臺灣博碩士論文加值系統

生成式人工智慧（Generative AI）代表了現代科技的進展，其能力涵蓋生成對話、故事、圖像、音樂等內容和模擬思維模式的能力，特別在語言處理和思考任務中顯示出卓越的適用性。隨著其應用不斷擴展，本研究旨在探索AI在日常生活和虛實交互中的融入，特別是在人機互動方面。本研究主要貢獻有二：一是提出了一種新型機器人設計，整合了磁場定向控制的機器人底盤和自行設計的輕量化複合式穩定投影架構；二是研發了一款擬人化語音助理作為核心應用；這兩個部分需要有效的軟硬體整合，方能完整的呈現本研究。

本研究為擬人化語音助理提供載體，利用投影技術在使用者周圍建立最佳視覺互動點並將助理投影成像，藉由此方式促進人機交流。研究目標是透過這些創新應用縮短人類與人工智慧的距離，拓展相關研究的應用。

Generative Artificial Intelligence (Generative AI) is a major technological advancement, capable of generating conversations, stories, images, music, and simulating cognitive patterns. It excels in language processing and cognitive tasks. This study explores AI integration into daily life and virtual-real interactions, particularly in human-machine interaction. The research contributes two main innovations: a novel robot design combining a field-oriented control chassis with a lightweight composite gimbal projection structure, and the development of a humanized AI voice assistant. Effective hardware and software integration is crucial for achieving the study's goals.

This study provides a platform for the humanized AI voice assistant, using projection technology to create optimal visual interaction points around the user and project the assistant’s image, enhancing human-machine communication. The goal is to bridge the gap between humans and AI, expanding the scope of related research applications.

Chinese Abstract…i
English Abstract…ii
Acknowledgements…iii
Table of Contents…iv
List of Tables…vii
List of Figures…viii
Chapter 1 Introduction…1
1.1 Research Motivation and Objectives…1
1.2 Problem Description…2
1.3 Literature Review…3
1.3.1 Comparison of Traditional DC Motors and Brushless Motors…3
1.3.2 Brushless Motor Drive Methods…4
1.4 Gimbal Stabilizer Technology…6
1.5 Anthropomorphic AI Voice Assistant…7
1.6 Structure of the Thesis…8
Chapter 2 Analysis of Relevant Technologies and Literature Review…9
2.1 Analysis and Discussion of Professional Service Robots…9
2.2 Literature Analysis and Discussion…10
2.3 Image Recognition Analysis…12
2.3.1 yoloV4 (You Only Look Once version 4)…12
2.3.2 OpenCV (Open Source Computer Vision Library)…13
2.4 Literature Review…14
Chapter 3 Field-Oriented Control of Brushless Robot…15
3.1 Overview of Hardware Design…15
3.2 Mechanical Structure Design…15
3.3 Chassis Structure Design…17
3.4 Shock Absorber Mechanism…19
3.5 Steering Mechanism and Operation Mode…19
3.5.2 2WD (Two-Wheel Drive)…21
3.5.3 Front Ackermann steering…21
3.5.4 Rear Ackermann steering…22
3.5.5 Non- Onmi Wheel 2WD mode…23
3.6 Emergency Stop System…24
3.7 Overview of Hardware System Architecture…25
3.8 Core of the robot system (Intel NUC11Phi7C)…26
3.9 Environmental Detection System…27
3.10 PhantomLink System…27
3.10.2 PhantomLink Symbiotic mode…28
3.10.3 PhantomLink Extended applications…28
3.11 Hub motor for balancing robots…29
3.12 FOC driver improved based on ODrive and SimpleFOC…31
3.12.1 Introduction to ESC and FOC Technology…31
3.12.2 Odrive…32
3.12.3 SimpleFOC…33
3.12.4 FOC Drivers for Robot Control with Visual Interface…34
3.13 User Following Method…36
3.13.2 UWB Target Tracking System…36
3.13.3 Separated Ultrasonic Ranging System…39
3.13.4 Distance Measurement Methods and Positioning Algorithms…42
3.14 User Following Method without ROS System…44
3.15 User Following Method under ROS System Control…45
3.15.1 RViz…45
3.15.2 User Relative Position Mapping to Robot World Coordinates…45
3.16 Power System…47
3.17 Component Installation Configuration…48
Chapter 4 Lightweight Large Composite Gimbal…49
4.1 Overview of Hardware Design…49
4.2 Mechanical Structure Design…49
4.2.1 BFM5208 Brushless Motor…50
4.2.2 Quick-Release Base and Center of Gravity Adjustment Mechanism…51
4.3 Projection Screen Calibration…52
4.3.1 Screen Distortion Issues…52
4.3.2 Infrared TOF Distance Measurement Module…52
4.3.3 Calculation Methods for Projection Surface Angle and Distance…53
4.3.4 Transmission of Corrected Values…55
4.4 Gimbal Drive Circuit Improvements…56
4.4.1 STorM32 BGC…56
4.4.2 Circuit System Improvements Based on STorM32 BGC…57
4.4.3 Integrated System for Robot Chassis…57
4.5 Projection Surface and User Recognition…58
4.5.1 Logitech C922 Pro Webcam…58
4.5.2 Wide-Angle Lens Setup, Issues, and Solutions…59
4.6 Projection Strategies…60
4.6.1 Projection Strategies Under Automatic Navigation…60
4.6.2 User Tracking Strategies…61
4.7 Projection Devices…63
Chapter 5 Humanized AI Voice Assistant Design…65
5.1 Overview of Humanized AI Voice Assistant…65
5.2 System Flowchart…65
5.3 Humanized Character Model…66
5.3.1 Discomfort Caused by Model Characteristics…66
5.3.2 Live2D Technology…67
5.3.3 VRM Models…68
5.4 Large Language Models…70
5.4.1 ChatGPT…70
5.4.2 Meta_LLaMA 3…71
5.4.3 RWKV…72
5.5 Voice Input…73
5.5.1 Speech-to-Text…73
5.5.2 Voice Activation…74
5.6 Fine-Tuning Large Language Models…75
5.6.1 Fine-Tuning Methods…76
5.6.2 Retrieval-Augmented Generation (RAG) Techniques…77
5.7 Sentiment Analysis…78
5.8 Voice Output (Text-to-Speech)…80
Chapter 6 Data, Conclusions, and Future Prospects…81
6.1 Experimental Data…81
6.2 Robot architecture…82
6.3 Performance comparison of robot chassis…83
6.4 Comparison between ESC and FOC driver…84
6.5 Robot chassis configurations…85
6.6 Localization methods and field experiments…86
6.7 Gimbal energy consumption experiment…88
6.8 Comparison of different projection devices…89
6.9 Comparison of voice services…90
6.10 Interactivity of anthropomorphic models…91
6.11 Conclusions…92
6.12 Future Prospects…93
References…94

1.Inc., A. Siri. 2024 [cited 2024 2024-07-11]; Available from: https://www.apple.com/tw/siri/.
2.Damanauskas, V. and A. Janulevičius, Differences in tractor performance parameters between single-wheel 4WD and dual-wheel 2WD driving systems. Journal of Terramechanics, 2015. 60: p. 63-73.
3.Gröninger, M., et al., Electric Wheel Hub Motor. ATZelektronik worldwide, 2012. 7(1): p. 32-37.
4.Chen, K.-Y. and C.-Y. Tsui, The Fuzzy Control Approach for a Quadruped Robot Guide Dog. International Journal of Fuzzy Systems, 2021. 23(6): p. 1789-1796.
5.Learning the Basics of Motor Control. Motor Control Basics 2023 [cited 2024 July 11]; Available from: https://www.powerelectronicsnews.com/learning-the-basics-of-motor-control/.
6.Skuric, A., et al., SimpleFOC: A Field Oriented Control (FOC) Library for Controlling Brushless Direct Current (BLDC) and Stepper Motors. J. Open Source Softw., 2022. 7: p. 4232.
7.INSTRUMENTS, T., MCT8316A High Speed Sensorless Trapezoidal Control Integrated FET BLDC Driver datasheet (Rev. B), in Texas Instruments Motor Drivers. 2022: Dallas, TX, USA.
8.Kau, N., et al. Stanford doggo: An open-source, quasi-direct-drive quadruped. in 2019 International conference on robotics and automation (ICRA). 2019. IEEE.
9.Dere, E., M. Ozcan, and S. Canan. Three Axis Gimbal Design and Its Application. in Proceedings of the International Conference on Advanced Technologies, Computer Engineering and Science (ICATCES’18), Safranbolu, Turkey. 2018.
10.Hedrick, T.L., J.R. Usherwood, and A.A. Biewener, Wing inertia and whole-body acceleration: an analysis of instantaneous aerodynamic force production in cockatiels (Nymphicus hollandicus) flying across a range of speeds. Journal of Experimental Biology, 2004. 207(10): p. 1689-1702.
11.Achiam, J., et al., Gpt-4 technical report. arXiv preprint arXiv:2303.08774, 2023.
12.Touvron, H., et al., Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971, 2023.
13.Peng, B., et al., Rwkv: Reinventing rnns for the transformer era. arXiv preprint arXiv:2305.13048, 2023.
14.Group, I.S.R.W. World Robotics - Service Robots. 2024 [cited 2024 July 11]; Available from: https://ifr.org/service-robots.
15.Robotics, N. NUWA Robotics Products. 2024 [cited 2024 July 11]; Available from: https://www.nuwarobotics.com/zh-hant/product/.
16.Lee, D.-H., Combined Sensor–Sensorless Control of PMDC Motor for HD Camera of Unmanned Monitoring System. Journal of Electrical Engineering & Technology, 2020. 15(1): p. 27-35.
17.Koraqi, L. and F. Idrizi. “Detection, identification and tracking of objects during the motion”. in 2019 3rd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT). 2019.
18.Bradski, G., The opencv library. Dr. Dobb's Journal: Software Tools for the Professional Programmer, 2000. 25(11): p. 120-123.
19.Bochkovskiy, A., C.-Y. Wang, and H.-Y.M. Liao, Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934, 2020.
20.APAC, S.-N. Segway-Ninebot APAC. 2024 [cited 2024 July 14]; Available from: https://ap-en.segway.com/.
21.Ackermann, J. and W. Sienel, Robust yaw damping of cars with front and rear wheel steering. IEEE Transactions on Control Systems Technology, 1993. 1(1): p. 15-20.
22.Groskamp, J. What is the Ackermann angle. 2024 [cited 2024 July 14].
23.Inc., M.-O.M.H. Dimensions You Need to Know About Before Purchasing a Forklift. 2024 [cited 2024 July 14]; Available from: https://www.mmhforklifts.com/dimensions-you-need-to-know-about-before-purchasing-a-forklift/.
24.Ahmad, N., et al., Reviews on various inertial measurement unit (IMU) sensor applications. International Journal of Signal Processing Systems, 2013. 1(2): p. 256-262.
25.Company, T.B.R. Hoverboard Scooter Global Market Report. [cited 2024 July 14]; Available from: https://www.thebusinessresearchcompany.com/report/hoverboard-scooter-global-market-report.
26.FFBeast. Motors. FFBeast Documentation 2024 [cited 2024 July 14]; Available from: https://ffbeast.github.io/docs/en/hardware_motor.html.
27.Robotics, O. ODrive Robotics Products. 2024 [cited 2024 July 11]; Available from: https://odriverobotics.com/.
28.SimpleFOC. SimpleFOC Products. 2024 [cited 2024 July 11]; Available from: https://simplefoc.com/.
29.Aiello, G.R. and G.D. Rogerson, Ultra-wideband wireless systems. IEEE microwave magazine, 2003. 4(2): p. 36-47.
30.Li, J., Design of an Ultra-Wide Band based Indoor Positioning System. 2018.
31.Kleppmann, M. Designing Data-Intensive Applications: Ch. 7 Transactions. 2016 [cited 2024 July 11]; Available from: https://medium.com/theskyisblue/designing-data-intensive-applications-ch-7-transactions-d3d30e59e322.
32.Tamás Bátori, P.T., Zoltán Melis, Investigation of the Technological Possibilities of Warehouse Location. Academic Journal of Manufacturing Engineering, 2021. 19.
33.Gustafsson, F. and F. Gunnarsson. Positioning using time-difference of arrival measurements. in 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings.(ICASSP'03). 2003. IEEE.
34.Hess, W., et al. Real-time loop closure in 2D LIDAR SLAM. in 2016 IEEE international conference on robotics and automation (ICRA). 2016. IEEE.
35.Corporation, B., BenQ GS50 DLP Projector Datasheet. 2024, BenQ Europe B.V.: Eindhoven, The Netherlands.
36.Kätsyri, J., et al., A review of empirical evidence on different uncanny valley hypotheses: support for perceptual mismatch as one road to the valley of eeriness. Frontiers in psychology, 2015. 6: p. 390.
37.Morita, M., Y. Fujii, and T. Sato, The face narrowing caused by the Mona Lisa effect. Journal of Vision, 2019. 19(10): p. 178-178.
38.Leonie Monigatti. From Theory to LangChain Implementation. Retrieval-Augmented Generation (RAG) 2023 [cited 2023 Nov 14]; Available from: https://towardsdatascience.com/retrieval-augmented-generation-rag-from-theory-to-langchain-implementation-4e9bd5f6a4f2.
39.Larsen, L., Learning Microsoft Cognitive Services. 2017: Packt Publishing Ltd.
40.Fujian LILLIPUT Optoelectronics Technology Co., L. OWON Digital Multimeter User Manual. [cited 2024 July 14]; Available from: https://www.electronicaembajadores.com/Datos/manuales/in/inha/OWON35-SeriesB41T.pdf.
41.Marouf, A., et al., A new control strategy of an electric-power-assisted steering system. IEEE Transactions on Vehicular Technology, 2012. 61(8): p. 3574-3589.
42.Stefano Lovati. Learning the Basics of Motor Control. Technical Articles 2023 [cited 2023 January 2]; Available from: https://www.powerelectronicsnews.com/learning-the-basics-of-motor-control/.
43.Tuan, H.M., F. Sanfilippo, and N.V. Hao, Modelling and control of a 2-dof robot arm with elastic joints for safe human-robot interaction. Frontiers in Robotics and AI, 2021. 8: p. 679304.
44.Wu, C., J. Angeles, and P. Montagnier, Robot Visualization System (RVS) User Manual. 1997, Citeseer.