arXiv subjects

Yi Hou

Publications and source records attributed to Yi Hou.

17 recordsLinked to original sources

arXiv2026

Multi-Agent Reinforcement Learning from Delayed Marketplace Feedback for Objective-Weight Adaptation in Three-Sided Dispatch

Dispatch in three-sided marketplaces provides a natural setting for reinforcement learning from world feedback: decisions are evaluated by delayed operational outcomes such as delivery speed, courier utilization, and merchant congestion. We present a deployed reinforcement learning system at DoorDash that adapts dispatch objective weights in a large-scale food-delivery marketplace using delayed signals. Rather than replacing the combinatorial assignment optimizer, a store-level policy learned from logged marketplace data selects a discrete multiplier that shifts the dispatch optimizer's tradeoff between delivery quality and batching efficiency. This interface enables offline policy learning under noisy, delayed, and coupled feedback while preserving production feasibility constraints and operational safeguards. We train a shared value function using centralized offline data and decentralized store-level execution, with Double Q-learning targets and a conservative regularizer to reduce out-of-distribution value overestimation. In a production switchback experiment, the offline-trained policy increases batching and reduces courier-side time costs without degrading customer-facing delivery quality. Results illustrate how world feedback from a live economic and logistics system can be used to safely adapt decision policies online.

cs.AI↗

arXiv2026

Injectable Thermochemical Micro-Explosion for Prompt Thrombolysis via Liquid Alkali Metal

Thrombotic vascular diseases contribute to significant global mortality, yet current therapeutic strategies face persistent challenges including bleeding risks, suboptimal efficiency, and procedural complexity. Here, we report a micro-explosive thermochemical thrombolysis (METCT) therapy via injectable liquid alkali metal (LAM) encapsulated in dimethyl silicone (LAM@oil), which enables prompt, efficient and safe vascular recanalization within an ultrafast timeframe (< 90 seconds). This LAM@oil system effectively disrupts thrombus tissue through a synergistic triple-action mechanism: Mechanical micro-explosions forces, alkaline ablation due to highly localized exothermic chemical reactions, and thermal thrombolysis mediated by elevated temperature. Upon thrombolysis completion, the non-toxic reaction byproducts (sodium and potassium ions) exhibit physiologically biocompatible and metabolizable effects. Critically, the LAM@oil demonstrates significantly higher thrombolytic efficacy compared to clinically available thrombolytic drugs (residual thrombus area percent 10.87%+-7.16% for LAM@oil vs. 80.86%+-13.32% for urokinase), with no associated bleeding risks. This strategy opens a byproduct-free, cost-effective, and high-efficiency alternative to conventional thrombolytics, holding big potential for clinical translation in acute thrombosis management.

physics.med-ph↗

arXiv2024

An Integrated Artificial Intelligence Operating System for Advanced Low-Altitude Aviation Applications

This paper introduces a high-performance artificial intelligence operating system tailored for low-altitude aviation, designed to address key challenges such as real-time task execution, computational efficiency, and seamless modular collaboration. Built on a powerful hardware platform and leveraging the UNIX architecture, the system implements a distributed data processing strategy that ensures rapid and efficient synchronization across critical modules, including vision, navigation, and perception. By adopting dynamic resource management, it optimally allocates computational resources, such as CPU and GPU, based on task priority and workload, ensuring high performance for demanding tasks like real-time video processing and AI model inference. Furthermore, the system features an advanced interrupt handling mechanism that allows for quick responses to sudden environmental changes, such as obstacle detection, by prioritizing critical tasks, thus improving safety and mission success rates. Robust security measures, including data encryption, access control, and fault tolerance, ensure the system's resilience against external threats and its ability to recover from potential hardware or software failures. Complementing these core features are modular components for image analysis, multi-sensor fusion, dynamic path planning, multi-drone coordination, and ground station monitoring. Additionally, a low-code development platform simplifies user customization, making the system adaptable to various mission-specific needs. This comprehensive approach ensures the system meets the evolving demands of intelligent aviation, providing a stable, efficient, and secure environment for complex drone operations.

cs.LG↗

arXiv2024

VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model

In the realm of household robotics, the Zero-Shot Object Navigation (ZSON) task empowers agents to adeptly traverse unfamiliar environments and locate objects from novel categories without prior explicit training. This paper introduces VoroNav, a novel semantic exploration framework that proposes the Reduced Voronoi Graph to extract exploratory paths and planning nodes from a semantic map constructed in real time. By harnessing topological and semantic information, VoroNav designs text-based descriptions of paths and images that are readily interpretable by a large language model (LLM). In particular, our approach presents a synergy of path and farsight descriptions to represent the environmental context, enabling LLM to apply commonsense reasoning to ascertain waypoints for navigation. Extensive evaluation on HM3D and HSSD validates VoroNav surpasses existing benchmarks in both success rate and exploration efficiency (absolute improvement: +2.8% Success and +3.7% SPL on HM3D, +2.6% Success and +3.8% SPL on HSSD). Additionally introduced metrics that evaluate obstacle avoidance proficiency and perceptual efficiency further corroborate the enhancements achieved by our method in ZSON planning. Project page: https://voro-nav.github.io

cs.RO↗

arXiv2022

Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanisms

Blind watermarking provides powerful evidence for copyright protection, image authentication, and tampering identification. However, it remains a challenge to design a watermarking model with high imperceptibility and robustness against strong noise attacks. To resolve this issue, we present a framework Combining the Invertible and Non-invertible (CIN) mechanisms. The CIN is composed of the invertible part to achieve high imperceptibility and the non-invertible part to strengthen the robustness against strong noise attacks. For the invertible part, we develop a diffusion and extraction module (DEM) and a fusion and split module (FSM) to embed and extract watermarks symmetrically in an invertible way. For the non-invertible part, we introduce a non-invertible attention-based module (NIAM) and the noise-specific selection module (NSM) to solve the asymmetric extraction under a strong noise attack. Extensive experiments demonstrate that our framework outperforms the current state-of-the-art methods of imperceptibility and robustness significantly. Our framework can achieve an average of 99.99% accuracy and 67.66 dB PSNR under noise-free conditions, while 96.64% and 39.28 dB combined strong noise attacks. The code will be available in https://github.com/rmpku/CIN.

cs.MM↗

arXiv2022

Enhancing and Dissecting Crowd Counting By Synthetic Data

In this article, we propose a simulated crowd counting dataset CrowdX, which has a large scale, accurate labeling, parameterized realization, and high fidelity. The experimental results of using this dataset as data enhancement show that the performance of the proposed streamlined and efficient benchmark network ESA-Net can be improved by 8.4\%. The other two classic heterogeneous architectures MCNN and CSRNet pre-trained on CrowdX also show significant performance improvements. Considering many influencing factors determine performance, such as background, camera angle, human density, and resolution. Although these factors are important, there is still a lack of research on how they affect crowd counting. Thanks to the CrowdX dataset with rich annotation information, we conduct a large number of data-driven comparative experiments to analyze these factors. Our research provides a reference for a deeper understanding of the crowd counting problem and puts forward some useful suggestions in the actual deployment of the algorithm.

cs.CV↗

arXiv2022

BBA-net: A bi-branch attention network for crowd counting

In the field of crowd counting, the current mainstream CNN-based regression methods simply extract the density information of pedestrians without finding the position of each person. This makes the output of the network often found to contain incorrect responses, which may erroneously estimate the total number and not conducive to the interpretation of the algorithm. To this end, we propose a Bi-Branch Attention Network (BBA-NET) for crowd counting, which has three innovation points. i) A two-branch architecture is used to estimate the density information and location information separately. ii) Attention mechanism is used to facilitate feature extraction, which can reduce false responses. iii) A new density map generation method combining geometric adaptation and Voronoi split is introduced. Our method can integrate the pedestrian's head and body information to enhance the feature expression ability of the density map. Extensive experiments performed on two public datasets show that our method achieves a lower crowd counting error compared to other state-of-the-art methods.

cs.CV↗

arXiv2021

Arbitrary-Oriented Ship Detection through Center-Head Point Extraction

Ship detection in remote sensing images plays a crucial role in various applications and has drawn increasing attention in recent years. However, existing arbitrary-oriented ship detection methods are generally developed on a set of predefined rotated anchor boxes. These predefined boxes not only lead to inaccurate angle predictions but also introduce extra hyper-parameters and high computational cost. Moreover, the prior knowledge of ship size has not been fully exploited by existing methods, which hinders the improvement of their detection accuracy. Aiming at solving the above issues, in this paper, we propose a center-head point extraction based detector (named CHPDet) to achieve arbitrary-oriented ship detection in remote sensing images. Our CHPDet formulates arbitrary-oriented ships as rotated boxes with head points which are used to determine the direction. And rotated Gaussian kernel is used to map the annotations into target heatmaps. Keypoint estimation is performed to find the center of ships. Then, the size and head point of the ships are regressed. The orientation-invariant model (OIM) is also used to produce orientation-invariant feature maps. Finally, we use the target size as prior to finetune the results. Moreover, we introduce a new dataset for multi-class arbitrary-oriented ship detection in remote sensing images at a fixed ground sample distance (GSD) which is named FGSD2021. Experimental results on FGSD2021 and two other widely used data sets, i.e., HRSC2016, and UCAS-AOD demonstrate that our CHPDet achieves state-of-the-art performance and can well distinguish between bow and stern. Code and FGSD2021 dataset are available at https://github.com/zf020114/CHPDet.

cs.CV↗

arXiv2021

Decentralized Cooperative Lane Changing at Freeway Weaving Areas Using Multi-Agent Deep Reinforcement Learning

Frequent lane changes during congestion at freeway bottlenecks such as merge and weaving areas further reduce roadway capacity. The emergence of deep reinforcement learning (RL) and connected and automated vehicle technology provides a possible solution to improve mobility and energy efficiency at freeway bottlenecks through cooperative lane changing. Deep RL is a collection of machine-learning methods that enables an agent to improve its performance by learning from the environment. In this study, a decentralized cooperative lane-changing controller was developed using proximal policy optimization by adopting a multi-agent deep RL paradigm. In the decentralized control strategy, policy learning and action reward are evaluated locally, with each agent (vehicle) getting access to global state information. Multi-agent deep RL requires lower computational resources and is more scalable than single-agent deep RL, making it a powerful tool for time-sensitive applications such as cooperative lane changing. The results of this study show that cooperative lane changing enabled by multi-agent deep RL yields superior performance to human drivers in term of traffic throughput, vehicle speed, number of stops per vehicle, vehicle fuel efficiency, and emissions. The trained RL policy is transferable and can be generalized to uncongested, moderately congested, and extremely congested traffic conditions.

cs.MA↗

arXiv2021

A Modular and Transferable Reinforcement Learning Framework for the Fleet Rebalancing Problem

Mobility on demand (MoD) systems show great promise in realizing flexible and efficient urban transportation. However, significant technical challenges arise from operational decision making associated with MoD vehicle dispatch and fleet rebalancing. For this reason, operators tend to employ simplified algorithms that have been demonstrated to work well in a particular setting. To help bridge the gap between novel and existing methods, we propose a modular framework for fleet rebalancing based on model-free reinforcement learning (RL) that can leverage an existing dispatch method to minimize system cost. In particular, by treating dispatch as part of the environment dynamics, a centralized agent can learn to intermittently direct the dispatcher to reposition free vehicles and mitigate against fleet imbalance. We formulate RL state and action spaces as distributions over a grid partitioning of the operating area, making the framework scalable and avoiding the complexities associated with multiagent RL. Numerical experiments, using real-world trip and network data, demonstrate that this approach has several distinct advantages over baseline methods including: improved system cost; high degree of adaptability to the selected dispatch method; and the ability to perform scale-invariant transfer learning between problem instances with similar vehicle and request distributions.

eess.SY↗

arXiv2020

High Yield Growth and Doping of Black Phosphorus with Tunable Electronic Properties

Black phosphorus (BP) has recently attracted significant interest due to its unique electronic and optical properties. Doping is an effective strategy to tune a material's electronic structures, however, the direct and controllable growth of BP with a high yield and its doping remain a great challenge. Here we report an efficient short-distance transport (SDT) growth approach and achieve the controlled growth of high quality BP with the highest yield so far, where 98% of the red phosphorus is converted to BP. The doping of BP by As, Sb, Bi, Se and Te are also achieved by this SDT growth approach. Spectroscopic results show that doping systematically changes its electronic structures including band gap, work function, and energy band position. As a result, we have found that the air-stability of doped BP samples (Sb and Te-doped BP) improves compared with pristine BP, due to the downshift of the conduction band minimum with doping. This work develops a new method to grow BP and doped BP with tunable electronic structures and improved stability, and should extend the uses of these class of materials in various areas.

cond-mat.mtrl-sci↗

arXiv2019

Data-Driven Multi-step Demand Prediction for Ride-hailing Services Using Convolutional Neural Network

Ride-hailing services are growing rapidly and becoming one of the most disruptive technologies in the transportation realm. Accurate prediction of ride-hailing trip demand not only enables cities to better understand people's activity patterns, but also helps ride-hailing companies and drivers make informed decisions to reduce deadheading vehicle miles traveled, traffic congestion, and energy consumption. In this study, a convolutional neural network (CNN)-based deep learning model is proposed for multi-step ride-hailing demand prediction using the trip request data in Chengdu, China, offered by DiDi Chuxing. The CNN model is capable of accurately predicting the ride-hailing pick-up demand at each 1-km by 1-km zone in the city of Chengdu for every 10 minutes. Compared with another deep learning model based on long short-term memory, the CNN model is 30% faster for the training and predicting process. The proposed model can also be easily extended to make multi-step predictions, which would benefit the on-demand shared autonomous vehicles applications and fleet operators in terms of supply-demand rebalancing. The prediction error attenuation analysis shows that the accuracy stays acceptable as the model predicts more steps.

cs.LG↗

arXiv2016

A Gb/s Parallel Block-based Viterbi Decoder for Convolutional Codes on GPU

In this paper, we propose a parallel block-based Viterbi decoder (PBVD) on the graphic processing unit (GPU) platform for the decoding of convolutional codes. The decoding procedure is simplified and parallelized, and the characteristic of the trellis is exploited to reduce the metric computation. Based on the compute unified device architecture (CUDA), two kernels with different parallelism are designed to map two decoding phases. Moreover, the optimal design of data structures for several kinds of intermediate information are presented, to improve the efficiency of internal memory transactions. Experimental results demonstrate that the proposed decoder achieves high throughput of 598Mbps on NVIDIA GTX580 and 1802Mbps on GTX980 for the 64-state convolutional code, which are 1.5 times speedup compared to the existing fastest works on GPUs.

cs.DC↗

arXiv2015

Time-domain simulation of ultrasound propagation in a tissue-like medium based on the resolution of the nonlinear acoustic constitutive relations

A time-domain numerical code based on the constitutive relations of nonlinear acoustics for simulating ultrasound propagation is presented. To model frequency power law attenuation, such as observed in biological media, multiple relaxation processes are included and relaxation parameters are fitted to both exact frequency power law attenuation and empirically measured attenuation of a variety of tissues that does not fit an exact power law. A computational technique based on artificial relaxation is included to correct the non-negligible numerical dispersion of the numerical method and to improve stability when shock waves are present. This technique avoids the use of high order finite difference schemes, leading to fast calculations. The numerical code is especially suitable to study high intensity and focused axisymmetric acoustic beams in tissue-like medium, as it is based on the full constitutive relations that overcomes the limitations of the parabolic approximations, while some specific effects not contemplated by the Westervelt equation can be also studied. The accuracy of the method is discussed by comparing the proposed simulation solutions to one-dimensional analytical ones, to $k$-space numerical solutions and also to experimental data from a focused beam propagating in a frequency power law attenuation media.

physics.flu-dyn↗

arXiv2015

Convolutional Neural Network-Based Image Representation for Visual Loop Closure Detection

Deep convolutional neural networks (CNN) have recently been shown in many computer vision and pattern recog- nition applications to outperform by a significant margin state- of-the-art solutions that use traditional hand-crafted features. However, this impressive performance is yet to be fully exploited in robotics. In this paper, we focus one specific problem that can benefit from the recent development of the CNN technology, i.e., we focus on using a pre-trained CNN model as a method of generating an image representation appropriate for visual loop closure detection in SLAM (simultaneous localization and mapping). We perform a comprehensive evaluation of the outputs at the intermediate layers of a CNN as image descriptors, in comparison with state-of-the-art image descriptors, in terms of their ability to match images for detecting loop closures. The main conclusions of our study include: (a) CNN-based image representations perform comparably to state-of-the-art hand- crafted competitors in environments without significant lighting change, (b) they outperform state-of-the-art competitors when lighting changes significantly, and (c) they are also significantly faster to extract than the state-of-the-art hand-crafted features even on a conventional CPU and are two orders of magnitude faster on an entry-level GPU.

cs.RO↗

arXiv2014

Joint Successive Cancellation Decoding of Polar Codes over Intersymbol Interference Channels

Polar codes are a class of capacity-achieving codes for the binary-input discrete memoryless channels (B-DMCs). However, when applied in channels with intersymbol interference (ISI), the codes may perform poorly with BCJR equalization and conventional decoding methods. To deal with the ISI problem, in this paper a new joint successive cancellation (SC) decoding algorithm is proposed for polar codes in ISI channels, which combines the equalization and conventional decoding. The initialization information of the decoding method is the likelihood functions of ISI codeword symbols rather than the codeword symbols. The decoding adopts recursion formulas like conventional SC decoding and is without iterations. This is in contrast to the conventional iterative algorithm which performs iterations between the equalizer and decoder. In addition, the proposed SC trellis decoding can be easily extended to list decoding which can further improve the performance. Simulation shows that the proposed scheme significantly outperforms the conventional decoding schemes in ISI channels.

cs.IT↗

arXiv2014

Nonlinear Acoustics FDTD method including Frequency Power Law Attenuation for Soft Tissue Modeling

This paper describes a model for nonlinear acoustic wave propagation through absorbing and weakly dispersive media, and its numerical solution by means of finite differences in time domain method (FDTD). The attenuation is based on multiple relaxation processes, and provides frequency dependent absorption and dispersion without using computational expensive convolutional operators. In this way, by using an optimization algorithm the coefficients for the relaxation processes can be obtained in order to fit a frequency power law that agrees the experimentally measured attenuation data for heterogeneous media over the typical frequency range for ultrasound medical applications. Our results show that two relaxation processes are enough to fit attenuation data for most soft tissues in this frequency range including the fundamental and the first ten harmonics. Furthermore, this model can fit experimental attenuation data that do not follow exactly a frequency power law over the frequency range of interest. The main advantage of the proposed method is that only one auxiliary field per relaxation process is needed, which implies less computational resources compared with time-domain fractional derivatives solvers based on convolutional operators.

physics.med-ph↗