Application of reinforcement learning for active noise control
Application of reinforcement learning for active noise control
Active noise control (ANC) systems are used to reduce the sound noise level by generating antinoise signals. M-Estimators are widely employed in ANC systems for updating the adaptive FIR filter taps used as the system controller. Observing the state-of-the-art M-estimators design shows that there is a need for further improvements. In this paper, a feedback ANC based on the reinforcement learning (RL) method is proposed. The sensitivity of the constant parameter in the RL method is checked. The effectiveness of the proposed method is proven by comparing the results with previous feedforward studies through computer simulations.
___
- [1] Sutton RS, Barto AG. Reinforcement Learning: An Introduction. Cambridge, MA, USA: MIT Press, 2011.
- [2] El-Fakdi A, Carreras M. Two-step gradient-based reinforcement learning for underwater robotics behavior learning. Robot Auton Syst 2013; 3: 271-282.
- [3] La HM, Lim R, Sheng W. Multirobot cooperative learning for predator avoidance. IEEE T Contr Syst T 2015; 23: 52-63.
- [4] Fiore M, Clodic A, Alami R. On planning and task achievement modalities for human-robot collaboration. Spr Tra Adv Robot 2016; 4: 293-306.
- [5] Kretzschmar H, Spies M, Sprunk C, Burgard W. Socially compliant mobile robot navigation via inverse reinforcement learning. Spr Tra Adv Robot 2016; 4: 71-83.
- [6] Wu L, Qiu X. An M-estimator based algorithm for active impulse-like noise control. Appl Acoust 2013; 31: 407-12.
- [7] Rout NK, Das DP, Panda G. Particle swarm optimization based nonlinear active noise control under saturation nonlinearity. Appl Soft Comput 2016; 41: 275-289.
- [8] Molesworth BR, Burgess M, Chung A. Using active noise cancelling headphones to reduce the effects of masking in commercial aviation. Acta Acust United Ac 2013; 5: 822-827.
- [9] Elliott SJ, Sutton TJ. Performance of feedforward and feedback systems for active control. IEEE T Speech Audi P 1996; 3: 214-223.
- [10] Yang IH, Jeong JE, Jeong UC, Kim JS, Oh JE. Improvement of noise reduction performance for a high-speed elevator using modified active noise control. Appl Acoust 2014; 79: 58-68.
- [11] Hart CR, Lau SK. Active noise control with linear control source and sensor arrays for a noise barrier. J Sound Vib 2012; 1: 15-26.
- [12] Akhtar MT, Mitsuhashi W. Improving performance of FxLMS algorithm for active noise control of impulsive noise. J Sound Vib 2009; 3: 647-56.
- [13] Thanigai P, Kuo SM, Yenduri R. Nonlinear active noise control for infant incubators in neo-natal intensive care units. In: IEEE 2007 Acoustics, Speech and Signal Processing Conference; 1520 April 2007; Honolulu, HI, USA. New York, NY, USA: IEEE. pp. 103-109.
- [14] Leahy R, Zhou Z, Hsu YC. Adaptive filtering of stable processes for active attenuation of impulsive noise. In: IEEE 1995 Acoustics, Speech and Signal Processing Conference; 912 May 1995; Detroit, MI, USA. New York, NY, USA: IEEE. pp. 2983-2986.
- [15] Sun X, Kuo SM, Meng G. Adaptive algorithm for active control of impulsive noise. J Sound Vib 2006; 1: 516-522.
- [16] Akhtar MT, Mitsuhashi W. Improving robustness of filtered-x least mean p-power algorithm for active attenuation of standard symmetric-α-stable impulsive noise. Appl Acoust 2011; 9: 688-694.
- [17] Kuo SM, Morgan D. Active Noise Control Systems: Algorithms and DSP Implementations. New York, NY, USA: Wiley, 1995.
- [18] Navarro-Guerrero N, Weber C, Schroeter P, Wermter S. Real-world reinforcement learning for autonomous humanoid robot docking. Robot Auton Syst 2012; 11: 1400-1407.