한국전자통신학회논문지 (The Journal of the Korea institute of electronic communication sciences)

한국전자통신학회 (Korea Institute of Electronic Communication Science)
권호 표지
DOI QR코드

DOI QR Code

CNN-LSTM 기반의 자율주행 기술

CNN-LSTM based Autonomous Driving Technology

  • 박가은 (전남대학교 전자통신공학과) ;
  • 황치운 (전남대학교 전자통신공학과) ;
  • 임세령 (전남대학교 전자통신공학과) ;
  • 장한승 (전남대학교 전자통신공학과)
  • 투고 : 2023.10.12
  • 심사 : 2023.12.27
  • 발행 : 2023.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 연구는 딥러닝의 합성곱과 순환신경망 네트워크를 기반으로 시각센서를 이용해 속도(Throttle)와 조향(Steering) 제어 기술을 제안한다. 학습 트랙을 시계, 반시계 방향으로 주행하며 카메라 영상 이미지와 조종 값 데이터를 수집하고 효율적인 학습을 위해 데이터 샘플링, 전처리 과정을 거쳐 Throttle과 Steering을 예측하는 모델을 생성한다. 이후 학습에 사용되지 않은 다른 환경의 테스트 트랙을 통해 검증을 진행하여 최적의 모델을 찾고 이를 CNN(Convolutional Neural Network)과 비교하였다. 그 결과 제안하는 딥러닝 모델의 성능이 뛰어남을 확인했다.

This study proposes a throttle and steering control technology using visual sensors based on deep learning's convolutional and recurrent neural networks. It collects camera image and control value data while driving a training track in clockwise and counterclockwise directions, and generates a model to predict throttle and steering through data sampling and preprocessing for efficient learning. Afterward, the model was validated on a test track in a different environment that was not used for training to find the optimal model and compare it with a CNN (Convolutional Neural Network). As a result, we found that the proposed deep learning model has excellent performance.

키워드

과제정보

본 논문은 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행되었음(NRF-2021R1F1A1058795).

참고문헌

  1. E. Yurtsever, J. Lambert, A. Carballo, and K. Takeda, "A Survey of Autonomous Driving: Common Practices and Emerging Technologies," IEEE Access, vol. 8, 2020, pp. 58443-58469. https://doi.org/10.1109/ACCESS.2020.2983149
  2. J. Shin, J. Yoo, J. Han, I. Hwang, and H. Park, "A Study on Basic Technology for Autonomous-Driving Using RC car," J. of the Korea Institute of Electronic Communication Sciences, vol. 17, no. 1, 2022, pp. 49-58.
  3. P. Kaur and R. Sobti, "Current challenges in modelling advanced driver assistance systems: Future trends and advancements," In 2017 2nd IEEE Int. Conf. on Intelligent Transportation Engineering (ICITE), Singapore, Singapore, Sept. 2017, pp. 236-240.
  4. A. Mammeri, G. Lu, and A. Boukerche, "Design of lane keeping assist system for autonomous vehicles," In 2015 7th Int. Conf. on New Technologies, Mobility and Security (NTMS), Paris, France, July 2015, pp. 1-5.
  5. K. Hwang and J. Park, "Steering Control of an Autonomous Vehicle Using CNN," J. of the Korea Institute of Information and Communication Engineering, vol. 24, no. 7, 2020, pp. 834-841.
  6. J. Jo, "Effectiveness of Normalization Pre-Processing of Big Data to the Machine Learning Performance," J. of the Korea Institute of Information and Communication Engineering, vol. 14, no. 3, 2019, pp. 547-552.
  7. Y. Kim, J. Kang, J. Yoon, Y. Lee and B. Whang, "Implementation of Camera-Based Autonomous Driving Vehicle for Indoor Delivery using SLAM," J. of the Korea Institute of Information and Communication Engineering, vol. 17, no. 4, 2022, pp. 687-694.
  8. S. Bak, H. Kim, B. Kim, D. Hwang, U. Enkhjargal, and H. Yoon, "Study on Detection Technique for Cochlodinium polykrikoides Red tide using Logistic Regression Model under Imbalanced Data," J. of the Korea Institute of Information and Communication Engineering, vol. 13, no. 6, 2018, pp. 1353-1364.
  9. K. Maharana, S. Mondal, and B. Nemade, "A review: Data pre-processing and data augmentation techniques," Global Trans. Proc., vol. 3, no. 1, 2022, pp. 91-99. https://doi.org/10.1016/j.gltp.2022.04.020
  10. W. M. Wells, "Efficient Synthesis of Gaussian Filters by Cascaded Uniform Filters," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. PAMI-8, no. 2, Mar. 1986, pp. 234-239. https://doi.org/10.1109/TPAMI.1986.4767776
  11. D. Kim, W. Choi, S. Ju, S. Yoo, J. Choi and H. Park. "Smart Streetlight based on Accident Recognition using Raspberry Pi Camera OpenCV," J. of the Korea Institute of Information and Communication Engineering, vol. 17, no. 6, 2022, pp. 1229-1236.
  12. P. Y. Simard, D. Steinkraus, and J. C. Platt, "Best practices for convolutional neural networks applied to visual document analysis," Int. Conf. on Document Analysis and Recognition (ICDAR), vol. 3, 2003, pp. 958-963.
  13. S. Hochreiter and J. Schmidhuber, "Long Short-Term Memory," Neural Computation, vol. 9, no. 8, 1997, pp. 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  14. N. R. Draper and H. Smith, Applied regression analysis. New York: John Wiley & Sons, 1998.
  15. A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet classification with deep convolutional neural networks," Communications of the ACM, vol. 60, no. 6, 2017, pp. 84-90. https://doi.org/10.1145/3065386