Design and Implementation of Automatic Car Driving Control System Based on FPGA

Abstract:

This paper studies and designs of a car automatic driving control system, the system is a dual-core FFT processor based on the pipeline structure CORDIC algorithm design is based on the voice signal spectrum analysis, and through the to extract MFCC voice characteristics Template Library instruction data in comparison, thereby generating a control signal, and ultimately by the FPGA control the wireless communication module to achieve the basic operation of the voice control of the car commonly. Download test results show that the system can be done in real-time response to voice commands, the system has a simple hardware structure, real-time, high reliability, and can be widely used in the field of voice recognition control systems in DE2 experimental development platform .

• Periodical: Applied Mechanics and Materials (Volumes 380-384)
• Pages: 408-412
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.380-384.408
• Online since: August 2013
• Authors: Qian Huang, Jun Yang, Zheng Peng Zhao, Fu Shou Tao
• Keywords: Dual-Core FFT, Field-Programmable Gate Array (FPGA), Trolley Automatic Driving System, Voice Recognition

References

[1] H. GENG, W.Q. LIANG, M. DONG, R.S. LIU. An Speech Recongnition SoC Solution Based on FPGA, Audio Engineering, vol. 10, pp.32-34, (2009).

[2] Y.J. PENG. A parallel architecture for VLSI implementation of FFT processor, 5th ASIC International Conference. IEEE, 2003. vol. 2, 748-751.

DOI: 10.1109/icasic.2003.1277319

[3] C.C. Hui, J.D. Tiong, Error Analysis of FFT Architecture for Digital Video Applications, 3th IEEE International Conference on Electronics, Circuits and Systems. Greece: IEEE CAS Society Press, 1996, pp.820-823.

DOI: 10.1109/icecs.1996.584488

[4] Y. Dong , J. Yang , Z.X. Tang, Design of Twofish Encryption /Decryption Unit Based on SOPC, Journal of Yunnan University, vol. 33, pp.397-401, (2011).

[5] X.J. Wang,G. Zhao P.P. Shu,J. Yang, FPGA-based IMA-ADPCM Codec Research and Design, Journal of Yunnan University, vol. 34, pp.415-419, (2012).

[6] M.A. Hossan, S. Memon, M.A. Gregory, A Novel Approach for MFCC Feature Extraction, Signal Processing and Communication Systems (ICSPCS), 2010, pp.1-5.

DOI: 10.1109/icspcs.2010.5709752

[7] S.H. Jin, J.U. Cho, D. R. Lee, H. S. Kim, CH.H. Lee, J. S. Choi,J. W. Jeon , An FPGA-based Voice Signal Preprocessor for the Real-time Cross-correlation, , Control, Automation and Systems (ICCAS 07), International Conference, 2007, pp.793-797.

DOI: 10.1109/iccas.2007.4407008

[8] Hojin Kee, Petersen N, Kornerup, Bhattacharyya, S.S. Systematic Generation of FPGA-based FFT Implementations, Acoustics, Speech and Signal Processing (ICASSP) , IEEE International Conference , 2008, p.1413 – 1416.

DOI: 10.1109/icassp.2008.4517884

[9] H.J. Tae V.O. Alan, Effects of FFT Coefficient Quantization on Sinusoidal Signal Detection, Acoustics, Speech and Signal Processing. New York, USA: IEEE Press, 1988, pp.1818-1821.

DOI: 10.1109/icassp.1988.196975