Search

Driving risk assessment is crucial for both autonomous vehicles and human-driven vehicles. The driving risk can be quantified as the product of the probability that an event (such as collision) will occur and the consequence of that event. However, the probability of events occurring is often difficult to predict due to the uncertainty of drivers' or vehicles' behavior. Traditional methods generally employ kinematic-based approaches to predict the future trajectories of entities, which often yield unrealistic prediction results. In this paper, the Enhanced Driving Risk Field (EDRF) model is proposed, integrating deep learning-based multimodal trajectory prediction results with Gaussian distribution models to quantitatively capture the uncertainty of traffic entities' behavior. The applications of the EDRF are also proposed. It is applied across various tasks (traffic risk monitoring, ego-vehicle risk analysis, and motion and trajectory planning) through the defined concept Interaction Risk (IR). Adequate example scenarios are provided for each application to illustrate the effectiveness of the model.

This study focuses on a critical aspect of bridge engineering -- the evaluation of cable forces, paying particular attention to the cables that are internally constrained by elastic supports. Detecting these cable forces is important for the safety and stability of bridges. The practical problem introduces a novel mathematical challenge: how to effectively address string vibration equations with one or multiple internal elastic supports,~which remains a theoretical issue not fully solved in engineering. To tackle this, it is necessary to firstly establish an appropriate mathematical model and accurately define initial-boundary value problems. We then formulate the well-posedness of the solution using both classical and weak solution approaches, supplementing the existing numerical results available in engineering. Meanwhile, we attempt to use PINNs (Physics-Informed Neural Networks) instead of traditional FEM (Finite Element Method) in engineering. Consequently, in contrast to the classical solution method, we demonstrate that for a string with finite elastic supports, the weak solution method not only improves mathematical modeling efficiency but also simplifies the process of explaining the well-posedness of the solution.

Safety is one of the most crucial challenges of autonomous driving vehicles, and one solution to guarantee safety is to employ an additional control revision module after the planning backbone. Control Barrier Function (CBF) has been widely used because of its strong mathematical foundation on safety. However, the incompatibility with heterogeneous perception data and incomplete consideration of traffic scene elements make existing systems hard to be applied in dynamic and complex real-world scenarios. In this study, we introduce a generalized control revision method for autonomous driving safety, which adopts both vectorized perception and occupancy grid map as inputs and comprehensively models multiple types of traffic scene constraints based on a new proposed barrier function. Traffic elements are integrated into one unified framework, decoupled from specific scenario settings or rules. Experiments on CARLA, SUMO, and OnSite simulator prove that the proposed algorithm could realize safe control revision under complicated scenes, adapting to various planning backbones, road topologies, and risk types. Physical platform validation also verifies the real-world application feasibility.

Visual bird's eye view (BEV) perception, due to its excellent perceptual capabilities, is progressively replacing costly LiDAR-based perception systems, especially in the realm of urban intelligent driving. However, this type of perception still relies on LiDAR data to construct ground truth databases, a process that is both cumbersome and time-consuming. Moreover, most massproduced autonomous driving systems are only equipped with surround camera sensors and lack LiDAR data for precise annotation. To tackle this challenge, we propose a fine-tuning method for BEV perception network based on visual 2D semantic perception, aimed at enhancing the model's generalization capabilities in new scene data. Considering the maturity and development of 2D perception technologies, our method significantly reduces the dependency on high-cost BEV ground truths and shows promising industrial application prospects. Extensive experiments and comparative analyses conducted on the nuScenes and Waymo public datasets demonstrate the effectiveness of our proposed method.

Domain-generalized nuclei segmentation refers to the generalizability of models to unseen domains based on knowledge learned from source domains and is challenged by various image conditions, cell types, and stain strategies. Recently, the Segment Anything Model (SAM) has made great success in universal image segmentation by interactive prompt modes (e.g., point and box). Despite its strengths, the original SAM presents limited adaptation to medical images. Moreover, SAM requires providing manual bounding box prompts for each object to produce satisfactory segmentation masks, so it is laborious in nuclei segmentation scenarios. To address these limitations, we propose a domain-generalizable framework for nuclei image segmentation, abbreviated to NuSegDG. Specifically, we first devise a Heterogeneous Space Adapter (HS-Adapter) to learn multi-dimensional feature representations of different nuclei domains by injecting a small number of trainable parameters into the image encoder of SAM. To alleviate the labor-intensive requirement of manual prompts, we introduce a Gaussian-Kernel Prompt Encoder (GKP-Encoder) to generate density maps driven by a single point, which guides segmentation predictions by mixing position prompts and semantic prompts. Furthermore, we present a Two-Stage Mask Decoder (TSM-Decoder) to effectively convert semantic masks to instance maps without the manual demand for morphological shape refinement. Based on our experimental evaluations, the proposed NuSegDG demonstrates state-of-the-art performance in nuclei instance segmentation, exhibiting superior domain generalization capabilities. The source code is available at https://github.com/xq141839/NuSegDG., Comment: Under Reivew

The universality of deep neural networks across different modalities and their generalization capabilities to unseen domains play an essential role in medical image segmentation. The recent Segment Anything Model (SAM) has demonstrated its potential in both settings. However, the huge computational costs, demand for manual annotations as prompts and conflict-prone decoding process of SAM degrade its generalizability and applicability in clinical scenarios. To address these issues, we propose an efficient self-prompting SAM for universal domain-generalized medical image segmentation, named ESP-MedSAM. Specifically, we first devise the Multi-Modal Decoupled Knowledge Distillation (MMDKD) strategy to construct a lightweight semi-parameter sharing image encoder that produces discriminative visual features for diverse modalities. Further, we introduce the Self-Patch Prompt Generator (SPPG) to automatically generate high-quality dense prompt embeddings for guiding segmentation decoding. Finally, we design the Query-Decoupled Modality Decoder (QDMD) that leverages a one-to-one strategy to provide an independent decoding channel for every modality. Extensive experiments indicate that ESP-MedSAM outperforms state-of-the-arts in diverse medical imaging segmentation tasks, displaying superior modality universality and generalization capabilities. Especially, ESP-MedSAM uses only 4.5\% parameters compared to SAM-H. The source code is available at https://github.com/xq141839/ESP-MedSAM., Comment: Under Review

Perception is essential for autonomous driving system. Recent approaches based on Bird's-eye-view (BEV) and deep learning have made significant progress. However, there exists challenging issues including lengthy development cycles, poor reusability, and complex sensor setups in perception algorithm development process. To tackle the above challenges, this paper proposes a novel hierarchical BEV perception paradigm, aiming to provide a library of fundamental perception modules and user-friendly graphical interface, enabling swift construction of customized models. We conduct the Pretrain-Finetune strategy to effectively utilize large scale public datasets and streamline development processes. Moreover, we present a Multi-Module Learning (MML) approach, enhancing performance through synergistic and iterative training of multiple models. Extensive experimental results on the Nuscenes dataset demonstrate that our approach renders significant improvement over the traditional training scheme.

Bird's-eye-view (BEV) semantic segmentation is becoming crucial in autonomous driving systems. It realizes ego-vehicle surrounding environment perception by projecting 2D multi-view images into 3D world space. Recently, BEV segmentation has made notable progress, attributed to better view transformation modules, larger image encoders, or more temporal information. However, there are still two issues: 1) a lack of effective understanding and enhancement of BEV space features, particularly in accurately capturing long-distance environmental features and 2) recognizing fine details of target objects. To address these issues, we propose OE-BevSeg, an end-to-end multimodal framework that enhances BEV segmentation performance through global environment-aware perception and local target object enhancement. OE-BevSeg employs an environment-aware BEV compressor. Based on prior knowledge about the main composition of the BEV surrounding environment varying with the increase of distance intervals, long-sequence global modeling is utilized to improve the model's understanding and perception of the environment. From the perspective of enriching target object information in segmentation results, we introduce the center-informed object enhancement module, using centerness information to supervise and guide the segmentation head, thereby enhancing segmentation performance from a local enhancement perspective. Additionally, we designed a multimodal fusion branch that integrates multi-view RGB image features with radar/LiDAR features, achieving significant performance improvements. Extensive experiments show that, whether in camera-only or multimodal fusion BEV segmentation tasks, our approach achieves state-of-the-art results by a large margin on the nuScenes dataset for vehicle segmentation, demonstrating superior applicability in the field of autonomous driving.

Adversarial attack on skeletal motion is a hot topic. However, existing researches only consider part of dynamic features when measuring distance between skeleton graph sequences, which results in poor imperceptibility. To this end, we propose a novel adversarial attack method to attack action recognizers for skeletal motions. Firstly, our method systematically proposes a dynamic distance function to measure the difference between skeletal motions. Meanwhile, we innovatively introduce emotional features for complementary information. In addition, we use Alternating Direction Method of Multipliers(ADMM) to solve the constrained optimization problem, which generates adversarial samples with better imperceptibility to deceive the classifiers. Experiments show that our method is effective on multiple action classifiers and datasets. When the perturbation magnitude measured by l norms is the same, the dynamic perturbations generated by our method are much lower than that of other methods. What's more, we are the first to prove the effectiveness of emotional features, and provide a new idea for measuring the distance between skeletal motions.

Limited by the scale and diversity of time series data, the neural networks trained on time series data often overfit and show unsatisfacotry performances. In comparison, large language models (LLMs) recently exhibit impressive generalization in diverse fields. Although massive LLM based approaches are proposed for time series tasks, these methods require to load the whole LLM in both training and reference. This high computational demands limit practical applications in resource-constrained settings, like edge-computing and IoT devices. To address this issue, we propose Knowledge Pruning (KP), a novel paradigm for time series learning in this paper. For a specific downstream task, we argue that the world knowledge learned by LLMs is much redundant and only the related knowledge termed as "pertinent knowledge" is useful. Unlike other methods, our KP targets to prune the redundant knowledge and only distill the pertinent knowledge into the target model. This reduces model size and computational costs significantly. Additionally, different from existing LLM based approaches, our KP does not require to load the LLM in the process of training and testing, further easing computational burdens. With our proposed KP, a lightweight network can effectively learn the pertinent knowledge, achieving satisfactory performances with a low computation cost. To verify the effectiveness of our KP, two fundamental tasks on edge-computing devices are investigated in our experiments, where eight diverse environments or benchmarks with different networks are used to verify the generalization of our KP. Through experiments, our KP demonstrates effective learning of pertinent knowledge, achieving notable performance improvements in regression (19.7% on average) and classification (up to 13.7%) tasks, showcasing state-of-the-art results., Comment: 12 pages, 5 figures

In this paper, we consider the problem of visual scanning mechanism underpinning sensorimotor tasks, such as walking and driving, in dynamic environments. We exploit eye tracking data for offering two new cognitive effort measures in visual scanning behavior of virtual driving. By utilizing the retinal flow induced by fixation, two novel measures of cognitive effort are proposed through the importance of grids in the viewing plane and the concept of information quantity, respectively. Psychophysical studies are conducted to reveal the effectiveness of the two proposed measures. Both these two cognitive effort measures have shown their significant correlation with pupil size change. Our results suggest that the quantitative exploitation of eye tracking data provides an effective approach for the evaluation of sensorimotor activities.

Deep neural networks (DNNs) have been widely used in many artificial intelligence (AI) tasks. However, deploying them brings significant challenges due to the huge cost of memory, energy, and computation. To address these challenges, researchers have developed various model compression techniques such as model quantization and model pruning. Recently, there has been a surge in research of compression methods to achieve model efficiency while retaining the performance. Furthermore, more and more works focus on customizing the DNN hardware accelerators to better leverage the model compression techniques. In addition to efficiency, preserving security and privacy is critical for deploying DNNs. However, the vast and diverse body of related works can be overwhelming. This inspires us to conduct a comprehensive survey on recent research toward the goal of high-performance, cost-efficient, and safe deployment of DNNs. Our survey first covers the mainstream model compression techniques such as model quantization, model pruning, knowledge distillation, and optimizations of non-linear operations. We then introduce recent advances in designing hardware accelerators that can adapt to efficient model compression approaches. Additionally, we discuss how homomorphic encryption can be integrated to secure DNN deployment. Finally, we discuss several issues, such as hardware evaluation, generalization, and integration of various compression approaches. Overall, we aim to provide a big picture of efficient DNNs, from algorithm to hardware accelerators and security perspectives., Comment: This manuscript is the accepted version for TNNLS(IEEE Transactions on Neural Networks and Learning Systems)

In driving tasks, the driver's situation awareness of the surrounding scenario is crucial for safety driving. However, current methods of measuring situation awareness mostly rely on subjective questionnaires, which interrupt tasks and lack non-intrusive quantification. To address this issue, our study utilizes objective gaze motion data to provide an interference-free quantification method for situation awareness. Three quantitative scores are proposed to represent three different levels of awareness: perception, comprehension, and projection, and an overall score of situation awareness is also proposed based on above three scores. To validate our findings, we conducted experiments where subjects performed driving tasks in a virtual reality simulated environment. All the four proposed situation awareness scores have clearly shown a significant correlation with driving performance. The proposed not only illuminates a new path for understanding and evaluating the situation awareness but also offers a satisfying proxy for driving performance.

Knowledge distillation (KD) has become a widely used technique in the field of model compression, which aims to transfer knowledge from a large teacher model to a lightweight student model for efficient network development. In addition to the supervision of ground truth, the vanilla KD method regards the predictions of the teacher as soft labels to supervise the training of the student model. Based on vanilla KD, various approaches have been developed to further improve the performance of the student model. However, few of these previous methods have considered the reliability of the supervision from teacher models. Supervision from erroneous predictions may mislead the training of the student model. This paper therefore proposes to tackle this problem from two aspects: Label Revision to rectify the incorrect supervision and Data Selection to select appropriate samples for distillation to reduce the impact of erroneous supervision. In the former, we propose to rectify the teacher's inaccurate predictions using the ground truth. In the latter, we introduce a data selection technique to choose suitable training samples to be supervised by the teacher, thereby reducing the impact of incorrect predictions to some extent. Experiment results demonstrate the effectiveness of our proposed method, and show that our method can be combined with other distillation approaches, improving their performance.

Byte-addressable non-volatile memory (NVM) sitting on the memory bus is employed to make persistent memory (PMem) in general-purpose computing systems and embedded systems for data storage. Researchers develop software drivers such as the block translation table (BTT) to build block devices on PMem, so programmers can keep using mature and reliable conventional storage stack while expecting high performance by exploiting fast PMem. However, our quantitative study shows that BTT underutilizes PMem and yields inferior performance, due to the absence of the imperative in-device cache. We add a conventional I/O staging cache made of DRAM space to BTT. As DRAM and PMem have comparable access latency, I/O staging cache is likely to be fully filled over time. Continual cache evictions and fsyncs thus cause on-demand flushes with severe stalls, such that the I/O staging cache is concretely unappealing for PMem-based block devices. We accordingly propose an algorithm named Caiti with novel I/O transit caching. Caiti eagerly evicts buffered data to PMem through CPU's multi-cores. It also conditionally bypasses a full cache and directly writes data into PMem to further alleviate I/O stalls. Experiments confirm that Caiti significantly boosts the performance with BTT by up to 3.6x, without loss of block-level write atomicity., Comment: Accepted by the Journal of Systems Architecture: Embedded Software Design (JSA)

In digital pathology, precise nuclei segmentation is pivotal yet challenged by the diversity of tissue types, staining protocols, and imaging conditions. Recently, the segment anything model (SAM) revealed overwhelming performance in natural scenarios and impressive adaptation to medical imaging. Despite these advantages, the reliance of labor-intensive manual annotation as segmentation prompts severely hinders their clinical applicability, especially for nuclei image analysis containing massive cells where dense manual prompts are impractical. To overcome the limitations of current SAM methods while retaining the advantages, we propose the Universal prompt-free SAM framework for Nuclei segmentation (UN-SAM), by providing a fully automated solution with remarkable generalization capabilities. Specifically, to eliminate the labor-intensive requirement of per-nuclei annotations for prompt, we devise a multi-scale Self-Prompt Generation (SPGen) module to revolutionize clinical workflow by automatically generating high-quality mask hints to guide the segmentation tasks. Moreover, to unleash the generalization capability of SAM across a variety of nuclei images, we devise a Domain-adaptive Tuning Encoder (DT-Encoder) to seamlessly harmonize visual features with domain-common and domain-specific knowledge, and further devise a Domain Query-enhanced Decoder (DQ-Decoder) by leveraging learnable domain queries for segmentation decoding in different nuclei domains. Extensive experiments prove that UN-SAM with exceptional performance surpasses state-of-the-arts in nuclei instance and semantic segmentation, especially the generalization capability in zero-shot scenarios. The source code is available at https://github.com/CUHK-AIM-Group/UN-SAM., Comment: 10 pages, 6 figures

Learning a human-like driving policy from large-scale driving demonstrations is promising, but the uncertainty and non-deterministic nature of planning make it challenging. In this work, to cope with the uncertainty problem, we propose VADv2, an end-to-end driving model based on probabilistic planning. VADv2 takes multi-view image sequences as input in a streaming manner, transforms sensor data into environmental token embeddings, outputs the probabilistic distribution of action, and samples one action to control the vehicle. Only with camera sensors, VADv2 achieves state-of-the-art closed-loop performance on the CARLA Town05 benchmark, significantly outperforming all existing methods. It runs stably in a fully end-to-end manner, even without the rule-based wrapper. Closed-loop demos are presented at https://hgao-cv.github.io/VADv2., Comment: Project Page: https://hgao-cv.github.io/VADv2

Data-driven predictive control promises model-free wave-dampening strategies for Connected and Autonomous Vehicles (CAVs) in mixed traffic flow. However, its performance relies on data quality, which suffers from unknown noise and disturbances. This paper introduces a Robust Data-EnablEd Predictive Leading Cruise Control (RDeeP-LCC) method based on reachability analysis, aiming to achieve safe and optimal CAV control under bounded process noise and external disturbances. Precisely, the matrix zonotope set technique and Willems' Fundamental Lemma are employed to derive the over-approximated system dynamics directly from data, and a data-driven feedback control technique is utilized to obtain an additional feedback input for stability. We decouple the mixed platoon into an error system and a nominal system, where the error system provides data-driven reachability sets for the enhanced safety constraints in the nominal system. Finally, a data-driven predictive control framework is formulated in a tube-based control manner for robustness guarantees. Nonlinear simulations with noise-corrupted data demonstrate that the proposed method outperforms baseline methods in mitigating traffic waves., Comment: 8 pages, 4 figures

Speech enhancement is widely used as a front-end to improve the speech quality in many audio systems, while it is hard to extract the target speech in multi-talker conditions without prior information on the speaker identity. It was shown that the auditory attention on the target speaker can be decoded from the electroencephalogram (EEG) of the listener implicitly. In this work, we therefore propose a novel end-to-end brain-assisted speech enhancement network (BASEN), which incorporates the listeners' EEG signals and adopts a temporal convolutional network together with a convolutional multi-layer cross attention module to fuse EEG-audio features. Considering that an EEG cap with sparse channels exhibits multiple benefits and in practice many electrodes might contribute marginally, we further propose two channel selection methods, called residual Gumbel selection and convolutional regularization selection. They are dedicated to tackling training instability and duplicated channel selections, respectively. Experimental results on a public dataset show the superiority of the proposed BASEN over existing approaches. The proposed channel selection methods can significantly reduce the amount of informative EEG channels with a negligible impact on the performance., Comment: arXiv admin note: text overlap with arXiv:2305.09994

This article is devoted to addressing the cloud control of connected vehicles, specifically focusing on analyzing the effect of bi-directional communication-induced delays. To mitigate the adverse effects of such delays, a novel predictor-observer structured controller is proposed which compensate for both measurable output delays and unmeasurable, yet bounded, input delays simultaneously. The study begins by novelly constructing an equivalent delay-free inter-connected system model that incorporates the Predictor-Observer controller, considering certain delay boundaries and model uncertainties. Subsequently, a stability analysis is conducted to assess the system's robustness under these conditions. Next, the connected vehicle lateral control scenario is built which contain high-fidelity vehicle dynamic model. The results demonstrate the controller's ability to accurately predict the system states, even under time-varying bi-directional delays. Finally, the proposed method is deployed in a real connected vehicle lateral control system. Comparative tests with a conventional linear feedback controller showcase significantly improved control performance under dominant bi-directional delay conditions, affirming the superiority of the proposed method against the delay.

The emergence of connected and automated vehicles (CAVs) promises smoother traffic flow. In mixed traffic where human-driven vehicles (HDVs) also exist, existing research mostly focuses on "looking ahead" (i.e., the CAVs receive information from preceding vehicles) strategies for CAVs, while recent work reveals that "looking behind" (i.e., the CAVs receive information from their rear vehicles) strategies might provide more possibilities for CAV longitudinal control. This paper presents a comparative study between these two types of information flow topology (IFT) from the string stability perspective, with the role of maximum platoon size (MPS) also under investigation. Precisely, we provide a dynamical modeling framework for the mixed platoon under the multi-predecessor-following (MPF) topology and the multi-successor-leading (MSL) topology. Then, a unified method for string stability analysis is presented, with explicit consideration of both IFT and MPS. Numerical results suggest that MSL ("looking behind") outperforms MPF ("looking ahead" ) in mitigating traffic perturbations. In addition, increasing MPS could further improve string stability of mixed traffic flow., Comment: This paper has been accepted by 26th IEEE International Conference on Intelligent Transportation Systems ITSC 2023

Image segmentation plays an essential role in nuclei image analysis. Recently, the segment anything model has made a significant breakthrough in such tasks. However, the current model exists two major issues for cell segmentation: (1) the image encoder of the segment anything model involves a large number of parameters. Retraining or even fine-tuning the model still requires expensive computational resources. (2) in point prompt mode, points are sampled from the center of the ground truth and more than one set of points is expected to achieve reliable performance, which is not efficient for practical applications. In this paper, a single-point prompt network is proposed for nuclei image segmentation, called SPPNet. We replace the original image encoder with a lightweight vision transformer. Also, an effective convolutional block is added in parallel to extract the low-level semantic information from the image and compensate for the performance degradation due to the small image encoder. We propose a new point-sampling method based on the Gaussian kernel. The proposed model is evaluated on the MoNuSeg-2018 dataset. The result demonstrated that SPPNet outperforms existing U-shape architectures and shows faster convergence in training. Compared to the segment anything model, SPPNet shows roughly 20 times faster inference, with 1/70 parameters and computational cost. Particularly, only one set of points is required in both the training and inference phases, which is more reasonable for clinical applications. The code for our work and more technical details can be found at https://github.com/xq141839/SPPNet.

For many real-world time series tasks, the computational complexity of prevalent deep leaning models often hinders the deployment on resource-limited environments (e.g., smartphones). Moreover, due to the inevitable domain shift between model training (source) and deploying (target) stages, compressing those deep models under cross-domain scenarios becomes more challenging. Although some of existing works have already explored cross-domain knowledge distillation for model compression, they are either biased to source data or heavily tangled between source and target data. To this end, we design a novel end-to-end framework called Universal and joint knowledge distillation (UNI-KD) for cross-domain model compression. In particular, we propose to transfer both the universal feature-level knowledge across source and target domains and the joint logit-level knowledge shared by both domains from the teacher to the student model via an adversarial learning scheme. More specifically, a feature-domain discriminator is employed to align teacher's and student's representations for universal knowledge transfer. A data-domain discriminator is utilized to prioritize the domain-shared samples for joint knowledge transfer. Extensive experimental results on four time series datasets demonstrate the superiority of our proposed method over state-of-the-art (SOTA) benchmarks., Comment: Accepted by IJCAI 2023

Chest radiographs are the most commonly performed radiological examinations for lesion detection. Recent advances in deep learning have led to encouraging results in various thoracic disease detection tasks. Particularly, the architecture with feature pyramid network performs the ability to recognise targets with different sizes. However, such networks are difficult to focus on lesion regions in chest X-rays due to their high resemblance in vision. In this paper, we propose a dual attention supervised module for multi-label lesion detection in chest radiographs, named DualAttNet. It efficiently fuses global and local lesion classification information based on an image-level attention block and a fine-grained disease attention algorithm. A binary cross entropy loss function is used to calculate the difference between the attention map and ground truth at image level. The generated gradient flow is leveraged to refine pyramid representations and highlight lesion-related features. We evaluate the proposed model on VinDr-CXR, ChestX-ray8 and COVID-19 datasets. The experimental results show that DualAttNet surpasses baselines by 0.6% to 2.7% mAP and 1.4% to 4.7% AP50 with different detection architectures. The code for our work and more technical details can be found at https://github.com/xq141839/DualAttNet.

The deep learning, which is a dominating technique in artificial intelligence, has completely changed the image understanding over the past decade. As a consequence, the sea ice extraction (SIE) problem has reached a new era. We present a comprehensive review of four important aspects of SIE, including algorithms, datasets, applications, and the future trends. Our review focuses on researches published from 2016 to the present, with a specific focus on deep learning-based approaches in the last five years. We divided all relegated algorithms into 3 categories, including classical image segmentation approach, machine learning-based approach and deep learning-based methods. We reviewed the accessible ice datasets including SAR-based datasets, the optical-based datasets and others. The applications are presented in 4 aspects including climate research, navigation, geographic information systems (GIS) production and others. It also provides insightful observations and inspiring future research directions., Comment: 24 pages, 6 figures

In empathetic conversations, individuals express their empathy towards others. Previous work has mainly focused on generating empathetic responses by utilizing the speaker's emotion. Besides, external commonsense knowledge has been applied to enhance the system's understandings of the speaker's situation. However, given an event, commonsense knowledge base contains various relations, potentially leading to confusion for the dialogue system. Consequently, inconsistencies arise among the emotion, generated response and speaker's contextual information. To this end, we propose a novel approach for empathetic response generation, which incorporates an adaptive module for commonsense knowledge selection to ensure consistency between the generated empathetic responses and the speaker's situation. This selected knowledge is used to refine the commonsense cognition and empathy expression for generated responses. Experimental results show that our approach significantly outperforms baseline models in both automatic and human evaluations, exhibiting the generation of more coherent and empathetic responses. Moreover, case studies highlight the interpretability of knowledge selection in the responses and the effectiveness of adaptive module in our model. Code: https://github.com/Hanscal/DCKS., Comment: Accepted by ACL 2023. arXiv admin note: substantial text overlap with arXiv:2109.05739 by other authors

Time-domain single-channel speech enhancement (SE) still remains challenging to extract the target speaker without any prior information on multi-talker conditions. It has been shown via auditory attention decoding that the brain activity of the listener contains the auditory information of the attended speaker. In this paper, we thus propose a novel time-domain brain-assisted SE network (BASEN) incorporating electroencephalography (EEG) signals recorded from the listener for extracting the target speaker from monaural speech mixtures. The proposed BASEN is based on the fully-convolutional time-domain audio separation network. In order to fully leverage the complementary information contained in the EEG signals, we further propose a convolutional multi-layer cross attention module to fuse the dual-branch features. Experimental results on a public dataset show that the proposed model outperforms the state-of-the-art method in several evaluation metrics. The reproducible code is available at https://github.com/jzhangU/Basen.git., Comment: Submitted to ISCA Interspeech 2023

A road is the skeleton of a city and is a fundamental and important geographical component. Currently, many countries have built geo-information databases and gathered large amounts of geographic data. However, with the extensive construction of infrastructure and rapid expansion of cities, automatic updating of road data is imperative to maintain the high quality of current basic geographic information. However, obtaining bi-phase images for the same area is difficult, and complex post-processing methods are required to update the existing databases.To solve these problems, we proposed a road detection method based on semi-supervised learning (SRUNet) specifically for road-updating applications; in this approach, historical road information was fused with the latest images to directly obtain the latest state of the road.Considering that the texture of a road is complex, a multi-branch network, named the Map Encoding Branch (MEB) was proposed for representation learning, where the Boundary Enhancement Module (BEM) was used to improve the accuracy of boundary prediction, and the Residual Refinement Module (RRM) was used to optimize the prediction results. Further, to fully utilize the limited amount of label information and to enhance the prediction accuracy on unlabeled images, we utilized the mean teacher framework as the basic semi-supervised learning framework and introduced Regional Contrast (ReCo) in our work to improve the model capacity for distinguishing between the characteristics of roads and background elements.We applied our method to two datasets. Our model can effectively improve the performance of a model with fewer labels. Overall, the proposed SRUNet can provide stable, up-to-date, and reliable prediction results for a wide range of road renewal tasks., Comment: 22 pages, 8 figures

Autonomous driving requires a comprehensive understanding of the surrounding environment for reliable trajectory planning. Previous works rely on dense rasterized scene representation (e.g., agent occupancy and semantic map) to perform planning, which is computationally intensive and misses the instance-level structure information. In this paper, we propose VAD, an end-to-end vectorized paradigm for autonomous driving, which models the driving scene as a fully vectorized representation. The proposed vectorized paradigm has two significant advantages. On one hand, VAD exploits the vectorized agent motion and map elements as explicit instance-level planning constraints which effectively improves planning safety. On the other hand, VAD runs much faster than previous end-to-end planning methods by getting rid of computation-intensive rasterized representation and hand-designed post-processing steps. VAD achieves state-of-the-art end-to-end planning performance on the nuScenes dataset, outperforming the previous best method by a large margin. Our base model, VAD-Base, greatly reduces the average collision rate by 29.0% and runs 2.5x faster. Besides, a lightweight variant, VAD-Tiny, greatly improves the inference speed (up to 9.3x) while achieving comparable planning performance. We believe the excellent performance and the high efficiency of VAD are critical for the real-world deployment of an autonomous driving system. Code and models are available at https://github.com/hustvl/VAD for facilitating future research., Comment: Accepted to ICCV 2023. Code&Demos: https://github.com/hustvl/VAD

Reliable and efficient validation technologies are critical for the recent development of multi-vehicle cooperation and vehicle-road-cloud integration. In this paper, we introduce our miniature experimental platform, Mixed Cloud Control Testbed (MCCT), developed based on a new notion of Mixed Digital Twin (mixedDT). Combining Mixed Reality with Digital Twin, mixedDT integrates the virtual and physical spaces into a mixed one, where physical entities coexist and interact with virtual entities via their digital counterparts. Under the framework of mixedDT, MCCT contains three major experimental platforms in the physical, virtual and mixed spaces respectively, and provides a unified access for various human-machine interfaces and external devices such as driving simulators. A cloud unit, where the mixed experimental platform is deployed, is responsible for fusing multi-platform information and assigning control instructions, contributing to synchronous operation and real-time cross-platform interaction. Particularly, MCCT allows for multi-vehicle coordination composed of different multi-source vehicles (\eg, physical vehicles, virtual vehicles and human-driven vehicles). Validations on vehicle platooning demonstrate the flexibility and scalability of MCCT., Comment: 13 pages, 13 figures

Today solid-state cooling technologies below liquid nitrogen boiling temperature (77 K), crucial to quantum information technology and probing quantum state of matter, are greatly limited due to the lack of good thermoelectric and/or thermomagnetic materials. Here, we report the discovery of colossal Nernst power factor of 3800$\times$10$^{-4}$ W m$^{-1}$ K$^{-2}$ under 5 T at 25 K and high Nernst figure-of-merit of 71$\times$10$^{-4}$ K$^{-1}$ under 5 T at 20 K in topological semimetal NbSb$_2$ single crystals. The observed high thermomagnetic performance is attributed to large Nernst thermopower and longitudinal electrical conductivity, and relatively low transverse thermal conductivity. The large and unsaturated Nernst thermopower is the result of the combination of highly desirable electronic structures of NbSb$_2$ having compensated high mobility electrons and holes near Fermi level and strong phonon-drag effect. This discovery opens an avenue for exploring material option for the solid-state heat pumping below liquid nitrogen temperature.

Cooperative control of connected and automated vehicles (CAVs) promises smoother traffic flow. In mixed traffic, where human-driven vehicles with unknown dynamics coexist, data-driven predictive control techniques allow for CAV safe and optimal control with measurable traffic data. However, the centralized control setting in most existing strategies limits their scalability for large-scale mixed traffic flow. To address this problem, this paper proposes a cooperative DeeP-LCC (Data-EnablEd Predictive Leading Cruise Control) formulation and its distributed implementation algorithm. In cooperative DeeP-LCC, the traffic system is naturally partitioned into multiple subsystems with one single CAV, which collects local trajectory data for subsystem behavior predictions based on the Willems' fundamental lemma. Meanwhile, the cross-subsystem interaction is formulated as a coupling constraint. Then, we employ the Alternating Direction Method of Multipliers (ADMM) to design the distributed DeeP-LCC algorithm. This algorithm achieves both computation and communication efficiency, as well as trajectory data privacy, through parallel calculation. Our simulations on different traffic scales verify the real-time wave-dampening potential of distributed DeeP-LCC, which can reduce fuel consumption by over 31.84% in a large-scale traffic system of 100 vehicles with only 5%-20% CAVs., Comment: 28 pages, 9 figures

Deep Q-learning Network (DQN) is a successful way which combines reinforcement learning with deep neural networks and leads to a widespread application of reinforcement learning. One challenging problem when applying DQN or other reinforcement learning algorithms to real world problem is data collection. Therefore, how to improve data efficiency is one of the most important problems in the research of reinforcement learning. In this paper, we propose a framework which uses the Max-Mean loss in Deep Q-Network (M$^2$DQN). Instead of sampling one batch of experiences in the training step, we sample several batches from the experience replay and update the parameters such that the maximum TD-error of these batches is minimized. The proposed method can be combined with most of existing techniques of DQN algorithm by replacing the loss function. We verify the effectiveness of this framework with one of the most widely used techniques, Double DQN (DDQN), in several gym games. The results show that our method leads to a substantial improvement in both the learning speed and performance., Comment: 5 pages

In this paper, we present the first experimental results of data-driven predictive control for connected and autonomous vehicles (CAVs) in dissipating traffic waves. In particular, we consider a recent strategy of Data-EnablEd Predicted Leading Cruise Control (DeeP-LCC), which bypasses the need of identifying the driving behaviors of surrounding vehicles and directly relies on measurable traffic data to achieve safe and optimal CAV control in mixed traffic. We present the implementation details of DeeP-LCC, including data collection, equilibrium estimation, and control execution. Based on a miniature experiment platform, we reproduce the phenomenon of stop-and-go waves in two typical traffic scenarios: 1) open straight-road scenario under external disturbances and 2) closed ring-road scenario with no bottlenecks. Our experiments clearly demonstrate that DeeP-LCC enables one or a few CAVs to dissipate the traffic waves in both traffic scenarios. These experimental findings validate the great potential of DeeP-LCC in smoothing practical traffic flow in the presence of noisy data, uncertain low-level vehicle dynamics, and communication and computation delays. The code and videos of our experimental results are available at https://github.com/soc-ucsd/DeeP-LCC., Comment: 14 pages, 11 figures

For the control of connected and autonomous vehicles (CAVs), most existing methods focus on model-based strategies. They require explicit knowledge of car-following dynamics of human-driven vehicles that are non-trivial to identify accurately. In this paper, instead of relying on a parametric car-following model, we introduce a data-driven non-parametric strategy, called DeeP-LCC (Data-EnablEd Predictive Leading Cruise Control), to achieve safe and optimal control of CAVs in mixed traffic. We first utilize Willems' fundamental lemma to obtain a data-centric representation of mixed traffic behavior. This is justified by rigorous analysis on controllability and observability properties of mixed traffic. We then employ a receding horizon strategy to solve a finite-horizon optimal control problem at each time step, in which input/output constraints are incorporated for collision-free guarantees. Numerical experiments validate the performance of DeeP-LCC compared to a standard predictive controller that requires an accurate model. Multiple nonlinear traffic simulations further confirm its great potential on improving traffic efficiency, driving safety, and fuel economy., Comment: 16 pages, 8 figures. arXiv admin note: text overlap with arXiv:2110.10097

Deep learning architecture with convolutional neural network (CNN) achieves outstanding success in the field of computer vision. Where U-Net, an encoder-decoder architecture structured by CNN, makes a great breakthrough in biomedical image segmentation and has been applied in a wide range of practical scenarios. However, the equal design of every downsampling layer in the encoder part and simply stacked convolutions do not allow U-Net to extract sufficient information of features from different depths. The increasing complexity of medical images brings new challenges to the existing methods. In this paper, we propose a deeper and more compact split-attention u-shape network (DCSAU-Net), which efficiently utilises low-level and high-level semantic information based on two novel frameworks: primary feature conservation and compact split-attention block. We evaluate the proposed model on CVC-ClinicDB, 2018 Data Science Bowl, ISIC-2018 and SegPC-2021 datasets. As a result, DCSAU-Net displays better performance than other state-of-the-art (SOTA) methods in terms of the mean Intersection over Union (mIoU) and F1-socre. More significantly, the proposed model demonstrates excellent segmentation performance on challenging images. The code for our work and more technical details can be found at https://github.com/xq141839/DCSAU-Net.

Formation control methods of connected and automated vehicles have been proposed to smoothly switch the structure of vehicular formations in different scenarios. In the previous research, simulations are often conducted to verify the performance of formation control methods. This paper presents the experimental results of multi-lane formation control for connected and automated vehicles. The coordinated formation control framework and specific methods utilized for different scenarios are introduced. The details of experimental platform and vehicle control strategy is provided. Simulations and experiments are conducted in different scenarios, and the results indicate that the formation control method is applicable to multiple traffic scenarios and able to improve formation-structure-switching efficiency compared with benchmark methods.

With the development of V2X technology, multiple vehicles cooperative control has been widely studied. However, filed testing is rarely conducted due to financial and safety considerations. To solve this problem, this study proposes a digital twin method to carry out multi-vehicle experiments, which uses combination of physical and virtual vehicles to perform coordination tasks. To confirm effectiveness of this method, a prototype system is developed, which consists of sand table testbed, its twin system and cloud. Several aspects are quantified to describe system performance, including time delay and localization accuracy. Finally, a vehicle level experiment in platoon scenario is carried out and experiment results confirm effectiveness of this method.

Cooperative control of Connected and Autonomous Vehicles (CAVs) promises great benefits for mixed traffic. Most existing research focuses on model-based control strategies, assuming that car-following dynamics of human-driven vehicles are explicitly known. In this paper, instead of relying on a parametric car-following model, we introduce a data-driven predictive control strategy to achieve safe and optimal control for CAVs in mixed traffic. We first present a linearized dynamical model for mixed traffic systems, and investigate its controllability and observability. Based on these control-theoretic properties, we then propose a novel DeeP-LCC (Data-EnablEd Predictive Leading Cruise Control) strategy for CAVs based on measurable driving data to smooth mixed traffic. Our method is implemented in a receding horizon manner, in which input/output constraints are incorporated to achieve collision-free guarantees. Nonlinear traffic simulations reveal its saving of up to 24.96% fuel consumption during a braking scenario of Extra-Urban Driving Cycle while ensuring safety., Comment: 7 figures, 3 figures

The cooperation of connected and automated vehicles (CAVs) has shown great potential in improving traffic efficiency during intersection management. Existing research mainly focuses on intersections where lane changing is prohibited, which is impractical for real-life implementation. This paper proposes a two-stage cooperation framework, which decouples the longitudinal and lateral control of CAVs, allowing them to change to their preferred lanes. Based on formation control, an iterative framework is initially proposed to solve the target assignment and path planning problem for multiple CAVs on multiple lanes. A graph-based minimum clique cover method is then applied to obtain the optimal scheduling plan for the CAVs. Extensive numerical simulations for different numbers of vehicles and traffic volumes validate the effectiveness of the proposed algorithm., Comment: arXiv admin note: text overlap with arXiv:2107.07179

Unsignalized intersection cooperation of connected and automated vehicles (CAVs) is able to eliminate green time loss of signalized intersections and improve traffic efficiency. Most of the existing research on unsignalized intersection cooperation considers fixed lane direction, where only specific turning behavior of vehicles is allowed on each lane. Given that traffic volume and the proportion of vehicles with different turning expectation may change with time, fixed lane direction may lead to inefficiency at intersections. This paper proposes a multi-lane unsignalized intersection cooperation method that considers flexible lane direction. The two-dimensional distribution of vehicles is calculated and vehicles that are not in conflict are scheduled to pass the intersection simultaneously. The formation reconfiguration method is utilized to achieve collision-free longitudinal and lateral position adjustment of vehicles. Simulations are conducted at different input traffic volumes and turning proportion of incoming vehicles, and the results indicate that our method outperformances the fixed-lane-direction unsignalized cooperation method and the signalized method.

Connected and automated vehicles have shown great potential in improving traffic mobility and reducing emissions, especially at unsignalized intersections. Previous research has shown that vehicle passing order is the key influencing factor in improving intersection traffic mobility. In this paper, we propose a graph-based cooperation method to formalize the conflict-free scheduling problem at an unsignalized intersection. Based on graphical analysis, a vehicle's trajectory conflict relationship is modeled as a conflict directed graph and a coexisting undirected graph. Then, two graph-based methods are proposed to find the vehicle passing order. The first is an improved depth-first spanning tree algorithm, which aims to find the local optimal passing order vehicle by vehicle. The other novel method is a minimum clique cover algorithm, which identifies the global optimal solution. Finally, a distributed control framework and communication topology are presented to realize the conflict-free cooperation of vehicles. Extensive numerical simulations are conducted for various numbers of vehicles and traffic volumes, and the simulation results prove the effectiveness of the proposed algorithms.

Multi-lane roads are typical scenarios in the real-world traffic system. Vehicles usually have preference on lanes according to their routes and destinations. Few of the existing studies looks into the problem of controlling vehicles to drive on their desired lanes. This paper proposes a formation control method that considers vehicles' preference on different lanes. The bi-level formation control framework is utilized to plan collision-free motion for vehicles, where relative target assignment and path planning are performed in the upper level, and trajectory planning and tracking are performed in the lower level. The collision-free multi-vehicle path planning problem considering lane preference is decoupled into two sub problems: calculating assignment list with non-decreasing cost and planning collision-free paths according to given assignment result. The Conflict-based Searching (CBS) method is utilized to plan collision-free paths for vehicles based on given assignment results. Case study is conducted and simulations are carried out in a three-lane road scenario. The results indicate that the proposed formation control method significantly reduces congestion and improves traffic efficiency at high traffic volumes, compared to the rule-based method.

Metasurfaces are planar structures that can manipulate the amplitude, phase and polarization (APP) of light at subwavelength scale. Although various functionalities have been proposed based on metasurface, a most general optical control, i.e., independent complex-amplitude (amplitude and phase) control of arbitrary two orthogonal states of polarizations, has not yet been realized. Such level of optical control can not only cover the various functionalities realized previously, but also enable new functionalities that are not feasible before. Here, we propose a single-layer dielectric metasurface to realize this goal and experimentally demonstrate several advanced functionalities, such as two independent full-color printing images under arbitrary elliptically orthogonal polarizations and dual sets of printing-hologram integrations. Our work opens the way for a wide range of applications in advanced image display, information encoding, and polarization optics., Comment: 23 pages, 4 figures

Major accidents (e.g., the Space Shuttle Challenger disaster in the USA, the Bhopal Disaster in India, Fukushima nuclear accident in Japan, Tianjin Port fire and explosion accident in China) have occurred all over the world. Safety scientists are always trying to understand why these accidents happened and how to prevent these accidents. Accident models and theories form the basis for many safety research fields and practices such as investigation of accidents, design of a safer system and decision making on safety related field. There is no universally accepted model with useful elements relating to understanding accident causation, although many accident causation models exist. Based on STAMP and RMF, we proposed a new theory named the Interaction Theory of Hazard-Target System (ITHTS) that incorporate human, organisational and technological characteristics in the same framework. Accident analysis methods provide the necessary information to analysis the accident in a specific setting. In order to solve the issues that current accident analysis methods still face, we proposed a new systemic accident analysis method based on ITHTS and STPA. We choose Tianjin Port fire and explosion accident in China as a case study to demonstrate the viability of the Interaction Theory of Hazard-target System and the applicability of the new accident analysis method. It is concluded that ITHTS can explain the phenomena in safety practice and the new accident analysis method can be application in the explanation and analysis of major accident., Comment: 28 pages, 9 figures, 3 tables

Electric, intelligent, and network are the most important future development directions of automobiles. Intelligent electric vehicles have shown great potentials to improve traffic mobility and reduce emissions, especially at unsignalized intersections. Previous research has shown that vehicle passing order is the key factor in traffic mobility improvement. In this paper, we propose a graph-based cooperation method to formalize the conflict-free scheduling problem at unsignalized intersections. Firstly, conflict directed graphs and coexisting undirected graphs are built to describe the conflict relationship of the vehicles. Then, two graph-based methods are introduced to solve the vehicle passing order. One method is an optimized depth-first spanning tree method which aims to find the local optimal passing order for each vehicle. The other method is a maximum matching algorithm that solves the global optimal problem. The computational complexity of both methods is also derived. Numerical simulation results demonstrate the effectiveness of the proposed algorithms.

Multi-vehicle coordinated decision making and control can improve traffic efficiency while guaranteeing driving safety. Formation control is a typical multi-vehicle coordination method in the multi-lane scenario. Among the existing formation control methods, the formation switching process is predefined and the collision-free behavior of vehicles has not been considered and explained in detail. This paper proposes a formation control method for multiple Connected and Automated Vehicles (CAVs) on multi-lane roads. Firstly, a bi-level planning framework is proposed to switch the structure of the formation in different scenarios smoothly and effectively. Secondly, the relative coordinate system is established and the conflict-free relative paths are planned in the upper level. Then, multi-stage trajectory planning and tracking are modeled and solved as an optimal control problem with path constraints in the lower level. Next, case study is conducted to verify the function of the proposed method in different scenarios. Finally, simulation in the lane-drop bottleneck scenario is carried out under different traffic volume and numerical results indicate that the proposed method can improve both traffic efficiency and fuel economy at high traffic volume.

With the development of deep learning technology, multi-spectral image super-resolution methods based on convolutional neural network have recently achieved great progress. However, the single hyperspectral image super-resolution remains a challenging problem due to the high-dimensional and complex spectral characteristics of hyperspectral data, which make it difficult to simultaneously capture spatial and spectral information. To deal with this issue, we propose a novel Feedback Refined Local-Global Network (FRLGN) for the super-resolution of hyperspectral image. To be specific, we develop a new Feedback Structure and a Local-Global Spectral Block to alleviate the difficulty in spatial and spectral feature extraction. The Feedback Structure can transfer the high-level information to guide the generation process of low-level feature, which is achieved by a recurrent structure with finite unfoldings. Furthermore, in order to effectively use the high-level information passed back, a Local-Global Spectral Block is constructed to handle the feedback connections. The Local-Global Spectral Block utilizes the feedback high-level information to correct the low-level feature from local spectral bands and generates powerful high-level representations among global spectral bands. By incorporating the Feedback Structure and Local-Global Spectral Block, the FRLGN can fully exploit spatial-spectral correlations among spectral bands and gradually reconstruct high-resolution hyperspectral images. The source code of FRLGN is available at https://github.com/tangzhenjie/FRLGN.

In this paper, we propose a maximum entropy method for predicting disease risks. It is based on a patient's medical history with diseases coded in ICD-10 which can be used in various cases. The complete algorithm with strict mathematical derivation is given. We also present experimental results on a medical dataset, demonstrating that our method performs well in predicting future disease risks and achieves an accuracy rate twice that of the traditional method. We also perform a comorbidity analysis to reveal the intrinsic relation of diseases., Comment: 15 pages

Lithium niobate on insulator (LNOI) is an emerging photonic platform with great promises for future optical communications, nonlinear optics and microwave photonics. An important integrated photonic building block, active waveguide amplifiers, however, is still missing in the LNOI platform. Here we report an efficient and compact waveguide amplifier based on erbium-doped LNOI waveguides, realized by a sequence of erbium-doped crystal growth, ion slicing and lithography-based waveguide fabrication. Using a compact 5-mm-long waveguide, we demonstrate on-chip net gain of > 5 dB for 1530-nm signal light with a relatively low pump power of 21 mW at 980 nm. The efficient LNOI waveguide amplifiers could become an important fundamental element in future lithium niobate photonic integrated circuits.