arXiv subjects

Jiaqi Jiang

Publications and source records attributed to Jiaqi Jiang.

36 records · Page 2Linked to original sources

arXiv2022

A4T: Hierarchical Affordance Detection for Transparent Objects Depth Reconstruction and Manipulation

Transparent objects are widely used in our daily lives and therefore robots need to be able to handle them. However, transparent objects suffer from light reflection and refraction, which makes it challenging to obtain the accurate depth maps required to perform handling tasks. In this paper, we propose a novel affordance-based framework for depth reconstruction and manipulation of transparent objects, named A4T. A hierarchical AffordanceNet is first used to detect the transparent objects and their associated affordances that encode the relative positions of an object's different parts. Then, given the predicted affordance map, a multi-step depth reconstruction method is used to progressively reconstruct the depth maps of transparent objects. Finally, the reconstructed depth maps are employed for the affordance-based manipulation of transparent objects. To evaluate our proposed method, we construct a real-world dataset TRANS-AFF with affordances and depth maps of transparent objects, which is the first of its kind. Extensive experiments show that our proposed methods can predict accurate affordance maps, and significantly improve the depth reconstruction of transparent objects compared to the state-of-the-art method, with the Root Mean Squared Error in meters significantly decreased from 0.097 to 0.042. Furthermore, we demonstrate the effectiveness of our proposed method with a series of robotic manipulation experiments on transparent objects. See supplementary video and results at https://sites.google.com/view/affordance4trans.

cs.RO↗

arXiv2022

Central charges, elliptic genera, and Bekenstein-Hawking entropy in $\mathcal{N}=(2,2)$ AdS$_3$/CFT$_2$

We consider $\mathcal{N}=(2,2)$ AdS$_3$/CFT$_2$ dualities proposed in the large central charge limit ($c\to\infty$) by Eberhardt. Here we propose the associated D1-D5 systems to be orbifolds of the standard $\mathcal{N}=(4,4)$ systems, thereby elevating the dualities to the finite-$c$ level on the boundary and to the quantum level in the bulk. In particular, we show that our brane systems yield low-energy sigma models whose subleading central charges match earlier predictions from bulk one-loop supergravity computations. In the case involving the Enriques surface, the finite-$c$ sigma model has a non-trivial elliptic genus which we use to microscopically explain both the Bekenstein-Hawking entropy and the subleading logarithmic correction to it for the associated macroscopic black brane.

hep-th↗

arXiv2022

WaveY-Net: Physics-augmented deep learning for high-speed electromagnetic simulation and optimization

The calculation of electromagnetic field distributions within structured media is central to the optimization and validation of photonic devices. We introduce WaveY-Net, a hybrid data- and physics-augmented convolutional neural network that can predict electromagnetic field distributions with ultra fast speeds and high accuracy for entire classes of dielectric photonic structures. This accuracy is achieved by training the neural network to learn only the magnetic near-field distributions of a system and to use a discrete formalism of Maxwell's equations in two ways: as physical constraints in the loss function and as a means to calculate the electric fields from the magnetic fields. As a model system, we construct a surrogate simulator for periodic silicon nanostructure arrays and show that the high speed simulator can be directly and effectively used in the local and global freeform optimization of metagratings. We anticipate that physics-augmented networks will serve as a viable Maxwell simulator replacement for many classes of photonic systems, transforming the way they are designed.

physics.app-ph↗

arXiv2021

Robotic Perception of Object Properties using Tactile Sensing

The sense of touch plays a key role in enabling humans to understand and interact with surrounding environments. For robots, tactile sensing is also irreplaceable. While interacting with objects, tactile sensing provides useful information for the robot to understand the object, such as distributed pressure, temperature, vibrations and texture. During robot grasping, vision is often occluded by its end-effectors, whereas tactile sensing can measure areas that are not accessible by vision. In the past decades, a number of tactile sensors have been developed for robots and used for different robotic tasks. In this chapter, we focus on the use of tactile sensing for robotic grasping and investigate the recent trends in tactile perception of object properties. We first discuss works on tactile perception of three important object properties in grasping, i.e., shape, pose and material properties. We then review the recent development in grasping stability prediction with tactile sensing. Among these works, we identify the requirement for coordinating vision and tactile sensing in the robotic grasping. To demonstrate the use of tactile sensing to improve the visual perception, our recent development of vision-guided tactile perception for crack reconstruction is presented. In the proposed framework, the large receptive field of camera vision is first leveraged to achieve a quick search of candidate regions containing cracks, a high-resolution optical tactile sensor is then used to examine these candidate regions and reconstruct a refined crack shape. The experiments show that our proposed method can achieve a significant reduction of mean distance error from 0.82 mm to 0.24 mm for crack reconstruction. Finally, we conclude this chapter with a discussion of open issues and future directions for applying tactile sensing in robotic tasks.

cs.RO↗

arXiv2021

Vision-Guided Active Tactile Perception for Crack Detection and Reconstruction

Crack detection is of great significance for monitoring the integrity and well-being of the infrastructure such as bridges and underground pipelines, which are harsh environments for people to access. In recent years, computer vision techniques have been applied in detecting cracks in concrete structures. However, they suffer from variances in light conditions and shadows, lacking robustness and resulting in many false positives. To address the uncertainty in vision, human inspectors actively touch the surface of the structures, guided by vision, which has not been explored in autonomous crack detection. In this paper, we propose a novel approach to detect and reconstruct cracks in concrete structures using vision-guided active tactile perception. Given an RGB-D image of a structure, the rough profile of the crack in the structure surface will first be segmented with a fine-tuned Deep Convolutional Neural Networks, and a set of contact points are generated to guide the collection of tactile images by a camera-based optical tactile sensor. When contacts are made, a pixel-wise mask of the crack can be obtained from the tactile images and therefore the profile of the crack can be refined by aligning the RGB-D image and the tactile images. Extensive experiment results have shown that the proposed method improves the effectiveness and robustness of crack detection and reconstruction significantly, compared to crack detection with vision only, and has the potential to enable robots to help humans with the inspection and repair of the concrete infrastructure.

cs.RO↗

arXiv2021

TouchRoller: A Rolling Optical Tactile Sensor for Rapid Assessment of Large Surfaces

Tactile sensing is important for robots to perceive the world as it captures the texture and hardness of the object in contact and is robust to illumination and colour variances. However, due to the limited sensing area and the resistance of the fixed surface, current tactile sensors have to tap the tactile sensor on target object many times when assessing a large surface, i.e., pressing, lifting up and shifting to another region. This process is ineffective and time consuming. It is also undesirable to drag such sensors as this often damages the sensitive membrane of the sensor or the object. To address these problems, we propose a cylindrical optical tactile sensor named TouchRoller that can roll around its center axis. It maintains being in contact with the assessed surface throughout the entire motion, which allows for measuring the object continuously and effectively. Extensive experiments show that the TouchRoller sensor can cover a textured surface of 8cm*11cm in a short time of 10s, much more effectively than a flat optical tactile sensor (in 196s). The reconstructed map of the texture from the collected tactile images has a high Structural Similarity Index (SSIM) of 0.31 on average, when compared with the visual texture. In addition, the contacts on the sensor can be localised with a low localisation error, 2.63mm in the center regions and 7.66mm on average. The proposed sensor will enable the fast assessment of large surfaces with high-resolution tactile sensing, and also the effective collection of tactile images.

cs.RO↗

arXiv2020

Giant Wilson Loops and AdS$_2$/dCFT$_1$

The 1/2-BPS Wilson loop in $\mathcal{N}=4$ supersymmetric Yang-Mills theory is an important and well-studied example of conformal defect. In particular, much work has been done for the correlation functions of operator insertions on the Wilson loop in the fundamental representation. In this paper, we extend such analyses to Wilson loops in the large-rank symmetric and antisymmetric representations, which correspond to probe D3 and D5 branes with $AdS_2 \times S^2$ and $AdS_2 \times S^4$ worldvolume geometries, ending at the $AdS_5$ boundary along a one-dimensional contour. We first compute the correlation functions of protected scalar insertions from supersymmetric localization, and obtain a representation in terms of multiple integrals that are similar to the eigenvalue integrals of the random matrix, but with important differences. Using ideas from the Fermi Gas formalism and the Clustering method, we evaluate their large $N$ limit exactly as a function of the 't Hooft coupling. The results are given by simple integrals of polynomials that resemble the $Q$-functions of the Quantum Spectral Curve, with integration measures depending on the number of insertions. Next, we study the correlation functions of fluctuations on the probe D3 and D5 branes in AdS. We compute a selection of three- and four-point functions from perturbation theory on the D-branes, and show that they agree with the results of localization when restricted to supersymmetric kinematics. We also explain how the difference of the internal geometries of the D3 and D5 branes manifests itself in the localization computation.

hep-th↗

arXiv2020

Design space reparameterization enforces hard geometric constraints in inverse-designed nanophotonic devices

Inverse design algorithms are the basis for realizing high-performance, freeform nanophotonic devices. Current methods to enforce geometric constraints, such as practical fabrication constraints, are heuristic and not robust. In this work, we show that hard geometric constraints can be imposed on inverse-designed devices by reparameterizing the design space itself. Instead of evaluating and modifying devices in the physical device space, candidate device layouts are defined in a constraint-free latent space and mathematically transformed to the physical device space, which robustly imposes geometric constraints. Modifications to the physical devices, specified by inverse design algorithms, are made to their latent space representations using backpropagation. As a proof-of-concept demonstration, we apply reparameterization to enforce strict minimum feature size constraints in local and global topology optimizers for metagratings. We anticipate that concepts in reparameterization will provide a general and meaningful platform to incorporate physics and physical constraints in any gradient-based optimizer, including machine learning-enabled global optimizers.

physics.app-ph↗

arXiv2020

Multi-objective and categorical global optimization of photonic structures based on ResNet generative neural networks

We show that deep generative neural networks, based on global topology optimization networks (GLOnets), can be configured to perform the multi-objective and categorical global optimization of photonic devices. A residual network scheme enables GLOnets to evolve from a deep architecture, which is required to properly search the full design space early in the optimization process, to a shallow network that generates a narrow distribution of globally optimal devices. As a proof-of-concept demonstration, we adapt our method to design thin film stacks consisting of multiple material types. Benchmarks with known globally-optimized anti-reflection structures indicate that GLOnets can find the global optimum with orders of magnitude faster speeds compared to conventional algorithms. We also demonstrate the utility of our method in complex design tasks with its application to incandescent light filters. These results indicate that advanced concepts in deep learning can push the capabilities of inverse design algorithms for photonics.

physics.app-ph↗

arXiv2020

Deep neural networks for the evaluation and design of photonic devices

The data sciences revolution is poised to transform the way photonic systems are simulated and designed. Photonics are in many ways an ideal substrate for machine learning: the objective of much of computational electromagnetics is the capture of non-linear relationships in high dimensional spaces, which is the core strength of neural networks. Additionally, the mainstream availability of Maxwell solvers makes the training and evaluation of neural networks broadly accessible and tailorable to specific problems. In this Review, we will show how deep neural networks, configured as discriminative networks, can learn from training sets and operate as high-speed surrogate electromagnetic solvers. We will also examine how deep generative networks can learn geometric features in device distributions and even be configured to serve as robust global optimizers. Fundamental data sciences concepts framed within the context of photonics will also be discussed, including the network training process, delineation of different network classes and architectures, and dimensionality reduction.

eess.IV↗

arXiv2020

Scalar and Spinor Effective Actions in Global de Sitter

In this paper, we compute the effective action of both a scalar field and a Dirac spinor field in the global de Sitter space of any dimension $d$ using the in-/out-state formalism. We show that there is particle production in even dimensions for both scalar field and spinor field. The in-out vacuum amplitude $Z_{in/out}$ is divergent at late times. By using dimensional regularization, we extract the finite part of $\log Z_{in/out}$ for $d$ even and the logarithmically divergent part of $\log Z_{in/out}$ for $d$ odd. We also find that the regularized in-out vacuum amplitude equals the ratio of determinants associated with different quantizations in $AdS_d$ upon the identification of certain parameters in the two theories.

hep-th↗

arXiv2020

MetaNet: A new paradigm for data sharing in photonics research

Optimization methods are playing an increasingly important role in all facets of photonics engineering, from integrated photonics to free space diffractive optics. However, efforts in the photonics community to develop optimization algorithms remain uncoordinated, which has hindered proper benchmarking of design approaches and access to device designs based on optimization. We introduce MetaNet, an online database of photonic devices and design codes intended to promote coordination and collaboration within the photonics community. Using metagratings as a model system, we have uploaded over one hundred thousand device layouts to the database, as well as source code for implementations of local and global topology optimization methods. Further analyses of these large datasets allow the distribution of optimized devices to be visualized for a given optimization method. We expect that the coordinated research efforts enabled by MetaNet will expedite algorithm development for photonics design.

physics.optics↗

arXiv2019

Progressive-Growing of Generative Adversarial Networks for Metasurface Optimization

Generative adversarial networks, which can generate metasurfaces based on a training set of high performance device layouts, have the potential to significantly reduce the computational cost of the metasurface design process. However, basic GAN architectures are unable to fully capture the detailed features of topologically complex metasurfaces, and generated devices therefore require additional computationally-expensive design refinement. In this Letter, we show that GANs can better learn spatially fine features from high-resolution training data by progressively growing its network architecture and training set. Our results indicate that with this training methodology, the best generated devices have performances that compare well with the best devices produced by gradient-based topology optimization, thereby eliminating the need for additional design refinement. We envision that this network training method can generalize to other physical systems where device performance is strongly correlated with fine geometric structuring.

physics.comp-ph↗

arXiv2019

Simulator-based training of generative models for the inverse design of metasurfaces

Metasurfaces are subwavelength-structured artificial media that can shape and localize electromagnetic waves in unique ways. The inverse design of these devices is a non-convex optimization problem in a high dimensional space, making global optimization a major challenge. We present a new type of population-based global optimization algorithm for metasurfaces that is enabled by the training of a generative neural network. The loss function used for backpropagation depends on the generated pattern layouts, their efficiencies, and efficiency gradients, which are calculated by the adjoint variables method using forward and adjoint electromagnetic simulations. We observe that the distribution of devices generated by the network continuously shifts towards high performance design space regions over the course of optimization. Upon training completion, the best generated devices have efficiencies comparable to or exceeding the best devices designed using standard topology optimization. Our proposed global optimization algorithm can generally apply to other gradient-based optimization problems in optics, mechanics and electronics.

physics.comp-ph↗

arXiv2019

Thermodynamics and Many Body Chaos for generalized large q SYK models

This paper considers a type of generalized large $q$ SYK models which include multi-body interactions between Majorana fermions. We derive an effective action in the limit of large $N$ and large $q$ (with ${~q^2\over N} $ small), and find a universal expression for thermodynamical quantities. We also consider the chaos exponent using the retarded kernel method and find an efficient way to calculate the Lyapunov exponent for generalized large $q$ SYK models numerically.

hep-th↗

arXiv2019

Global optimization of dielectric metasurfaces using a physics-driven neural network

We present a global optimizer, based on a conditional generative neural network, which can output ensembles of highly efficient topology-optimized metasurfaces operating across a range of parameters. A key feature of the network is that it initially generates a distribution of devices that broadly samples the design space, and then shifts and refines this distribution towards favorable design space regions over the course of optimization. Training is performed by calculating the forward and adjoint electromagnetic simulations of outputted devices and using the subsequent efficiency gradients for backpropagation. With metagratings operating across a range of wavelengths and angles as a model system, we show that devices produced from the trained generative network have efficiencies comparable to or better than the best devices produced by adjoint-based topology optimization, while requiring less computational cost. Our reframing of adjoint-based optimization to the training of a generative neural network applies generally to physical systems that can utilize gradients to improve performance.

cs.LG↗

arXiv2019

Freeform Diffractive Metagrating Design Based on Generative Adversarial Networks

A key challenge in metasurface design is the development of algorithms that can effectively and efficiently produce high performance devices. Design methods based on iterative optimization can push the performance limits of metasurfaces, but they require extensive computational resources that limit their implementation to small numbers of microscale devices. We show that generative neural networks can train from images of periodic, topology-optimized metagratings to produce high-efficiency, topologically complex devices operating over a broad range of deflection angles and wavelengths. Further iterative optimization of these designs yields devices with enhanced robustness and efficiencies, and these devices can be utilized as additional training data for network refinement. In this manner, generative networks can be trained, with a onetime computation cost, and used as a design tool to facilitate the production of near-optimal, topologically-complex device designs. We envision that such data-driven design methodologies can apply to other physical sciences domains that require the design of functional elements operating across a wide parameter space.

physics.optics↗

arXiv2017

Design of racetrack ring resonator based dielectric laser accelerators

In this paper, we propose a novel design of dielectric laser-driven accelerator (DLA) utilizing evanescent electric field of racetrack ring resonator structures. Driven by laser light with the correctly designed optical phase window, sustained acceleration of electrons with controlled deflection is shown. Based on this design, we calculate an acceleration from 30 keV to 148.312 keV in 104.655 μm using a cascaded 11-stage racetrack ring resonators. This new idea poses a solution for on-chip integration of many DLA stages, while maintains high average accelerating gradients, providing a potential practical realization for "accelerator on a chip".

physics.optics↗