보행로봇의 신경망 이론을 이용한 가상센서 검증

다국어 초록 (Multilingual Abstract)

The sensor data measured by the legged robot are used to recognize the physical environment or information that controls the robot's posture. Therefore, a robot's ambulation can be advanced with the use of such sensing information. For the precise control of a robot, highly accurate sensor data are required, but most sensors are expensive and are exposed to excessive load operation in the field. The seriousness of these problems will be seen if the prototype's practicality and mass productivity, which are closely related to the unit cost of production and maintenance, will be considered. In this paper, the use of a virtual sensor technology was suggested to address the aforementioned problems, and various ways of applying the theory to a walking robot obtained through training with an actual sensor, and of various hardware information, were presented. Finally, the possibility of the replacement of the ground reaction force sensor of legged robot was verified.

목차 (Table of Contents)

• Abstract
• 1. 서론
• 2. 4족 보행로봇 실험 플랫폼 개발
• 3. 역전파 신경망 이론의 수식화
• 4. 역전파 알고리즘의 기본 성능 분석
• 5. 보행로봇에의 적용 실험 및 결론
• 후기
• 참고문헌

참고문헌 (Reference)

1 Caurin, G., "The Development of a Robot Terrain Interaction System for Walking Machines" 1013-1018, 1994

2 G. de Santos, "Quadrupedal Locomotion" Springer 2006

3 Iagnemma, K., "Online Terrain Parameter Estimation for Wheeled Mobile Robots with Application to Planetary Rovers" 20 (20): 921-927, 2004

4 Rehbinder H., "Nonlinear and Roll Estimation for Walking Robots" 2617-2622, 2000

5 Estremera, J., "Neural Virtual Sensor for Terrain Adaptation of Walking Machines" 22 (22): 299-311, 2005

6 Kim, D.S., "Neural Networks – Theory and Applications" Jinhan M&B 1993

7 Lenser, S., "CMPack: A Complete Software System for Autonomous Legged Soccer Robots" 204-211, 2011