arXiv subjects

Bin Liang

Publications and source records attributed to Bin Liang.

At least 127 records · Page 7Linked to original sources

arXiv2023

Acoustic meta-stethoscope for cardiac auscultation

Straight cylindrical stethoscopes serve as an important alternative to conventional stethoscopes whose application in the treatment of infectious diseases might be limited by the use of protective clothing. Yet their miniaturization is challenging due to the low-frequency of bioacoustics signal. Here, we design and experimentally implement a meta-stethoscope with subwavelength size, simple fabrication, easy assembly yet high sensitivity, which simply comprises multiple round perforated plate units and a cylindrical shell. We elucidate our proposed mechanism by analytically deriving the frequency response equation, which proves that the equivalent acoustic propagation path is substantially increased by the high-index metamaterial, enabling downscaling of the meta-stethoscope to subwavelength footprint. The acoustic performance of meta-stethoscope is experimentally characterized by monitoring the cardiac auscultation on clothed human body. The simulated and measured results agree well, with both showing the expected enhancement of sensitivity of our proposed meta-stethoscope (~ 10 dB) within the predicted working frequency range from 80 to 130 Hz despite its compactness and simplicity. Our designed portable, detachable yet effective meta-stethoscope opens a route to metamaterial-enabled stethoscope paradigm, with potential applications in diverse scenarios such as medical diagnosis and acoustic sensing.

physics.app-ph↗

arXiv2023

Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization

A key challenge of continual reinforcement learning (CRL) in dynamic environments is to promptly adapt the RL agent's behavior as the environment changes over its lifetime, while minimizing the catastrophic forgetting of the learned information. To address this challenge, in this article, we propose DaCoRL, i.e., dynamics-adaptive continual RL. DaCoRL learns a context-conditioned policy using progressive contextualization, which incrementally clusters a stream of stationary tasks in the dynamic environment into a series of contexts and opts for an expandable multihead neural network to approximate the policy. Specifically, we define a set of tasks with similar dynamics as an environmental context and formalize context inference as a procedure of online Bayesian infinite Gaussian mixture clustering on environment features, resorting to online Bayesian inference to infer the posterior distribution over contexts. Under the assumption of a Chinese restaurant process prior, this technique can accurately classify the current task as a previously seen context or instantiate a new context as needed without relying on any external indicator to signal environmental changes in advance. Furthermore, we employ an expandable multihead neural network whose output layer is synchronously expanded with the newly instantiated context, and a knowledge distillation regularization term for retaining the performance on learned tasks. As a general framework that can be coupled with various deep RL algorithms, DaCoRL features consistent superiority over existing methods in terms of the stability, overall performance and generalization ability, as verified by extensive experiments on several robot navigation and MuJoCo locomotion tasks.

cs.LG↗

arXiv2023

Chess-board Acoustic Crystals with Momentum-space Nonsymmorphic Symmetries

Spatial symmetries appearing in both real and momentum space are of fundamental significance to crystals. However, in the conventional framework, every space group in real space, either symmorphic or nonsymmorphic, corresponds to a symmorphic dual in momentum space. Our experiment breaks the framework by showing that in a 2D acoustic crystal with chess-board pattern of $π$ and 0 fluxes, mirror reflections are manifested nonsymmorphically as glide reflections in momentum space. These momentum-space nonsymmorphic symmetries stem from projective, rather than ordinary, representations of the real-space symmetries due to the peculiar flux pattern. Moreover, our experiment demonstrates that the glide reflection can reduce the topological type of the Brillouin zone from the torus to the Klein bottle, resulting in novel topological phases with new topological invariants. Since crystalline topologies are based on momentum-space symmetries, our work paves the way for utilizing engineerable gauge fluxes over artificial crystals to extend the current topological classifications into the broader regime of momentum-space nonsymmorphic symmetries.

cond-mat.mes-hall↗

arXiv2023

Data-driven prognostics based on time-frequency analysis and symbolic recurrent neural network for fuel cells under dynamic load

Data-centric prognostics is beneficial to improve the reliability and safety of proton exchange membrane fuel cell (PEMFC). For the prognostics of PEMFC operating under dynamic load, the challenges come from extracting degradation features, improving prediction accuracy, expanding the prognostics horizon, and reducing computational cost. To address these issues, this work proposes a data-driven PEMFC prognostics approach, in which Hilbert-Huang transform is used to extract health indicator in dynamic operating conditions and symbolic-based gated recurrent unit model is used to enhance the accuracy of life prediction. Comparing with other state-of-the-art methods, the proposed data-driven prognostics approach provides a competitive prognostics horizon with lower computational cost. The prognostics performance shows consistency and generalizability under different failure threshold settings.

cs.LG↗

arXiv2023

Foldsformer: Learning Sequential Multi-Step Cloth Manipulation With Space-Time Attention

Sequential multi-step cloth manipulation is a challenging problem in robotic manipulation, requiring a robot to perceive the cloth state and plan a sequence of chained actions leading to the desired state. Most previous works address this problem in a goal-conditioned way, and goal observation must be given for each specific task and cloth configuration, which is not practical and efficient. Thus, we present a novel multi-step cloth manipulation planning framework named Foldformer. Foldformer can complete similar tasks with only a general demonstration and utilize a space-time attention mechanism to capture the instruction information behind this demonstration. We experimentally evaluate Foldsformer on four representative sequential multi-step manipulation tasks and show that Foldsformer significantly outperforms state-of-the-art approaches in simulation. Foldformer can complete multi-step cloth manipulation tasks even when configurations of the cloth (e.g., size and pose) vary from configurations in the general demonstrations. Furthermore, our approach can be transferred from simulation to the real world without additional training or domain randomization. Despite training on rectangular clothes, we also show that our approach can generalize to unseen cloth shapes (T-shirts and shorts). Videos and source code are available at: https://sites.google.com/view/foldsformer.

cs.RO↗

arXiv2022

Domain Generalization by Learning and Removing Domain-specific Features

Deep Neural Networks (DNNs) suffer from domain shift when the test dataset follows a distribution different from the training dataset. Domain generalization aims to tackle this issue by learning a model that can generalize to unseen domains. In this paper, we propose a new approach that aims to explicitly remove domain-specific features for domain generalization. Following this approach, we propose a novel framework called Learning and Removing Domain-specific features for Generalization (LRDG) that learns a domain-invariant model by tactically removing domain-specific features from the input images. Specifically, we design a classifier to effectively learn the domain-specific features for each source domain, respectively. We then develop an encoder-decoder network to map each input image into a new image space where the learned domain-specific features are removed. With the images output by the encoder-decoder network, another classifier is designed to learn the domain-invariant features to conduct image classification. Extensive experiments demonstrate that our framework achieves superior performance compared with state-of-the-art methods.

cs.CV↗

arXiv2022

Distributed Deep Reinforcement Learning: A Survey and A Multi-Player Multi-Agent Learning Toolbox

With the breakthrough of AlphaGo, deep reinforcement learning becomes a recognized technique for solving sequential decision-making problems. Despite its reputation, data inefficiency caused by its trial and error learning mechanism makes deep reinforcement learning hard to be practical in a wide range of areas. Plenty of methods have been developed for sample efficient deep reinforcement learning, such as environment modeling, experience transfer, and distributed modifications, amongst which, distributed deep reinforcement learning has shown its potential in various applications, such as human-computer gaming, and intelligent transportation. In this paper, we conclude the state of this exciting field, by comparing the classical distributed deep reinforcement learning methods, and studying important components to achieve efficient distributed learning, covering single player single agent distributed deep reinforcement learning to the most complex multiple players multiple agents distributed deep reinforcement learning. Furthermore, we review recently released toolboxes that help to realize distributed deep reinforcement learning without many modifications of their non-distributed versions. By analyzing their strengths and weaknesses, a multi-player multi-agent distributed deep reinforcement learning toolbox is developed and released, which is further validated on Wargame, a complex environment, showing usability of the proposed toolbox for multiple players and multiple agents distributed deep reinforcement learning under complex games. Finally, we try to point out challenges and future trends, hoping this brief review can provide a guide or a spark for researchers who are interested in distributed deep reinforcement learning.

cs.LG↗

arXiv2022

Policy Learning for Nonlinear Model Predictive Control with Application to USVs

The unaffordable computation load of nonlinear model predictive control (NMPC) has prevented it for being used in robots with high sampling rates for decades. This paper is concerned with the policy learning problem for nonlinear MPC with system constraints, and its applications to unmanned surface vehicles (USVs), where the nonlinear MPC policy is learned offline and deployed online to resolve the computational complexity issue. A deep neural networks (DNN) based policy learning MPC (PL-MPC) method is proposed to avoid solving nonlinear optimal control problems online. The detailed policy learning method is developed and the PL-MPC algorithm is designed. The strategy to ensure the practical feasibility of policy implementation is proposed, and it is theoretically proved that the closed-loop system under the proposed method is asymptotically stable in probability. In addition, we apply the PL-MPC algorithm successfully to the motion control of USVs. It is shown that the proposed algorithm can be implemented at a sampling rate up to $5 Hz$ with high-precision motion control. The experiment video is available via:\url{https://v.youku.com/v_show/id_XNTkwMTM0NzM5Ng==.html

cs.RO↗

arXiv2022

The Simplest Balance Controller for Dynamic Walking

Humans can balance very well during walking, even when perturbed. But it seems difficult to achieve robust walking for bipedal robots. Here we describe the simplest balance controller that leads to robust walking for a linear inverted pendulum (LIP) model. The main idea is to use a linear function of the body velocity to determine the next foot placement, which we call linear foot placement control (LFPC). By using the Poincaré map, a balance criterion is derived, which shows that LFPC is stable when the velocity-feedback coefficient is located in a certain range. And that range is much bigger when stepping faster, which indicates "faster stepping, easier to balance". We show that various gaits can be generated by adjusting the controller parameters in LFPC. Particularly, a dead-beat controller is discovered that can lead to steady-state walking in just one step. The effectiveness of LFPC is verified through Matlab simulation as well as V-REP simulation for both 2D and 3D walking. The main feature of LFPC is its simplicity and inherent robustness, which may help us understand the essence of how to maintain balance in dynamic walking.

cs.RO↗

arXiv2022

Sound non-reciprocity based on synthetic magnetism

Synthetic magnetism has been recently realized using spatiotemporal modulation patterns, producing non-reciprocal steering of charge-neutral particles such as photons and phonons. Here, we design and experimentally demonstrate a non-reciprocal acoustic system composed of three compact cavities interlinked with both dynamic and static couplings, in which phase-correlated modulations induce a synthetic magnetic flux that breaks time-reversal symmetry. Within the rotating wave approximation, the transport properties of the system are controlled to efficiently realize large non-reciprocal acoustic transport. By optimizing the coupling strengths and modulation phases, we achieve frequency-preserved unidirectional transport with 45-dB isolation ratio and 0.85 forward transmission. Our results open to the realization of acoustic nonreciprocal technologies with high efficiency and large isolation, and offer a route towards Floquet topological insulators for sound.

physics.app-ph↗

arXiv2022

PUTN: A Plane-fitting based Uneven Terrain Navigation Framework

Autonomous navigation of ground robots has been widely used in indoor structured 2D environments, but there are still many challenges in outdoor 3D unstructured environments, especially in rough, uneven terrains. This paper proposed a plane-fitting based uneven terrain navigation framework (PUTN) to solve this problem. The implementation of PUTN is divided into three steps. First, based on Rapidly-exploring Random Trees (RRT), an improved sample-based algorithm called Plane Fitting RRT* (PF-RRT*) is proposed to obtain a sparse trajectory. Each sampling point corresponds to a custom traversability index and a fitted plane on the point cloud. These planes are connected in series to form a traversable strip. Second, Gaussian Process Regression is used to generate traversability of the dense trajectory interpolated from the sparse trajectory, and the sampling tree is used as the training set. Finally, local planning is performed using nonlinear model predictive control (NMPC). By adding the traversability index and uncertainty to the cost function, and adding obstacles generated by the real-time point cloud to the constraint function, a safe motion planning algorithm with smooth speed and strong robustness is available. Experiments in real scenarios are conducted to verify the effectiveness of the method. The source code is released for the reference of the community.

cs.RO↗

arXiv2022

Dynamic Control Barrier Function-based Model Predictive Control to Safety-Critical Obstacle-Avoidance of Mobile Robot

This paper presents an efficient and safe method to avoid static and dynamic obstacles based on LiDAR. First, point cloud is used to generate a real-time local grid map for obstacle detection. Then, obstacles are clustered by DBSCAN algorithm and enclosed with minimum bounding ellipses (MBEs). In addition, data association is conducted to match each MBE with the obstacle in the current frame. Considering MBE as an observation, Kalman filter (KF) is used to estimate and predict the motion state of the obstacle. In this way, the trajectory of each obstacle in the forward time domain can be parameterized as a set of ellipses. Due to the uncertainty of the MBE, the semi-major and semi-minor axes of the parameterized ellipse are extended to ensure safety. We extend the traditional Control Barrier Function (CBF) and propose Dynamic Control Barrier Function (D-CBF). We combine D-CBF with Model Predictive Control (MPC) to implement safety-critical dynamic obstacle avoidance. Experiments in simulated and real scenarios are conducted to verify the effectiveness of our algorithm. The source code is released for the reference of the community.

cs.RO↗

arXiv2022

Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation

The powerful learning ability of deep neural networks enables reinforcement learning agents to learn competent control policies directly from continuous environments. In theory, to achieve stable performance, neural networks assume i.i.d. inputs, which unfortunately does no hold in the general reinforcement learning paradigm where the training data is temporally correlated and non-stationary. This issue may lead to the phenomenon of "catastrophic interference" and the collapse in performance. In this paper, we present IQ, i.e., interference-aware deep Q-learning, to mitigate catastrophic interference in single-task deep reinforcement learning. Specifically, we resort to online clustering to achieve on-the-fly context division, together with a multi-head network and a knowledge distillation regularization term for preserving the policy of learned contexts. Built upon deep Q networks, IQ consistently boosts the stability and performance when compared to existing methods, verified with extensive experiments on classic control and Atari tasks. The code is publicly available at: https://github.com/Sweety-dm/Interference-aware-Deep-Q-learning.

cs.LG↗

arXiv2022

Remote Water-to-air Eavesdropping through Phase-Engineered Impedance Matching Metasurfaces

Efficiently receiving underwater sound remotely from air is a long-standing challenge in acoustics hindered by the large impedance mismatch at the water-air interface. Here we introduce and experimentally demonstrate a technique for remote and efficient water-to-air eavesdropping through phase-engineered impedance matching metasurfaces. By judiciously engineering an ultrathin mechanically-rigid boundary, we make the water-air interface acoustically transparent and at the same time we are able to pattern the transmitted wavefront, enabling efficient control over the effective spatial location of a distant airborne sensor such that it can measure underwater signals with large signal-to-noise ratio as if placed close to the physical underwater source. Such airborne eavesdropping of underwater sound is experimentally demonstrated with a measured sensitivity enhancement exceeding 38 dB at 8 kHz. We further demonstrate opportunities for orbital-angular-momentum-multiplexed communications and underwater acoustic communications. Our metasurface opens new avenues for communication and sensing, which may be translated to nano-optics and radio-frequencies.

physics.app-ph↗

arXiv2022

AI in Human-computer Gaming: Techniques, Challenges and Opportunities

With breakthrough of the AlphaGo, human-computer gaming AI has ushered in a big explosion, attracting more and more researchers all around the world. As a recognized standard for testing artificial intelligence, various human-computer gaming AI systems (AIs) have been developed such as the Libratus, OpenAI Five and AlphaStar, beating professional human players. The rapid development of human-computer gaming AIs indicate a big step of decision making intelligence, and it seems that current techniques can handle very complex human-computer games. So, one natural question raises: what are the possible challenges of current techniques in human-computer gaming, and what are the future trends? To answer the above question, in this paper, we survey recent successful game AIs, covering board game AIs, card game AIs, first-person shooting game AIs and real time strategy game AIs. Through this survey, we 1) compare the main difficulties among different kinds of games and the corresponding techniques utilized for achieving professional human level AIs; 2) summarize the mainstream frameworks and techniques that can be properly relied on for developing AIs for complex human-computer gaming; 3) raise the challenges or drawbacks of current techniques in the successful AIs; and 4) try to point out future trends in human-computer gaming AIs. Finally, we hope this brief review can provide an introduction for beginners, and inspire insights for researchers in the field of AI in human-computer gaming.

cs.AI↗

arXiv2022

Efficient, High-purity, Robust Sound Frequency Conversion with a Linear Metasurface

The intrinsic limitation of the material nonlinearity inevitably results in the poor mode purity, conversion efficiency and real-time reconfigurability of the generated harmonic waves, both in optics and acoustics. Rotational Doppler effect provides us an intuitive paradigm to shifting the frequency in a linear system, which needs to be facilitated by a spiraling phase change upon the wave propagation. Here we numerically and experimentally present a rotating linear vortex metasurface and achieve close-to-unity mode purity (above 95%) and conversion efficiency (above 65%) in audible sound frequency as low as 3000 Hz. The topological charge of the transmitted sound is almost immune from the rotational speed and transmissivity, demonstrating the mechanical robustness and stability in adjusting the high-performance frequency conversion in situ. These features enable us to cascade multiple vortex metasurfaces to further enlarge and diversify the extent of sound frequency conversion, which are experimentally verified. Our strategy takes a step further towards the freewheeling sound manipulation at acoustic frequency domain, and may have far-researching impacts in various acoustic communications, signal processing, and contactless detection.

physics.app-ph↗

arXiv2022

A Surrogate-Assisted Controller for Expensive Evolutionary Reinforcement Learning

The integration of Reinforcement Learning (RL) and Evolutionary Algorithms (EAs) aims at simultaneously exploiting the sample efficiency as well as the diversity and robustness of the two paradigms. Recently, hybrid learning frameworks based on this principle have achieved great success in various challenging robot control tasks. However, in these methods, policies from the genetic population are evaluated via interactions with the real environments, limiting their applicability in computationally expensive problems. In this work, we propose Surrogate-assisted Controller (SC), a novel and efficient module that can be integrated into existing frameworks to alleviate the computational burden of EAs by partially replacing the expensive policy evaluation. The key challenge in applying this module is to prevent the optimization process from being misled by the possible false minima introduced by the surrogate. To address this issue, we present two strategies for SC to control the workflow of hybrid frameworks. Experiments on six continuous control tasks from the OpenAI Gym platform show that SC can not only significantly reduce the cost of fitness evaluations, but also boost the performance of the original hybrid frameworks with collaborative learning and evolutionary processes.

cs.NE↗

arXiv2022

Latent-Variable Advantage-Weighted Policy Optimization for Offline RL

Offline reinforcement learning methods hold the promise of learning policies from pre-collected datasets without the need to query the environment for new transitions. This setting is particularly well-suited for continuous control robotic applications for which online data collection based on trial-and-error is costly and potentially unsafe. In practice, offline datasets are often heterogeneous, i.e., collected in a variety of scenarios, such as data from several human demonstrators or from policies that act with different purposes. Unfortunately, such datasets can exacerbate the distribution shift between the behavior policy underlying the data and the optimal policy to be learned, leading to poor performance. To address this challenge, we propose to leverage latent-variable policies that can represent a broader class of policy distributions, leading to better adherence to the training data distribution while maximizing reward via a policy over the latent variable. As we empirically show on a range of simulated locomotion, navigation, and manipulation tasks, our method referred to as latent-variable advantage-weighted policy optimization (LAPO), improves the average performance of the next best-performing offline reinforcement learning methods by 49% on heterogeneous datasets, and by 8% on datasets with narrow and biased distributions.

cs.LG↗