Korea University of Technology and Education Industry-university Cooperation Foundation

Education Industry-university Cooperation Foundation

Korea University of Technology and

Won Tae Kim

Han Jin Kim

Young Jin Kim

Jun Hyung Kwon

Deun Sol Cho

Jae Min Cho

Min Cheol Lee

A method of simulating robot arm motion planning to which curriculum-based deep reinforcement learning applies may be provided. The method according to an embodiment of the present disclosure may include: generating multiple features for each target point within a robot arm's work area; deciding on a selected feature based on correlations between the multiple features; determining a level of difficulty of the each target point based on the selected feature; determining a unit of curriculum (UoC), which is a group of the targets points, for which deep reinforcement learning is to be performed in the same episode, based on the determined level of difficulty; and performing sequentially the deep reinforcement learning for each of the units of curriculum.

Apparatus for and method of simulating robot arm motion planning, to which curriculum-based deep reinforcement learning applies

A spatial reuse (SR) method in a wireless LAN (WLAN) system may be provided. The operating method according to an embodiment of the present disclosure may include: the SR system according to an embodiment of the present disclosure may include: detecting a new signal by receiving communication environment information, comparing strength of the new signal with a first threshold, determining whether the new signal is a target signal of the WLAN system based on the determination that the strength of the new signal exceeds the first threshold, determining whether the new signal is a negligible signal based on the determination that the new signal is not a target signal of the WLAN system and performing spatial reuse simultaneous transmission by adjusting transmission power based on the determination that the new signal is the negligible signal.

Method and apparatus for spatial reuse based on interference recognition

An operating method of a server operating a digital twin built into a virtual space for a plurality of base stations and a plurality of mobile devices may be provided. The operating method according to an embodiment of the present disclosure may include: invoking a digital twin-based beamforming management service; obtaining location information about a target mobile device from among the plurality of mobile devices and a target base station corresponding to the target mobile device; searching for a plurality of paths capable of forming a beam from the target base station to the target mobile device based on the location information and spatial information of the digital twin; performing a first communication performance simulation for the plurality of paths; determining a final beamforming parameter based on a result of the first communication performance simulation; and transmitting beamforming information including the final beamforming parameter to the target base station.

Method and apparatus for digital twin-based beamforming

A network control method for handover in a mobile time-sensitive network (TSN) communication system is provided. The network control method includes: communicating of a user terminal within a wireless communication range of a first AP with an end system through the first AP; determining whether to handover to a second AP by determining communication strength between the user terminal and the first AP; requesting handover to a controller when the handover to the second AP is determined; reconfiguring a TSN communication operation after the handover, determining handover timing, and generating a handover command by a controller; transmitting the handover command to the first AP, the user terminal, and the second AP; and applying the reconfigured TSN communication operation to the second AP and the user terminal at the handover timing.

Growing community of inventors

Cheonan-si, South Korea

Won Tae Kim