AA
A. Anil Meera
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
7 records found
1
Free Energy Principle Based Precision Modulation for Robot Attention
Towards brain inspired robot intelligence
The potential impact of a grand unified theory of the brain on the robotics community might be immense, as it might hold the key to the general artificial intelligence. Such a theory might make revolutionary leaps in robot intelligence by improving the quality of our lives. The last two decades have witnessed the rise of one such brain theory - the free energy principle (FEP) - that seems to be successful in explaining a large body of cognitive functions. The tremendous amount of research centering FEP is a testament to its popularity within the neuroscience community. This raises two important questions: i) since biological systems are fundamentally different from robots, will FEP be useful in solving real robotics problems? ii) if so, will it outperform classical robot algorithms? To answer these questions, this thesis takes a step in the direction of applying FEP on three class of robotics challenges, with a special focus on Unmanned Aerial Vehicle (UAV): i) action, ii) perception and iii) active perception. This thesis demonstrates the usefulness of FEP in solving these challenges, and shows that FEP is particularly beneficial in dealing with colored (non-white) noise during estimation (perception) when compared to classical methods, marking the utility of FEP not only in neuroscience, but also in robotics. With these results, this thesis aims to contribute to the rise of FEP as a unified theory of robot intelligence.
...
The potential impact of a grand unified theory of the brain on the robotics community might be immense, as it might hold the key to the general artificial intelligence. Such a theory might make revolutionary leaps in robot intelligence by improving the quality of our lives. The last two decades have witnessed the rise of one such brain theory - the free energy principle (FEP) - that seems to be successful in explaining a large body of cognitive functions. The tremendous amount of research centering FEP is a testament to its popularity within the neuroscience community. This raises two important questions: i) since biological systems are fundamentally different from robots, will FEP be useful in solving real robotics problems? ii) if so, will it outperform classical robot algorithms? To answer these questions, this thesis takes a step in the direction of applying FEP on three class of robotics challenges, with a special focus on Unmanned Aerial Vehicle (UAV): i) action, ii) perception and iii) active perception. This thesis demonstrates the usefulness of FEP in solving these challenges, and shows that FEP is particularly beneficial in dealing with colored (non-white) noise during estimation (perception) when compared to classical methods, marking the utility of FEP not only in neuroscience, but also in robotics. With these results, this thesis aims to contribute to the rise of FEP as a unified theory of robot intelligence.
The free energy principle from neuroscience provides a brain-inspired perception scheme through a data-driven model learning algorithm called Dynamic Expectation Maximization (DEM). This paper aims at introducing an exper-imental design to provide the first experimental confirmation of the usefulness of DEM as a state and input estimator for real robots. Through a series of quadcopter flight experiments under unmodelled wind dynamics, we prove that DEM can leverage the information from colored noise for accurate state and input estimation through the use of generalized coordinates. We demonstrate the superior performance of DEM for state es-timation under colored noise with respect to other benchmarks like State Augmentation, SMIKF and Kalman Filtering through its minimal estimation error. We demonstrate the similarities in the performance of DEM and Unknown Input Observer (UIO) for input estimation. The paper concludes by showing the influence of prior beliefs in shaping the accuracy-complexity trade-off during DEM's estimation.
...
The free energy principle from neuroscience provides a brain-inspired perception scheme through a data-driven model learning algorithm called Dynamic Expectation Maximization (DEM). This paper aims at introducing an exper-imental design to provide the first experimental confirmation of the usefulness of DEM as a state and input estimator for real robots. Through a series of quadcopter flight experiments under unmodelled wind dynamics, we prove that DEM can leverage the information from colored noise for accurate state and input estimation through the use of generalized coordinates. We demonstrate the superior performance of DEM for state es-timation under colored noise with respect to other benchmarks like State Augmentation, SMIKF and Kalman Filtering through its minimal estimation error. We demonstrate the similarities in the performance of DEM and Unknown Input Observer (UIO) for input estimation. The paper concludes by showing the influence of prior beliefs in shaping the accuracy-complexity trade-off during DEM's estimation.
The free energy principle from neuroscience provides an efficient data-driven framework called the Dynamic Expectation Maximization (DEM), to learn the generative model in the environment. DEM’s growing potential to be the brain-inspired learning algorithm for robots demands a mathematically rigorous analysis using the standard control system tools. Therefore, this paper derives the mathematical proof of convergence for its parameter estimator for linear state space systems, subjected to colored noise. We show that the free energy based parameter learning converges to a stable solution for linear systems. The paper concludes by providing a proof of concept through simulation for a wide range of spring damper systems.
...
The free energy principle from neuroscience provides an efficient data-driven framework called the Dynamic Expectation Maximization (DEM), to learn the generative model in the environment. DEM’s growing potential to be the brain-inspired learning algorithm for robots demands a mathematically rigorous analysis using the standard control system tools. Therefore, this paper derives the mathematical proof of convergence for its parameter estimator for linear state space systems, subjected to colored noise. We show that the free energy based parameter learning converges to a stable solution for linear systems. The paper concludes by providing a proof of concept through simulation for a wide range of spring damper systems.
The free energy principle (FEP) from neuroscience provides a framework called active inference for the joint estimation and control of state space systems, subjected to colored noise. However, the active inference community has been challenged with the critical task of manually tuning the noise smoothness parameter. To solve this problem, we introduce a novel online noise smoothness estimator based on the idea of free energy principle. We mathematically show that our estimator can converge to the free energy optimum during smoothness estimation. Using this formulation, we introduce a joint state and noise smoothness observer design called DEMs. Through rigorous simulations, we show that DEMs outperforms state-of-the-art state observers with least state estimation error. Finally, we provide a proof of concept for DEMs by applying it on a real life robotics problem - state estimation of a quadrotor hovering in wind, demonstrating its practical use.
...
The free energy principle (FEP) from neuroscience provides a framework called active inference for the joint estimation and control of state space systems, subjected to colored noise. However, the active inference community has been challenged with the critical task of manually tuning the noise smoothness parameter. To solve this problem, we introduce a novel online noise smoothness estimator based on the idea of free energy principle. We mathematically show that our estimator can converge to the free energy optimum during smoothness estimation. Using this formulation, we introduce a joint state and noise smoothness observer design called DEMs. Through rigorous simulations, we show that DEMs outperforms state-of-the-art state observers with least state estimation error. Finally, we provide a proof of concept for DEMs by applying it on a real life robotics problem - state estimation of a quadrotor hovering in wind, demonstrating its practical use.
Journal article
(2022)
-
A. Anil Meera, Filip Novicky, Thomas Parr, Karl Friston, Pablo Lanillos, Noor Sajid
Computational models of visual attention in artificial intelligence and robotics have been inspired by the concept of a saliency map. These models account for the mutual information between the (current) visual information and its estimated causes. However, they fail to consider the circular causality between perception and action. In other words, they do not consider where to sample next, given current beliefs. Here, we reclaim salience as an active inference process that relies on two basic principles: uncertainty minimization and rhythmic scheduling. For this, we make a distinction between attention and salience. Briefly, we associate attention with precision control, i.e., the confidence with which beliefs can be updated given sampled sensory data, and salience with uncertainty minimization that underwrites the selection of future sensory data. Using this, we propose a new account of attention based on rhythmic precision-modulation and discuss its potential in robotics, providing numerical experiments that showcase its advantages for state and noise estimation, system identification and action selection for informative path planning
...
Computational models of visual attention in artificial intelligence and robotics have been inspired by the concept of a saliency map. These models account for the mutual information between the (current) visual information and its estimated causes. However, they fail to consider the circular causality between perception and action. In other words, they do not consider where to sample next, given current beliefs. Here, we reclaim salience as an active inference process that relies on two basic principles: uncertainty minimization and rhythmic scheduling. For this, we make a distinction between attention and salience. Briefly, we associate attention with precision control, i.e., the confidence with which beliefs can be updated given sampled sensory data, and salience with uncertainty minimization that underwrites the selection of future sensory data. Using this, we propose a new account of attention based on rhythmic precision-modulation and discuss its potential in robotics, providing numerical experiments that showcase its advantages for state and noise estimation, system identification and action selection for informative path planning
The free energy principle from neuroscience has recently gained traction as one of the most prominent brain theories that can emulate the brain’s perception and action in a bio-inspired manner. This renders the theory with the potential to hold the key for general artificial intelligence. Leveraging this potential, this paper aims to bridge the gap between neuroscience and robotics by reformulating an FEP-based inference scheme—Dynamic Expectation Maximization—into an algorithm that can perform simultaneous state, input, parameter, and noise hyperparameter estimation of any stable linear state space system subjected to colored noises. The resulting estimator was proved to be of the form of an augmented coupled linear estimator. Using this mathematical formulation, we proved that the estimation steps have theoretical guarantees of convergence. The algorithm was rigorously tested in simulation on a wide variety of linear systems with colored noises. The paper concludes by demonstrating the superior performance of DEM for parameter estimation under colored noise in simulation, when compared to the state-of-the-art estimators like Sub Space method, Prediction Error Minimization (PEM), and Expectation Maximization (EM) algorithm. These results contribute to the applicability of DEM as a robust learning algorithm for safe robotic applications.
...
The free energy principle from neuroscience has recently gained traction as one of the most prominent brain theories that can emulate the brain’s perception and action in a bio-inspired manner. This renders the theory with the potential to hold the key for general artificial intelligence. Leveraging this potential, this paper aims to bridge the gap between neuroscience and robotics by reformulating an FEP-based inference scheme—Dynamic Expectation Maximization—into an algorithm that can perform simultaneous state, input, parameter, and noise hyperparameter estimation of any stable linear state space system subjected to colored noises. The resulting estimator was proved to be of the form of an augmented coupled linear estimator. Using this mathematical formulation, we proved that the estimation steps have theoretical guarantees of convergence. The algorithm was rigorously tested in simulation on a wide variety of linear systems with colored noises. The paper concludes by demonstrating the superior performance of DEM for parameter estimation under colored noise in simulation, when compared to the state-of-the-art estimators like Sub Space method, Prediction Error Minimization (PEM), and Expectation Maximization (EM) algorithm. These results contribute to the applicability of DEM as a robust learning algorithm for safe robotic applications.
The free energy principle from neuroscience provides a biologically plausible solution to the brain's inference mechanism. This paper reformulates this theory to design a brain-inspired state and input estimator for a linear time-invariant state space system with colored noise. This reformulation for linear systems bridges the gap between the neuroscientific theory and control theory, therefore opening up the possibility of evaluating it under the hood of standard control approaches. Through rigorous simulations under colored noises, the observer is shown to outperform Kalman Filter and Unknown Input Observer with minimal error in state and input estimation. It is tested against a wide range of scenarios and the proof of concept is demonstrated by applying it on a real system.
...
The free energy principle from neuroscience provides a biologically plausible solution to the brain's inference mechanism. This paper reformulates this theory to design a brain-inspired state and input estimator for a linear time-invariant state space system with colored noise. This reformulation for linear systems bridges the gap between the neuroscientific theory and control theory, therefore opening up the possibility of evaluating it under the hood of standard control approaches. Through rigorous simulations under colored noises, the observer is shown to outperform Kalman Filter and Unknown Input Observer with minimal error in state and input estimation. It is tested against a wide range of scenarios and the proof of concept is demonstrated by applying it on a real system.