Byungjun Kwon
Byungjun Kwon

Categories

  • News

8월 22일, ‘인텔 Developer Zone’에 Accelerating Deep Learning Based Large-Scale Inverse Kinematics with Intel® Distribution of OpenVINO™ Toolkit에 대한 기사가 게재되었습니다.

‘인텔 Developer Zone’은 AI 및 Game, VR 등 다양한 분야에서 인텔의 소프트웨어를 활용한 대표적인 사례들을 개발자들에게 제공하는 공간입니다. 해당 프로젝트는 딥러닝 기반의 Inverse Kinematics(역운동학)에 대한 연구이며, GDC 2019(Game Developers Conference), NDC 2019(Nexon Developers Conference) 에서 발표되었습니다.

본문

Inverse kinematics (IK) technology was launched in the robotics field and studied to calculate joint angles to move robot arms (end effectors) to the target position with specific degrees of freedom (Figure 1). IK uses kinematic equations to determine the joint angles so that the end effector moves to a desired position. IK technology is now applied to many other areas such as engineering, computer graphics, and video games.

IK animation makes character motions appear more natural and reactive in a game environment. For example, it can be used to keep a character’s feet planted on uneven ground or on stairs. It can also be used for a character’s hand hold on moving objects.

원문 링크: Accelerating Deep Learning Based Large-Scale Inverse Kinematics with Intel® Distribution of OpenVINO™ Toolkit