Information Flow and Entropy Production in the Kalman - Bucy Filter ∗

نویسندگان

  • Sanjoy K. Mitter
  • Nigel J. Newton
  • NIGEL J. NEWTON
چکیده

We investigate the information theoretic properties of KalmanBucy filters in continuous time, developing notions of information supply, storage and dissipation. By introducing a concept of energy, we develop a physical analogy in which the unobservable signal describes a statistical mechanical system interacting with a heat bath. The abstract ‘universe’ comprising the signal and the heat bath obeys a non-increase law of entropy; however, with the introduction of partial observations, this law can be violated. The Kalman-Bucy filter behaves like a Maxwellian demon in this analogy, returning signal energy to the heat bath without causing entropy increase. This is made possible by the steady supply of new information. The analogy thus provides a quantitative example of Landauer’s Principle, operating in reverse. The filter sets up a stationary non-equilibrium state, in which energy flows around the loop comprising the heat bath, the signal and the filter. We define a rate of interactive entropy production, isolating the statistical mechanics of this flow from the marginal mechanics of the signal and filter. This leads naturally to a dual filtering problem in which information flows are reversed.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Application of the Kalman-Bucy filter in the stochastic differential equation for the modeling of RL circuit

In this paper, we present an application of the stochastic calculusto the problem of modeling electrical networks. The filtering problem have animportant role in the theory of stochastic differential equations(SDEs). In thisarticle, we present an application of the continuous Kalman-Bucy filter for a RLcircuit. The deterministic model of the circuit is replaced by a stochastic model byadding a ...

متن کامل

Information and Entropy Flow in the Kalman - Bucy Filter ∗ Sanjoy

We investigate the information theoretic properties of KalmanBucy filters in continuous time, developing notions of information supply, storage and dissipation. Introducing a concept of energy, we develop a physical analogy in which the unobserved signal describes a statistical mechanical system interacting with a heat bath. The abstract ‘universe’ comprising the signal and the heat bath obeys ...

متن کامل

A Statistical Mechanical View of Kalman Filtering

We develop a physical analogy for the Kalman-Bucy filter, in which the partially observed signal describes a statistical mechanical system interacting with a heat bath. The ‘universe’ comprising this system and the heat bath obeys a non-decrease law of entropy similar to the Second Law of Thermodynamics. However, this law can be violated in the presence of partial observations. Like Maxwell’s d...

متن کامل

Cooperative Control of Multiple Quadrotors for Transporting a Common Payload

This paper investigates the problem of controlling a team of Quadrotors that cooperatively transport a common payload. The main contribution of this study is to propose a cooperative control algorithm based on a decentralized algorithm. This strategy is comprised of two main steps: the first one is calculating the basic control vectors for each Quadrotor using Moore–Penrose theory aiming at coo...

متن کامل

Implementation of a Low- Cost Multi- IMU by Using Information Form of a Steady State Kalman Filter

In this paper, a homogenous multi-sensor fusion method is used to estimate the trueangular rate and acceleration with a combination of four low cost (< 10$) MEMS Inertial MeasurementUnits (IMU). An information form of steady state Kalman filter is designed to fuse the output of four lowaccuracy sensors to reduce the noise effect by the square root of the number of sensors. A hardware isimplemen...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2004