Strain-based Intelligent Control System for Micro-Aerial and Terrestrial Robots
- 주제(키워드) Bio-inspired , Artificial intelligence , Robot control
- 주제(DDC) 621.8
- 발행기관 아주대학교 일반대학원
- 지도교수 Daeshik Kang
- 발행년도 2025
- 학위수여년월 2025. 8
- 학위명 박사
- 학과 및 전공 일반대학원 기계공학과
- 실제URI http://www.dcollection.net/handler/ajou/000000035239
- 본문언어 영어
- 저작권 아주대학교 논문은 저작권에 의해 보호받습니다.
목차
Chapter 1. Introduction 1
1.1. Insect-inspired Robots 1
1.1.1. Research Trends 3
1.1.2. Challenges of Intelligent Control in Small-scale Robots 5
Chapter 2. Methodology 7
2.1. Bio-inspired Mechanosensory System 7
2.1.1. Campaniform Sensilla 7
2.1.2. Ultrasensitive Crack-based Strain Sensor 9
2.2. Deep Learning Model and Data Processing 11
2.2.1. 1D Convolutional Neural Network (CNN) 12
2.2.2. Exploratory Data Analysis (EDA) 13
2.3. End-to-End Reinforcement Learning 15
2.3.1. Soft Actor-Critic (SAC) Algorithm 16
2.3.2. Design of Reward Function 17
Chapter 3. Results 21
3.1. Control of Flapping-wing Drone 21
3.1.1. Wind Vector Prediction 22
3.1.2. Control in a 1 DOF Movement Environment 25
3.1.3. Control in a 2 DOF Movement Environment 28
3.1.4. Control in a 6 DOF Movement Environment 31
3.1.5. Control in a Windless Environment 35
3.2. Control of Legged Robot 39
3.2.1. Experimental Setup 41
3.2.2. Terrain Type Classification 44
3.2.3. Robot Orientation Regression 45
3.2.4. Energy-efficient Control Across Various Terrains 48
3.2.5. Adaptive Control on Mixed Terrain 51
Chapter 4. Conclusion and Future Work 55
4.1. Summary 55
4.2. Future Work 56
Bibliography 59
