sensor for generating first signal data based on traffic light image data in which a traffic light is included, a communication module that receives second signal data for communication with a surrounding object and an external device, an object information collection module that collects dynamic data of the surrounding object, and a signal information inference module that infers third signal data based on the dynamic data. The dynamic data of the surrounding object includes at least one information of whether the surrounding object moves, a moving direction of the surrounding object, and whether the surrounding object accelerates or decelerates. Each of the signal data includes pieces of information about a type of the traffic light and a signal direction of the traffic light.