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:
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 are an autonomous driving service system for an autonomous driving vehicle, a cloud server for the same, and a method for operating the cloud server. The autonomous driving service system for the autonomous driving vehicle according to an embodiment of the present invention includes a user terminal that requests autonomous driving map data used for an autonomous driving vehicle to perform autonomous driving from a departure point set in advance to a destination, and a cloud server that establishes and manages precise map data based on raw data collected from a plurality of collection vehicles which are driving in mutually different locations, acquires the autonomous driving map data by searching for the precise map data in response to the request for autonomous driving map data of the user terminal, and transmits the acquired autonomous driving map data to the autonomous driving vehicle.
Abstract:
Provided is an autonomous driving technology in which the autonomous driving method includes planning global travelling such that guidance information of global node points is acquired, determining a location of a subject vehicle, generating a first local high-definition map such that the first local high-definition map is generated for at least one section in a global-travelling planned route included in the planning of the global travelling using at least one of a road view and an aerial view provided from a map server, planning a local route for autonomous driving using the first local high-definition map, and controlling the subject vehicle according to the planning of the local route to perform the autonomous driving.
Abstract:
Provided is a technology for a vehicle sensor calibration, in which a vehicle sensor calibration apparatus according to an embodiment includes a sensor device installed inside a calibration room that is a space in which a vehicle having a vehicle sensor mounted thereon is positioned, and configured to obtain basic position information and basic orientation information of the vehicle, a calibration execution module installed in the vehicle and configured to execute calibration on the vehicle sensor on the basis of information received from the outside, and a control module configured to generate calibration position information and calibration orientation information for calibration of the vehicle by analyzing the basic position information and the basic orientation information obtained by the sensor device.
Abstract:
The present invention relates to a self-driving learning apparatus and method using driving experience information. The self-driving learning apparatus includes: an environment information collecting sensor configured to collect driving environment information of a traveling vehicle; a control information collecting sensor configured to collect behavior control information of the traveling vehicle; and a self-driving information generator configured to generate driving experience information by matching driving environment information of a driving environment changing around an ego vehicle to the collected behavior control information.
Abstract:
An unmanned vehicle driving apparatus which allows obstacle avoidance and the method of it is commenced. The unmanned vehicle driving apparatus according to an exemplary embodiment include: a routing part which generates or receives a vehicle's fundamental driving route and generates a moved-driving route by adding or subtracting a route changing value to the fundamental driving route to avoid obstacles while driving; an obstacle detecting part which detects obstacles while driving; and a route driving part which drives the vehicle on the fundamental driving route and when an obstacle is detected, drives the vehicle on the moved-driving route to avoid it.
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 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 are a method and an apparatus for generating a map for autonomous driving and recognizing a location based on the generated map. When generating a map, a spherical range image is obtained by projecting 3D coordinate information corresponding to a 3D space onto a 2D plane, and semantic segmentation is performed on the spherical range image to generate a semantic segmented image. Then, map data including a spherical range image, a semantic segmented image, and lane attribute information are generated.