近年來，隨著自動駕駛越來越興盛，在汽車中可以找到各種感測器，像是聲納、影像、光達和雷達系統。這些感測器可以用來輔助駕駛，精確測量汽車前方、旁邊或後方物體的距離和相對速度，使駕駛在能見度差時或物體隱藏在盲點時，能得知物體的位置。如果感測器不能準確探測到目標，就會對駕駛員的安全構成嚴重威脅。相較於其他感測器，雷達具有不易受環境影響、量測距離長且精準的優勢。在汽車雷達中，調頻連續波（FMCW）雷達被廣泛使用，因為與脈衝雷達相比，其可降低訊號處理的硬體複雜度。然而實務上存在由干擾效應和反射損耗等引起的系統誤差，且這些誤差有可能被誤認為是所需訊號。如何有效的抑制雜訊以及如何準確判斷物體位置將是本篇論文探討的重點，首先考慮了線性回歸的方法將雜訊與訊號區隔並利用深層神經網路將物體定位。

With self-driving automobiles becoming more and more popular in recent years, various sensors could be found in cars such as Sonar, Vision, Lidar, and Radar Systems. These sensors are used to assist drivers. Exact measurement of distance and relative velocity of objects in front, besides, or behind the car allow the driver to perceive objects during bad visibility or objects hidden in the blind spot. If sensors do not accurately detect targets, it can pose a serious threat to driver’s safety. Compared with other sensors, radar has the advantages of not being easily affected by the environment, and being capable of measuring longer distances precisely. For automotive radar systems, Frequency Modulation Continuous Wave (FMCW) radar is generally utilized because the complexity of hardware in the signal processing part can be reduced, compared to that of pulse radar. However, there are interference effects, reflection loss and some system errors in the practical application, which could be mistaken for desired signals. How to reduce the noise and accurately position the object will be the focus of this paper. First, the linear regression method is used to distinguish the noise and the signal, and the deep neural network is used to locate the object.

參考文獻

[1] 翁國樑、李玉忠等編著：〈自駕車發展趨勢與關鍵技術〉，DEC 2019 工程，92卷，04 期，2019。
[2] 葉冠甫：〈基於單一影像之車輛偵測系統軟硬體設計〉，碩士論文，國立中山大學，民國101年7月。
[3] J. Wenger, “Automotive mm-wave Radar: Status and Trends in System Design and Technology,” IEE Colloquium on Automotive Radar and Navigation Techniques, London, UK, Feb. 1998.
[4] J.-E. Lee, H.-S. Lim, et al., “Harmonic Clutter Recognition and Suppression for Automotive Radar Sensors,” International Journal of Distributed Sensor Networks, vol. 13, no. 9, pp. 1-11, Sep. 2017.
[5] S. Lee, and S.-C. Kim, “Distribution-Based Iron Road Structure Recognition Method Using Automotive Radar Sensor,” 2018 IEEE Radar Conference (RadarConf18), Oklahoma City, OK, USA, Apr. 2018.
[6] S. Lee, Y.-J. Yoon, et al., “Human–Vehicle Classification Using Feature-Based SVM in 77-GHz Automotive FMCW Radar,” IET Radar Sonar Navigation, vol. 11, no. 10, pp. 1589-1596, Oct. 2017.
[7] S. Lee, B.-H. Lee, et al., “Statistical Characteristic-Based Road Structure Recognition in Automotive FMCW Radar Systems,” IEEE Transactions on Intelligent Transportation Systems, vol. 20, no. 7, pp. 2418-2429, Jul. 2019.
[8] T.-N. Luo, C.-H. E. Wu, and Y.-J. E. Chen. “A 77-GHz CMOS Automotive Radar Transceiver with Anti-Interference Function,” IEEE Trans. Circuit Syst. I Reg. Papers, vol. 60, no. 12, pp. 3247-3255, Dec. 2013.
[9] S. Lee, J.-Y. Lee, and S.-C. Kim, “Mutual Interference Suppression Using Wavelet Denoising in Automotive FMCW Radar Systems,” IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 2, pp.887-897, Feb. 2021.
[10] 壹讀：〈雷達基礎知識：脈衝雷達〉，取自：https://read01.com/4Gj06M4. html#. YoT8ofNByUk，2020。
[11] 李文龍：〈5.8GHz 都卜勒雷達系統設計與整合〉，碩士論文，國立交通大學，民國100年3月。
[12] B. R. Mahafza, Radar Systems Analysis and Design Using MATLAB. London, U.K.: Chapman & Hall, 2000.
[13] M. Kronauge, C. Schroeder, and H. Rohling, “Radar Target Detection and Doppler Ambiguity Resolution,” 11th International Radar Symposium, Vilnius, Lithuania, 16-18 Jun. 2010.
[14] F. Ali and M. Vossiek, “Detection of Weak Moving Targets Based on 2-D Range-Doppler FMCW Radar Fourier Processing,” German Microwave Conference, Berlin, Germany, 9-13 Mar. 2010.
[15] A. Rizik, E. Tavanti, et al., “Single Target Recognition Using a Low-Cost FMCW Radar Based on Spectrum Analysis,” 27th IEEE International Conference on Electronics, Circuits and Systems (ICECS), Glasgow, UK, 23-25 Nov. 2020.
[16] E. Hyun, Y.-S. Jin, and J.-H. Lee, “A Pedestrian Detection Scheme Using a Coherent Phase Difference Method Based on 2D Range-Doppler FMCW Radar,” Sensors 2016, vol. 16, no. 124, Jan. 2016.
[17] Suleyman Suleymanov, “Design and Implementation of an FMCW Radar Signal Processing Module for Automotive Applications,” Master’s Thesis, University of Twente, Aug. 2016.
[18] D. Duraj, M. Plotka, et al., “Measurement of Distance, Velocity and Angle of Arrival Using FMCW-CW Combined Waveform,” 21st International Conference on Microwave, Radar and Wireless Communications (MIKON), Krakow, Poland, 09-11 May 2016.
[19] Tommy Huang：〈調頻連續波雷達 Frequency Modulated Continuous Wave (FMCW Radars): 測距/測速原理(2/3)〉，取自：https://chih-sheng-huang821.
medium.com/%E8%AA%BF%E9%A0%BB%E9%80%A3%E7%BA%8C%E6%B3%A2%E9%9B%B7%E9%81%94-frequency-modulated-continuous-wave-fmcw-radars-%E6%B8%AC%E8%B7%9D-%E6%B8%AC%E9%80%9F%E5%
8E%9F%E7%90%86-2-3-981e4706fc9d, 2022。
[20] M. Shobana, S. Aggarwal, and R. Pandeeswari, “Machine Learning Hexagonal Monopole Antenna Using Linear Regression Algorithm,” Asian Conference on Innovation in Technology (ASIANCON), Pune, India, 28-29 Aug. 2021.
[21] X. Wang, L. Yan, and Q. Zhang, “Research on the Application of Gradient Descent Algorithm in Machine Learning,” 2021 International Conference on Computer Network, Electronic and Automation (ICCNEA), Xi'an, China, 24-26 Sep. 2021.
[22] M. Chen, U. Challita, et al., “Artificial Neural Networks-Based Machine Learning for Wireless Networks: A Tutorial,” IEEE Communications Surveys & Tutorials, vol. 21, no.4, 03 Jul. 2019.