How to Train Your Gyro: Reinforcement Learning for Rotation Sensing with
a Shaken Optical Lattice
- URL: http://arxiv.org/abs/2212.14473v1
- Date: Thu, 29 Dec 2022 22:22:19 GMT
- Title: How to Train Your Gyro: Reinforcement Learning for Rotation Sensing with
a Shaken Optical Lattice
- Authors: Liang-Ying Chih, Dana Z. Anderson, Murray Holland
- Abstract summary: We apply reinforcement learning to engineer a shaken-lattice matter-wave gyroscope.
The machine is given no instructions as to how to construct the splitting, reflecting, and recombining components intrinsic to conventional interferometry.
What results is a machine-learned solution to the design task that is completely distinct from the familiar sequence of a typical Mach-Zehnder-type matter-wave interferometer.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: As the complexity of the next generation of quantum sensors increases, it
becomes more and more intriguing to consider a new paradigm in which the design
and control of metrological devices is supported by machine learning
approaches. In a demonstration of such a design philosophy, we apply
reinforcement learning to engineer a shaken-lattice matter-wave gyroscope
involving minimal human intuition. In fact, the machine is given no
instructions as to how to construct the splitting, reflecting, and recombining
components intrinsic to conventional interferometry. Instead, we assign the
machine the task of optimizing the sensitivity of a gyroscope to rotational
signals and ask it to create the lattice-shaking protocol in an end-to-end
fashion. What results is a machine-learned solution to the design task that is
completely distinct from the familiar sequence of a typical Mach-Zehnder-type
matter-wave interferometer, and with significant improvements in sensitivity.
Related papers
- Automated Discovery of Coupled Mode Setups [7.555791623885635]
In optics and photonics, a small number of building blocks, like resonators, waveguides, arbitrary couplings, and parametric interactions, allow the design of a broad variety of devices and functionalities.
Usually, the design of such a system is handcrafted by an experienced scientist in a time-consuming process where it remains uncertain whether the simplest possibility has indeed been found.
In our work, we develop a discovery algorithm that automates this challenge.
arXiv Detail & Related papers (2024-04-23T10:15:18Z) - Rotation Sensing using Tractor Atom Interferometry [0.6990493129893112]
We investigate a possible realization of an ultracold-atom rotation sensor based on proposed tractor atom interferometry (TAI)
An experimental design that includes generation of a Laguerre-Gaussian-beam-based "pinwheel" optical lattice and multi-loop interferometric cycles is discussed.
Numerical simulations of the proposed system demonstrate TAI rotation sensitivity comparable to that of contemporary matter-wave interferometers.
arXiv Detail & Related papers (2023-09-12T15:37:33Z) - Multi-Scale Control Signal-Aware Transformer for Motion Synthesis
without Phase [72.01862340497314]
We propose a task-agnostic deep learning method, namely Multi-scale Control Signal-aware Transformer (MCS-T)
MCS-T is able to successfully generate motions comparable to those generated by the methods using auxiliary information.
arXiv Detail & Related papers (2023-03-03T02:56:44Z) - The secret role of undesired physical effects in accurate shape sensing
with eccentric FBGs [1.0805335573008565]
Eccentric fiber Bragg gratings (FBG) are cheap and easy-to-fabricate shape sensors that are often interrogated with simple setups.
Here, we present a novel technique to overcome these limitations and provide accurate and precise shape estimation.
arXiv Detail & Related papers (2022-10-28T09:07:08Z) - Active Predicting Coding: Brain-Inspired Reinforcement Learning for
Sparse Reward Robotic Control Problems [79.07468367923619]
We propose a backpropagation-free approach to robotic control through the neuro-cognitive computational framework of neural generative coding (NGC)
We design an agent built completely from powerful predictive coding/processing circuits that facilitate dynamic, online learning from sparse rewards.
We show that our proposed ActPC agent performs well in the face of sparse (extrinsic) reward signals and is competitive with or outperforms several powerful backprop-based RL approaches.
arXiv Detail & Related papers (2022-09-19T16:49:32Z) - Virtual twins of nonlinear vibrating multiphysics microstructures:
physics-based versus deep learning-based approaches [0.0]
We apply deep learning techniques to generate accurate, efficient and real-time reduced order models.
We extensively test the reliability of the proposed procedures on micromirrors, arches and gyroscopes.
By addressing an electromechanical gyroscope, we show that the non-intrusive deep learning approach generalizes easily to complex multiphysics problems.
arXiv Detail & Related papers (2022-05-12T07:40:35Z) - Reinforcement-learning based matterwave interferometer in a shaken
optical lattice [0.0]
We demonstrate the design of a matterwave interferometer to measure acceleration in one dimension with high precision.
The system we base this on consists of ultracold atoms in an optical lattice potential created by interfering laser beams.
arXiv Detail & Related papers (2021-06-21T22:27:41Z) - Machine Learning Framework for Quantum Sampling of Highly-Constrained,
Continuous Optimization Problems [101.18253437732933]
We develop a generic, machine learning-based framework for mapping continuous-space inverse design problems into surrogate unconstrained binary optimization problems.
We showcase the framework's performance on two inverse design problems by optimizing thermal emitter topologies for thermophotovoltaic applications and (ii) diffractive meta-gratings for highly efficient beam steering.
arXiv Detail & Related papers (2021-05-06T02:22:23Z) - Signal Processing and Machine Learning Techniques for Terahertz Sensing:
An Overview [89.09270073549182]
Terahertz (THz) signal generation and radiation methods are shaping the future of wireless systems.
THz-specific signal processing techniques should complement this re-surged interest in THz sensing for efficient utilization of the THz band.
We present an overview of these techniques, with an emphasis on signal pre-processing.
We also address the effectiveness of deep learning techniques by exploring their promising sensing capabilities at the THz band.
arXiv Detail & Related papers (2021-04-09T01:38:34Z) - Attention that does not Explain Away [54.42960937271612]
Models based on the Transformer architecture have achieved better accuracy than the ones based on competing architectures for a large set of tasks.
A unique feature of the Transformer is its universal application of a self-attention mechanism, which allows for free information flow at arbitrary distances.
We propose a doubly-normalized attention scheme that is simple to implement and provides theoretical guarantees for avoiding the "explaining away" effect.
arXiv Detail & Related papers (2020-09-29T21:05:39Z) - Multilinear Compressive Learning with Prior Knowledge [106.12874293597754]
Multilinear Compressive Learning (MCL) framework combines Multilinear Compressive Sensing and Machine Learning into an end-to-end system.
Key idea behind MCL is the assumption of the existence of a tensor subspace which can capture the essential features from the signal for the downstream learning task.
In this paper, we propose a novel solution to address both of the aforementioned requirements, i.e., How to find those tensor subspaces in which the signals of interest are highly separable?
arXiv Detail & Related papers (2020-02-17T19:06:05Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.