Electronics and Telecommunications Research Institute

Kyung-Bok Sung

Jeong-Dan Choi

Dong-Yong Kwak

Kyoung-Wook Min

Jong-Hyun Park

Dong-Sun Lim

Byung-Tae Jang

Jung-Sook Kim

Jae-Han Lim

Kyoung-Hwan An

Do-Wook Kang

Jeong-Woo Lee

Yoo-Seung Song

Joo-Young Kim

Jae-Jun Yoo

Kyeong-Tae Kim

Chang-Sub Shin

Myung-Hee Son

Hyun-Kyun Choi

Yong-Woo Jo

Dong-Jin Lee

Mi-Jeong Kim

Jae-Hyuck Park

Jungyu Kang

Doo-Seop Choi

Do-Hyun Kim

Taeg-Hyun An

Seung-Jun Han

Disclosed herein are an apparatus and method for adaptive autonomous driving control. The apparatus includes memory in which at least one program is recorded and a processor for executing the program. The program may perform control of a target vehicle by converting a theoretical control value based on a vehicle control algorithm into a hardware-dependent control value, which is dependent on the platform or hardware of the target vehicle, and may modify at least one parameter or a conversion equation for conversion of the hardware-dependent control value such that an error is minimized based on the difference between a response value according to the control of the target vehicle and a control value.

Apparatus and method for adaptive autonomous driving control

Disclosed herein are an object recognition apparatus of an automated driving system using error removal based on object classification and a method using the same. The object recognition method is configured to train a multi-object classification model based on deep learning using training data including a data set corresponding to a noise class, into which a false-positive object is classified, among classes classified by the types of objects, to acquire a point cloud and image data respectively using a LiDAR sensor and a camera provided in an autonomous vehicle, to extract a crop image, corresponding to at least one object recognized based on the point cloud, from the image data and input the same to the multi-object classification model, and to remove a false-positive object classified into the noise class, among the at least one object, by the multi-object classification model.

Apparatus for recognizing object of automated driving system using error removal based on object classification and method using the same

Disclosed herein are an apparatus and method for detecting an obstacle adaptively to vehicle speed. The apparatus includes a control unit, a speed-adaptive camera sensor, a speed-adaptive laser scanner sensor, and a detection data integration unit. The control unit receives information about the speed of a vehicle and a Pulse Per Second (PPS) signal from a Global Positioning System (GPS) module. The speed-adaptive camera sensor adjusts the range of a detection region based on the information about the speed of the vehicle, and generates first detection data on an object. The speed-adaptive laser scanner sensor adjusts the range of the angle of the field of view of a laser scanner based on the information about the speed of the vehicle, and generates second detection data on the object. The detection data integration unit outputs obstacle detection data.

Apparatus and method for detecting obstacle adaptively to vehicle speed

An apparatus and method for recognizing a current position of a vehicle are disclosed. The apparatus receive information about an initial position of a vehicle from an external input, and receive an image signal from an image sensor to take a picture of an identifiable object and extract image signal information corresponding to the identifiable object from the image signal, and connect to an internal network of the vehicle of the vehicle and receive information about a traveling state of the vehicle, and calculate the current position of the vehicle based on the information obtained.

Apparatus and method for recognizing current position of vehicle using internal network of the vehicle and image sensor

An apparatus and method for detecting the location of a vehicle using results sensed by sensing devices installed outside the vehicle and the internal information of the vehicle without obtaining the current location information of the vehicle using signals transmitted from a Global Positioning System (GPS) satellite, the apparatus for detecting the location of a vehicle includes a location information reception unit for receiving location information that is generated by sensing a vehicle passing by a sensing point and that corresponds to the sensing point. A location detection unit estimates a current location of the vehicle based on information sensed by internal sensors of the vehicle and control information for a vehicle manipulation part while the location information is not received, and corrects the estimated current location of the vehicle using received location information when the location information is received.

Apparatus and method for detecting location of vehicle

Disclosed herein is an apparatus for detecting locations of a vehicle and an obstacle. The apparatus for detecting locations of a vehicle and an obstacle includes at least one distance measurement unit and a data processing unit. The distance measurement unit measures distance data relevant to a vehicle and an obstacle within a measurement area. The data processing unit maps the distance data on a grid layer, detects the location of the vehicle based on the result of the mapping, detects the location of the obstacle based on the detected location of the vehicle, and modifies the detected location of the vehicle using the distance data.

Apparatus and method for detecting locations of vehicle and obstacle

Provided are a reliability-based, real-time sensor network medium access control (MAC) communication system and method using a superframe. The superframe includes an active duration which is a time duration in which a communication is established, and a sleep duration which is a time duration in which no communication is established. The active duration includes a beacon block in which a plurality of beacon transmission nodes are respectively allocated beacon slots for transmitting a beacon frame, and a forwarding block in which each of sinks nodes is allocated a slot for unifying data regarding the sink node and data regarding sensor nodes managed by the sink node and transmit the result of unifying in order to establish a communication between the sink nodes and between each of the sink nodes and a base station.

Reliable and low-latency sensor network MAC system and method using superframe

Provided are a system and method for processing sensing data from a sensor network. The system includes: a data processing condition managing unit for storing sensing data processing conditions; a data processing function managing unit for storing sensing data processing function information; a processed data managing unit for storing processed sensing data; a data pattern managing unit for storing sensing data pattern information; an acquired data managing unit for storing sensing data; a data acquisition condition managing unit for storing sensing data acquisition conditions; a user requirement acquiring unit for acquiring the sensing data acquisition conditions; a data acquiring unit for acquiring sensing data; a data pattern extracting unit for extracting the pattern of sensing data; a data generating unit for processing the sensing data; and a data processing unit for processing the sensing data.

System and method for processing sensing data from sensor network

Growing community of inventors

Daejeon, South Korea

Kyung-Bok Sung