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.
초록/요약
Insect-inspired robots are promising for tasks requiring compactness, agility, and multifunctionality, taking cues from organisms like flies and ants. Using lightweight frames, origami structures, and soft actuators such as shape memory alloys or dielectric elastomers, these robots can walk, jump, or fly efficiently at millimeter scales—ideal for confined or hazardous environments. However, miniaturization limits sensing and control: IMUs suffer from noise under strong vibrations, and vision systems degrade under occlusion, dust, or low light. To overcome these limitations, we propose a bio-inspired control framework using strain sensing, modeled after campaniform sensilla in insect wings and legs. Our method integrates three components: ultrasensitive crack-based strain sensors at mechanically critical joints such as wing bases, leg hinges, data-driven state estimation using 1D convolutional neural network (1D CNN), and Soft Actor-Critic (SAC) reinforcement learning (RL) algorithm for real-time control using only strain feedback. In aerial applications, a flapping- wing drone with just two wing-base strain sensors estimated wind direction and speed with approximately 80% classification accuracy and 29° mean angular error. It performed flight control in windy and windless environments—all without IMUs or cameras—by adapting to subtle changes in airflows solely based on strain signals. On the ground, a legged robot classified terrain with 93% accuracy and estimated pitch and roll with <4% error. An RL controller trained on this input minimized energy consumption (cost of transport, CoT) by up to 7.8% on low-friction terrain and adapted effectively to mixed surfaces. These results highlight the potential of strain-based proprioception as a lightweight, scalable alternative to conventional sensors. The unified approach enables adaptive, efficient control in both aerial and terrestrial microrobots operating in unstructured environments, paving the way for future autonomous systems with minimal sensor configurations.
more목차
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
