Search

The unconditioned reflex (e.g., protective reflex), which is the innate reaction of the organism and usually performed through the spinal cord rather than the brain, can enable organisms to escape harms from environments. In this paper, we propose an online, highly-dynamic motion planning algorithm to endow manipulators the highly-dynamic unconditioned reflexes to humans and/or environments. Our method is based on a chained version of Signed Distance Functions (SDFs), which can be pre-computed and stored. Our proposed algorithm is divided into two stages. In the offline stage, we create 3 groups of local SDFs to store the geometric information of the manipulator and its working environment. In the online stage, the pre-computed local SDFs are chained together according the configuration of the manipulator, to provide global geometric information about the environment. While the point clouds of the dynamic objects serve as query points to look up these local SDFs for quickly generating escape velocity. Then we propose a modified geometric Jacobian matrix and use the Jacobian-pseudo-inverse method to generate real-time reflex behaviors to avoid the static and dynamic obstacles in the environment. The benefits of our method are validated in both static and dynamic scenarios. In the static scenario, our method identifies the path solutions with lower time consumption and shorter trajectory length compared to existing solutions. In the dynamic scenario, our method can reliably pursue the dynamic target point, avoid dynamic obstacles, and react to these obstacles within 1ms, which surpasses the unconditioned reflex reaction time of humans.

The Operating System (OS) kernel is foundational in modern computing, especially with the proliferation of diverse computing devices. However, its development also comes with vulnerabilities that can lead to severe security breaches. Kernel fuzzing, a technique used to uncover these vulnerabilities, poses distinct challenges when compared to userspace fuzzing. These include the complexity of configuring the testing environment and addressing the statefulness inherent to both the kernel and the fuzzing process. Despite the significant interest from the security community, a comprehensive understanding of kernel fuzzing remains lacking, hindering further progress in the field. In this paper, we present the first systematic study dedicated to OS kernel fuzzing. It begins by summarizing the progress of 99 academic studies from top-tier venues between 2017 and 2024. Following this, we introduce a stage-based fuzzing model and a novel fuzzing taxonomy that highlights nine core functionalities unique to kernel fuzzing. These functionalities are examined alongside their corresponding methodological approaches based on qualitative evaluation criteria. Our systematization identifies challenges in meeting functionality requirements and proposes potential technical solutions. Finally, we outline promising and practical future directions to guide forthcoming research in kernel security, supported in part by insights derived from our case study.

Recent studies have investigated various dynamic processes characterizing collective behaviors in real-world systems. However, these dynamics have been studied individually in specific contexts. In this article, we present a holistic analysis framework that bridges the interplays between dynamics across networks of different orders, demonstrating that these processes are not independent but can undergo systematic transformations. Focusing on contagion dynamics, we identify and quantify dynamical and structural factors that explains the interplay between dynamics on higher-order and pairwise networks, uncovering a universal model for system instability governed by these factors. Furthermore, we validate the findings from contagion dynamics to opinion dynamics, highlighting its broader applicability across diverse dynamical processes. Our findings reveal the intrinsic coupling between diverse dynamical processes, providing fresh insights into the distinct role of complex dynamics governed by higher-order interactions.

Bimanual dexterous manipulation remains significant challenges in robotics due to the high DoFs of each hand and their coordination. Existing single-hand manipulation techniques often leverage human demonstrations to guide RL methods but fail to generalize to complex bimanual tasks involving multiple sub-skills. In this paper, we introduce VTAO-BiManip, a novel framework that combines visual-tactile-action pretraining with object understanding to facilitate curriculum RL to enable human-like bimanual manipulation. We improve prior learning by incorporating hand motion data, providing more effective guidance for dual-hand coordination than binary tactile feedback. Our pretraining model predicts future actions as well as object pose and size using masked multimodal inputs, facilitating cross-modal regularization. To address the multi-skill learning challenge, we introduce a two-stage curriculum RL approach to stabilize training. We evaluate our method on a bottle-cap unscrewing task, demonstrating its effectiveness in both simulated and real-world environments. Our approach achieves a success rate that surpasses existing visual-tactile pretraining methods by over 20%.

Streaming graphs are ubiquitous in daily life, such as evolving social networks and dynamic communication systems. Due to the sensitive information contained in the graph, directly sharing the streaming graphs poses significant privacy risks. Differential privacy, offering strict theoretical guarantees, has emerged as a standard approach for private graph data synthesis. However, existing methods predominantly focus on static graph publishing, neglecting the intrinsic relationship between adjacent graphs, thereby resulting in limited performance in streaming data publishing scenarios. To address this gap, we propose PSGraph, the first differentially private streaming graph synthesis framework that integrates temporal dynamics. PSGraph adaptively adjusts the privacy budget allocation mechanism by analyzing the variations in the current graph compared to the previous one for conserving the privacy budget. Moreover, PSGraph aggregates information across various timestamps and adopts crucial post-processing techniques to enhance the synthetic streaming graphs. We conduct extensive experiments on four real-world datasets under five commonly used metrics. The experimental results demonstrate the superiority of PSGraph.

This paper studies a class of distributed bilevel optimization (DBO) problems with a coupled inner-level subproblem. Existing approaches typically rely on hypergradient estimations involving computationally expensive Hessian information. To address this, we propose an equivalent constrained reformulation by treating the inner-level subproblem as an inequality constraint, and introduce an adaptive penalty function to properly penalize both inequality and consensus constraints based on subproblem properties. Moreover, we propose a loopless distributed algorithm, \ALGNAME, that employs multiple-timescale updates to solve each subproblem asymptotically without requiring Hessian information. Theoretically, we establish convergence rates of $\mathcal{O}(\frac{\kappa^4}{(1-\rho)^2 K^{1/3}})$ for nonconvex-strongly-convex cases and $\mathcal{O}(\frac{\kappa^2}{(1-\rho)^2 K^{2/3}})$ for distributed min-max problems. Our analysis shows the clear dependence of convergence performance on bilevel heterogeneity, the adaptive penalty parameter, and network connectivity, with a weaker assumption on heterogeneity requiring only bounded first-order heterogeneity at the optimum. Numerical experiments validate our theoretical findings., Comment: 10 pages, 2 figures

Implicit neural representations and 3D Gaussian splatting (3DGS) have shown great potential for scene reconstruction. Recent studies have expanded their applications in autonomous reconstruction through task assignment methods. However, these methods are mainly limited to single robot, and rapid reconstruction of large-scale scenes remains challenging. Additionally, task-driven planning based on surface uncertainty is prone to being trapped in local optima. To this end, we propose the first 3DGS-based centralized multi-robot autonomous 3D reconstruction framework. To further reduce time cost of task generation and improve reconstruction quality, we integrate online open-vocabulary semantic segmentation with surface uncertainty of 3DGS, focusing view sampling on regions with high instance uncertainty. Finally, we develop a multi-robot collaboration strategy with mode and task assignments improving reconstruction quality while ensuring planning efficiency. Our method demonstrates the highest reconstruction quality among all planning methods and superior planning efficiency compared to existing multi-robot methods. We deploy our method on multiple robots, and results show that it can effectively plan view paths and reconstruct scenes with high quality.

Object detection is a fundamental enabler for many real-time downstream applications such as autonomous driving, augmented reality and supply chain management. However, the algorithmic backbone of neural networks is brittle to imperceptible perturbations in the system inputs, which were generally known as misclassifying attacks. By targeting the real-time processing capability, a new class of latency attacks are reported recently. They exploit new attack surfaces in object detectors by creating a computational bottleneck in the post-processing module, that leads to cascading failure and puts the real-time downstream tasks at risks. In this work, we take an initial attempt to defend against this attack via background-attentive adversarial training that is also cognizant of the underlying hardware capabilities. We first draw system-level connections between latency attack and hardware capacity across heterogeneous GPU devices. Based on the particular adversarial behaviors, we utilize objectness loss as a proxy and build background attention into the adversarial training pipeline, and achieve a reasonable balance between clean and robust accuracy. The extensive experiments demonstrate the defense effectiveness of restoring real-time processing capability from $13$ FPS to $43$ FPS on Jetson Orin NX, with a better trade-off between the clean and robust accuracy.

Condensing large datasets into smaller synthetic counterparts has demonstrated its promise for image classification. However, previous research has overlooked a crucial concern in image recognition: ensuring that models trained on condensed datasets are unbiased towards protected attributes (PA), such as gender and race. Our investigation reveals that dataset distillation (DD) fails to alleviate the unfairness towards minority groups within original datasets. Moreover, this bias typically worsens in the condensed datasets due to their smaller size. To bridge the research gap, we propose a novel fair dataset distillation (FDD) framework, namely FairDD, which can be seamlessly applied to diverse matching-based DD approaches, requiring no modifications to their original architectures. The key innovation of FairDD lies in synchronously matching synthetic datasets to PA-wise groups of original datasets, rather than indiscriminate alignment to the whole distributions in vanilla DDs, dominated by majority groups. This synchronized matching allows synthetic datasets to avoid collapsing into majority groups and bootstrap their balanced generation to all PA groups. Consequently, FairDD could effectively regularize vanilla DDs to favor biased generation toward minority groups while maintaining the accuracy of target attributes. Theoretical analyses and extensive experimental evaluations demonstrate that FairDD significantly improves fairness compared to vanilla DD methods, without sacrificing classification accuracy. Its consistent superiority across diverse DDs, spanning Distribution and Gradient Matching, establishes it as a versatile FDD approach.

Differential privacy (DP) has recently been introduced into episodic reinforcement learning (RL) to formally address user privacy concerns in personalized services. Previous work mainly focuses on two trust models of DP: the central model, where a central agent is responsible for protecting users' sensitive data, and the (stronger) local model, where the protection occurs directly on the user side. However, they either require a trusted central agent or incur a significantly higher privacy cost, making it unsuitable for many scenarios. This work introduces a trust model stronger than the central model but with a lower privacy cost than the local model, leveraging the emerging \emph{shuffle} model of privacy. We present the first generic algorithm for episodic RL under the shuffle model, where a trusted shuffler randomly permutes a batch of users' data before sending it to the central agent. We then instantiate the algorithm using our proposed shuffle Privatizer, relying on a shuffle private binary summation mechanism. Our analysis shows that the algorithm achieves a near-optimal regret bound comparable to that of the centralized model and significantly outperforms the local model in terms of privacy cost.

This paper studies privacy-preserving resilient vector consensus in multi-agent systems against faulty agents, where normal agents can achieve consensus within the convex hull of their initial states while protecting state vectors from being disclosed. Specifically, we consider a modification of an existing algorithm known as Approximate Distributed Robust Convergence Using Centerpoints (ADRC), i.e., Privacy-Preserving ADRC (PP-ADRC). Under PP-ADRC, each normal agent introduces multivariate Gaussian noise to its state during each iteration. We first provide sufficient conditions to ensure that all normal agents' states can achieve mean square convergence under PP-ADRC. Then, we analyze convergence accuracy from two perspectives, i.e., the Mahalanobis distance of the final value from its expectation and the Hausdorff distance based alteration of the convex hull caused by noise when only partial dimensions are added with noise. Then, we employ concentrated geo-privacy to characterize privacy preservation and conduct a thorough comparison with differential privacy. Finally, numerical simulations demonstrate the theoretical results.

Multi-modal fusion is imperative to the implementation of reliable object detection and tracking in complex environments. Exploiting the synergy of heterogeneous modal information endows perception systems the ability to achieve more comprehensive, robust, and accurate performance. As a nucleus concern in wireless-vision collaboration, radar-camera fusion has prompted prospective research directions owing to its extensive applicability, complementarity, and compatibility. Nonetheless, there still lacks a systematic survey specifically focusing on deep fusion of radar and camera for object detection and tracking. To fill this void, we embark on an endeavor to comprehensively review radar-camera fusion in a holistic way. First, we elaborate on the fundamental principles, methodologies, and applications of radar-camera fusion perception. Next, we delve into the key techniques concerning sensor calibration, modal representation, data alignment, and fusion operation. Furthermore, we provide a detailed taxonomy covering the research topics related to object detection and tracking in the context of radar and camera technologies.Finally, we discuss the emerging perspectives in the field of radar-camera fusion perception and highlight the potential areas for future research.

As the implementation of machine learning (ML) systems becomes more widespread, especially with the introduction of larger ML models, we perceive a spring demand for massive data. However, it inevitably causes infringement and misuse problems with the data, such as using unauthorized online artworks or face images to train ML models. To address this problem, many efforts have been made to audit the copyright of the model training dataset. However, existing solutions vary in auditing assumptions and capabilities, making it difficult to compare their strengths and weaknesses. In addition, robustness evaluations usually consider only part of the ML pipeline and hardly reflect the performance of algorithms in real-world ML applications. Thus, it is essential to take a practical deployment perspective on the current dataset copyright auditing tools, examining their effectiveness and limitations. Concretely, we categorize dataset copyright auditing research into two prominent strands: intrusive methods and non-intrusive methods, depending on whether they require modifications to the original dataset. Then, we break down the intrusive methods into different watermark injection options and examine the non-intrusive methods using various fingerprints. To summarize our results, we offer detailed reference tables, highlight key points, and pinpoint unresolved issues in the current literature. By combining the pipeline in ML systems and analyzing previous studies, we highlight several future directions to make auditing tools more suitable for real-world copyright protection requirements., Comment: To appear in the IEEE Symposium on Security and Privacy 2025, San Francisco, CA, USA

Deep learning-based feature matching has shown great superiority for point cloud registration in the absence of pose priors. Although coarse-to-fine matching approaches are prevalent, the coarse matching of existing methods is typically sparse and loose without consideration of geometric consistency, which makes the subsequent fine matching rely on ineffective optimal transport and hypothesis-and-selection methods for consistency. Therefore, these methods are neither efficient nor scalable for real-time applications such as odometry in robotics. To address these issues, we design a consistency-aware spot-guided Transformer (CAST), which incorporates a spot-guided cross-attention module to avoid interfering with irrelevant areas, and a consistency-aware self-attention module to enhance matching capabilities with geometrically consistent correspondences. Furthermore, a lightweight fine matching module for both sparse keypoints and dense features can estimate the transformation accurately. Extensive experiments on both outdoor LiDAR point cloud datasets and indoor RGBD point cloud datasets demonstrate that our method achieves state-of-the-art accuracy, efficiency, and robustness., Comment: Accepted by NeurIPS 2024 as poster

Zero-shot (ZS) 3D anomaly detection is a crucial yet unexplored field that addresses scenarios where target 3D training samples are unavailable due to practical concerns like privacy protection. This paper introduces PointAD, a novel approach that transfers the strong generalization capabilities of CLIP for recognizing 3D anomalies on unseen objects. PointAD provides a unified framework to comprehend 3D anomalies from both points and pixels. In this framework, PointAD renders 3D anomalies into multiple 2D renderings and projects them back into 3D space. To capture the generic anomaly semantics into PointAD, we propose hybrid representation learning that optimizes the learnable text prompts from 3D and 2D through auxiliary point clouds. The collaboration optimization between point and pixel representations jointly facilitates our model to grasp underlying 3D anomaly patterns, contributing to detecting and segmenting anomalies of unseen diverse 3D objects. Through the alignment of 3D and 2D space, our model can directly integrate RGB information, further enhancing the understanding of 3D anomalies in a plug-and-play manner. Extensive experiments show the superiority of PointAD in ZS 3D anomaly detection across diverse unseen objects., Comment: NeurIPS 2024

Large language models (LLMs) have revolutionized natural language processing with their exceptional capabilities. However, deploying LLMs on resource-constrained edge devices presents significant challenges due to computational limitations, memory constraints, and edge hardware heterogeneity. This survey summarizes recent developments in edge LLMs across their lifecycle, examining resource-efficient designs from pre-deployment techniques to runtime optimizations. Additionally, it explores on-device LLM applications in personal, enterprise, and industrial scenarios. By synthesizing advancements and identifying future directions, this survey aims to provide a comprehensive understanding of state-of-the-art methods for deploying LLMs on edge devices, bridging the gap between their immense potential and edge computing limitations.

Recent innovations in autonomous drones have facilitated time-optimal flight in single-drone configurations and enhanced maneuverability in multi-drone systems through the application of optimal control and learning-based methods. However, few studies have achieved time-optimal motion planning for multi-drone systems, particularly during highly agile maneuvers or in dynamic scenarios. This paper presents a decentralized policy network for time-optimal multi-drone flight using multi-agent reinforcement learning. To strike a balance between flight efficiency and collision avoidance, we introduce a soft collision penalty inspired by optimization-based methods. By customizing PPO in a centralized training, decentralized execution (CTDE) fashion, we unlock higher efficiency and stability in training, while ensuring lightweight implementation. Extensive simulations show that, despite slight performance trade-offs compared to single-drone systems, our multi-drone approach maintains near-time-optimal performance with low collision rates. Real-world experiments validate our method, with two quadrotors using the same network as simulation achieving a maximum speed of 13.65 m/s and a maximum body rate of 13.4 rad/s in a 5.5 m * 5.5 m * 2.0 m space across various tracks, relying entirely on onboard computation., Comment: 7 pages, 6 figures

Due to the vast testing space, the increasing demand for effective and efficient testing of deep neural networks (DNNs) has led to the development of various DNN test case prioritization techniques. However, the fact that DNNs can deliver high-confidence predictions for incorrectly predicted examples, known as the over-confidence problem, causes these methods to fail to reveal high-confidence errors. To address this limitation, in this work, we propose FAST, a method that boosts existing prioritization methods through guided FeAture SelecTion. FAST is based on the insight that certain features may introduce noise that affects the model's output confidence, thereby contributing to high-confidence errors. It quantifies the importance of each feature for the model's correct predictions, and then dynamically prunes the information from the noisy features during inference to derive a new probability vector for the uncertainty estimation. With the help of FAST, the high-confidence errors and correctly classified examples become more distinguishable, resulting in higher APFD (Average Percentage of Fault Detection) values for test prioritization, and higher generalization ability for model enhancement. We conduct extensive experiments to evaluate FAST across a diverse set of model structures on multiple benchmark datasets to validate the effectiveness, efficiency, and scalability of FAST compared to the state-of-the-art prioritization techniques.

3D human reconstruction from RGB images achieves decent results in good weather conditions but degrades dramatically in rough weather. Complementarily, mmWave radars have been employed to reconstruct 3D human joints and meshes in rough weather. However, combining RGB and mmWave signals for weather-robust 3D human reconstruction is still an open challenge, given the sparse nature of mmWave and the vulnerability of RGB images. The limited research about the impact of missing points and sparsity features of mmWave data on reconstruction performance, as well as the lack of available datasets for paired mmWave-RGB data, further complicates the process of fusing the two modalities. To fill these gaps, we build up an automatic 3D body annotation system with multiple sensors to collect a large-scale mmWave dataset. The dataset consists of synchronized and calibrated mmWave radar point clouds and RGB(D) images under different weather conditions and skeleton/mesh annotations for humans in these scenes. With this dataset, we conduct a comprehensive analysis about the limitations of single-modality reconstruction and the impact of missing points and sparsity on the reconstruction performance. Based on the guidance of this analysis, we design ImmFusion, the first mmWave-RGB fusion solution to robustly reconstruct 3D human bodies in various weather conditions. Specifically, our ImmFusion consists of image and point backbones for token feature extraction and a Transformer module for token fusion. The image and point backbones refine global and local features from original data, and the Fusion Transformer Module aims for effective information fusion of two modalities by dynamically selecting informative tokens. Extensive experiments demonstrate that ImmFusion can efficiently utilize the information of two modalities to achieve robust 3D human body reconstruction in various weather environments., Comment: TCSVT 2024, Project Page: https://chen3110.github.io/mmbody/index.html

The millimeter-wave (mmWave) radar has been exploited for gesture recognition. However, existing mmWave-based gesture recognition methods cannot identify different users, which is important for ubiquitous gesture interaction in many applications. In this paper, we propose GesturePrint, which is the first to achieve gesture recognition and gesture-based user identification using a commodity mmWave radar sensor. GesturePrint features an effective pipeline that enables the gesture recognition system to identify users at a minor additional cost. By introducing an efficient signal preprocessing stage and a network architecture GesIDNet, which employs an attention-based multilevel feature fusion mechanism, GesturePrint effectively extracts unique gesture features for gesture recognition and personalized motion pattern features for user identification. We implement GesturePrint and collect data from 17 participants performing 15 gestures in a meeting room and an office, respectively. GesturePrint achieves a gesture recognition accuracy (GRA) of 98.87% with a user identification accuracy (UIA) of 99.78% in the meeting room, and 98.22% GRA with 99.26% UIA in the office. Extensive experiments on three public datasets and a new gesture dataset show GesturePrint's superior performance in enabling effective user identification for gesture recognition systems., Comment: Accepted to the 44th IEEE International Conference on Distributed Computing Systems (ICDCS 2024)

Autonomous Vehicles (AVs) rely on sophisticated Autonomous Driving Systems (ADSs) to provide passengers a satisfying and safe journey. The individual preferences of riders plays a crucial role in shaping the perception of safety and comfort while they are in the car. Existing ADSs, however, lack mechanisms to systematically capture and integrate rider preferences into their planning modules. To bridge this gap, we propose $\mu$Drive, an event-based Domain-Specific Language (DSL) designed for specifying autonomous vehicle behaviour. $\mu$Drive enables users to express their preferences through rules triggered by contextual events, such as encountering obstacles or navigating complex traffic situations. These rules dynamically adjust the parameter settings of the ADS planning module, facilitating seamless integration of rider preferences into the driving plan. In our evaluation, we demonstrate the feasibility and efficacy of $\mu$Drive by integrating it with the Apollo ADS framework. Our findings show that users can effectively influence Apollo's planning through $\mu$Drive, assisting ADS in achieving improved compliance with traffic regulations. The response time for $\mu$Drive commands remains consistently at the second or millisecond level. This suggests that $\mu$Drive may help pave the way to more personalizsed and user-centric AV experiences.

Integrated Sensing and Communications (ISAC) is one of the core technologies of 6G, which combines sensing and communication functions into a single system. However, limited computing and storage resources make it impractical to combine multiple sensing models into a single device, constraining the system's function and performance. Therefore, this article proposes enhancing ISAC with the mixture of experts (MoE) architecture. Rigorously, we first investigate ISAC and MoE, including their concepts, advantages, and applications. Then, we explore how MoE can enhance ISAC from the perspectives of signal processing and network optimization. Building on this, we propose an MoE based ISAC framework, which uses a gating network to selectively activate multiple experts in handling sensing tasks under given communication conditions, thereby improving the overall performance. The case study demonstrates that the proposed framework can effectively increase the accuracy and robustness in detecting targets by using wireless communication signal, providing strong support for the practical deployment and applications of the ISAC system.

The performance of single image super-resolution depends heavily on how to generate and complement high-frequency details to low-resolution images. Recently, diffusion-based models exhibit great potential in generating high-quality images for super-resolution tasks. However, existing models encounter difficulties in directly predicting high-frequency information of wide bandwidth by solely utilizing the high-resolution ground truth as the target for all sampling timesteps. To tackle this problem and achieve higher-quality super-resolution, we propose a novel Frequency Domain-guided multiscale Diffusion model (FDDiff), which decomposes the high-frequency information complementing process into finer-grained steps. In particular, a wavelet packet-based frequency complement chain is developed to provide multiscale intermediate targets with increasing bandwidth for reverse diffusion process. Then FDDiff guides reverse diffusion process to progressively complement the missing high-frequency details over timesteps. Moreover, we design a multiscale frequency refinement network to predict the required high-frequency components at multiple scales within one unified network. Comprehensive evaluations on popular benchmarks are conducted, and demonstrate that FDDiff outperforms prior generative methods with higher-fidelity super-resolution results.

Neural radiance field (NeRF) has achieved impressive results in high-quality 3D scene reconstruction. However, NeRF heavily relies on precise camera poses. While recent works like BARF have introduced camera pose optimization within NeRF, their applicability is limited to simple trajectory scenes. Existing methods struggle while tackling complex trajectories involving large rotations. To address this limitation, we propose CT-NeRF, an incremental reconstruction optimization pipeline using only RGB images without pose and depth input. In this pipeline, we first propose a local-global bundle adjustment under a pose graph connecting neighboring frames to enforce the consistency between poses to escape the local minima caused by only pose consistency with the scene structure. Further, we instantiate the consistency between poses as a reprojected geometric image distance constraint resulting from pixel-level correspondences between input image pairs. Through the incremental reconstruction, CT-NeRF enables the recovery of both camera poses and scene structure and is capable of handling scenes with complex trajectories. We evaluate the performance of CT-NeRF on two real-world datasets, NeRFBuster and Free-Dataset, which feature complex trajectories. Results show CT-NeRF outperforms existing methods in novel view synthesis and pose estimation accuracy.

The sim-to-real gap poses a significant challenge in RL-based multi-agent exploration due to scene quantization and action discretization. Existing platforms suffer from the inefficiency in sampling and the lack of diversity in Multi-Agent Reinforcement Learning (MARL) algorithms across different scenarios, restraining their widespread applications. To fill these gaps, we propose MAexp, a generic platform for multi-agent exploration that integrates a broad range of state-of-the-art MARL algorithms and representative scenarios. Moreover, we employ point clouds to represent our exploration scenarios, leading to high-fidelity environment mapping and a sampling speed approximately 40 times faster than existing platforms. Furthermore, equipped with an attention-based Multi-Agent Target Generator and a Single-Agent Motion Planner, MAexp can work with arbitrary numbers of agents and accommodate various types of robots. Extensive experiments are conducted to establish the first benchmark featuring several high-performance MARL algorithms across typical scenarios for robots with continuous actions, which highlights the distinct strengths of each algorithm in different scenarios.

Implicit neural representations have demonstrated significant promise for 3D scene reconstruction. Recent works have extended their applications to autonomous implicit reconstruction through the Next Best View (NBV) based method. However, the NBV method cannot guarantee complete scene coverage and often necessitates extensive viewpoint sampling, particularly in complex scenes. In the paper, we propose to 1) incorporate frontier-based exploration tasks for global coverage with implicit surface uncertainty-based reconstruction tasks to achieve high-quality reconstruction. and 2) introduce a method to achieve implicit surface uncertainty using color uncertainty, which reduces the time needed for view selection. Further with these two tasks, we propose an adaptive strategy for switching modes in view path planning, to reduce time and maintain superior reconstruction quality. Our method exhibits the highest reconstruction quality among all planning methods and superior planning efficiency in methods involving reconstruction tasks. We deploy our method on a UAV and the results show that our method can plan multi-task views and reconstruct a scene with high quality., Comment: 7 pages

Human activity recognition (HAR) will be an essential function of various emerging applications. However, HAR typically encounters challenges related to modality limitations and label scarcity, leading to an application gap between current solutions and real-world requirements. In this work, we propose MESEN, a multimodal-empowered unimodal sensing framework, to utilize unlabeled multimodal data available during the HAR model design phase for unimodal HAR enhancement during the deployment phase. From a study on the impact of supervised multimodal fusion on unimodal feature extraction, MESEN is designed to feature a multi-task mechanism during the multimodal-aided pre-training stage. With the proposed mechanism integrating cross-modal feature contrastive learning and multimodal pseudo-classification aligning, MESEN exploits unlabeled multimodal data to extract effective unimodal features for each modality. Subsequently, MESEN can adapt to downstream unimodal HAR with only a few labeled samples. Extensive experiments on eight public multimodal datasets demonstrate that MESEN achieves significant performance improvements over state-of-the-art baselines in enhancing unimodal HAR by exploiting multimodal data., Comment: Accepted to the 21th ACM Conference on Embedded Networked Sensor Systems (SenSys 2023)

Tracking by natural language specification (TNL) aims to consistently localize a target in a video sequence given a linguistic description in the initial frame. Existing methodologies perform language-based and template-based matching for target reasoning separately and merge the matching results from two sources, which suffer from tracking drift when language and visual templates miss-align with the dynamic target state and ambiguity in the later merging stage. To tackle the issues, we propose a joint multi-modal tracking framework with 1) a prompt modulation module to leverage the complementarity between temporal visual templates and language expressions, enabling precise and context-aware appearance and linguistic cues, and 2) a unified target decoding module to integrate the multi-modal reference cues and executes the integrated queries on the search image to predict the target location in an end-to-end manner directly. This design ensures spatio-temporal consistency by leveraging historical visual information and introduces an integrated solution, generating predictions in a single step. Extensive experiments conducted on TNL2K, OTB-Lang, LaSOT, and RefCOCOg validate the efficacy of our proposed approach. The results demonstrate competitive performance against state-of-the-art methods for both tracking and grounding., Comment: Accepted by CVPR2024

Trajectory prediction is an essential component in autonomous driving, particularly for collision avoidance systems. Considering the inherent uncertainty of the task, numerous studies have utilized generative models to produce multiple plausible future trajectories for each agent. However, most of them suffer from restricted representation ability or unstable training issues. To overcome these limitations, we propose utilizing the diffusion model to generate the distribution of future trajectories. Two cruxes are to be settled to realize such an idea. First, the diversity of intention is intertwined with the uncertain surroundings, making the true distribution hard to parameterize. Second, the diffusion process is time-consuming during the inference phase, rendering it unrealistic to implement in a real-time driving system. We propose an Intention-aware denoising Diffusion Model (IDM), which tackles the above two problems. We decouple the original uncertainty into intention uncertainty and action uncertainty and model them with two dependent diffusion processes. To decrease the inference time, we reduce the variable dimensions in the intention-aware diffusion process and restrict the initial distribution of the action-aware diffusion process, which leads to fewer diffusion steps. To validate our approach, we conduct experiments on the Stanford Drone Dataset (SDD) and ETH/UCY dataset. Our methods achieve state-of-the-art results, with an FDE of 13.83 pixels on the SDD dataset and 0.36 meters on the ETH/UCY dataset. Compared with the original diffusion model, IDM reduces inference time by two-thirds. Interestingly, our experiments further reveal that introducing intention information is beneficial in modeling the diffusion process of fewer steps., Comment: 14 pages, 9 figures

Recently, promptable segmentation models, such as the Segment Anything Model (SAM), have demonstrated robust zero-shot generalization capabilities on static images. These promptable models exhibit denoising abilities for imprecise prompt inputs, such as imprecise bounding boxes. In this paper, we explore the potential of applying SAM to track and segment objects in videos where we recognize the tracking task as a prompt denoising task. Specifically, we iteratively propagate the bounding box of each object's mask in the preceding frame as the prompt for the next frame. Furthermore, to enhance SAM's denoising capability against position and size variations, we propose a multi-prompt strategy where we provide multiple jittered and scaled box prompts for each object and preserve the mask prediction with the highest semantic similarity to the template mask. We also introduce a point-based refinement stage to handle occlusions and reduce cumulative errors. Without involving tracking modules, our approach demonstrates comparable performance in video object/instance segmentation tasks on three datasets: DAVIS2017, YouTubeVOS2018, and UVO, serving as a concise baseline and endowing SAM-based downstream applications with tracking capabilities.

Given 2D point correspondences between an image pair, inferring the camera motion is a fundamental issue in the computer vision community. The existing works generally set out from the epipolar constraint and estimate the essential matrix, which is not optimal in the maximum likelihood (ML) sense. In this paper, we dive into the original measurement model with respect to the rotation matrix and normalized translation vector and formulate the ML problem. We then propose a two-step algorithm to solve it: In the first step, we estimate the variance of measurement noises and devise a consistent estimator based on bias elimination; In the second step, we execute a one-step Gauss-Newton iteration on manifold to refine the consistent estimate. We prove that the proposed estimate owns the same asymptotic statistical properties as the ML estimate: The first is consistency, i.e., the estimate converges to the ground truth as the point number increases; The second is asymptotic efficiency, i.e., the mean squared error of the estimate converges to the theoretical lower bound -- Cramer-Rao bound. In addition, we show that our algorithm has linear time complexity. These appealing characteristics endow our estimator with a great advantage in the case of dense point correspondences. Experiments on both synthetic data and real images demonstrate that when the point number reaches the order of hundreds, our estimator outperforms the state-of-the-art ones in terms of estimation accuracy and CPU time.

The flying speed of autonomous quadrotors has increased significantly over the past 5 years, particularly in the field of autonomous drone racing. However, most research primarily focuses on the aggressive flight of a single quadrotor, simplifying the racing gate traversal problem to a waypoint passing problem that neglects the orientations of the racing gates. In this paper, we propose a systematic method called Pairwise Model Predictive Control (PMPC) that can guide two quadrotors online to navigate racing gates with minimal time and without collisions. The flight task is initially simplified as a point-mass model waypoint passing problem to provide analytical time optimal reference through an efficient two-step velocity search method. Subsequently, we utilize the spatial configuration of the racing track to compute the optimal heading at each gate, maximizing the visibility of subsequent gates for the quadrotors. To address varying gate orientations, we introduce a novel Magnetic Induction Line-based spatial curve to guide the quadrotors through racing gates of different orientations. Furthermore, we formulate a nonlinear optimization problem that uses the point-mass trajectory as initial values and references to enhance solving efficiency, enabling the method to run onboard at a frequency of 200 Hz. The feasibility of the proposed method is validated through both simulation and real-world experiments. In real-world tests, the two quadrotors achieved a top speed of 6.1 m/s on a 7-waypoint racing track within a compact flying arena of 5 m * 4 m * 2 m.

Over the past decade, there has been a remarkable surge in utilizing quadrotors for various purposes due to their simple structure and aggressive maneuverability, such as search and rescue, delivery and autonomous drone racing, etc. One of the key challenges preventing quadrotors from being widely used in these scenarios is online waypoint-constrained time-optimal trajectory generation and control technique. This letter proposes an imitation learning-based online solution to efficiently navigate the quadrotor through multiple waypoints with time-optimal performance. The neural networks (WN&CNets) are trained to learn the control law from the dataset generated by the time-consuming CPC algorithm and then deployed to generate the optimal control commands online to guide the quadrotors. To address the challenge of limited training data and the hover maneuver at the final waypoint, we propose a transition phase strategy that utilizes MINCO trajectories to help the quadrotor 'jump over' the stop-and-go maneuver when switching waypoints. Our method is demonstrated in both simulation and real-world experiments, achieving a maximum speed of 5.6m/s while navigating through 7 waypoints in a confined space of 5.5m*5.5m*2.0m. The results show that with a slight loss in optimality, the WN&CNets significantly reduce the processing time and enable online optimal control for multiple-waypoint constrained flight tasks.

We report the test results of several independent foreground-cleaning pipelines used in the Ali CMB Polarization Telescope experiment (AliCPT-1), a high-altitude CMB imager in the Northern hemisphere with thousands of detectors dedicated to the search for a primordial CMB polarization $B$-mode signature. Based on simulated data from 4 detector modules and a single season of observation, which we refer to as Data Challenge 1 (DC1), we employ different and independent pipelines to examine the robustness and effectiveness of the estimates on foreground parameters and the primordial $B$-mode detection. The foreground-cleaning strategies used in the pipelines include the parametric method of template fitting (TF) and the non-parametric methods of the constrained internal linear combination (cILC), the analytical blind separation (ABS), and the generalized least squares (GLS). We examine the impact of possible foreground residuals on the estimate of the CMB tensor-to-scalar ratio ($r$) for each pipeline by changing the contamination components in the simulated maps and varying the foreground models and sky patches for various tests. According to the DC1 data with the simulation input value $r_{\rm true}=0.023$, the foreground residual contamination levels in the TF/ABS/cILC/GLS pipelines are well within the corresponding statistical errors at the $2\sigma$ level. Furthermore, by utilizing the tension estimator, which helps identify significant residual foreground contamination in the detection of the primordial $B$-mode signal by quantifying the discrepancy between various $r$ measurements, we conclude that the presence of small foreground residuals does not lead to any significant inconsistency in the estimation of $r$., Comment: 38 pages, 22 figures; accepted for publication in ApJS

Inverse reinforcement learning (IRL) usually assumes the model of the reward function is pre-specified and estimates the parameter only. However, how to determine a proper reward model is nontrivial. A simplistic model is less likely to contain the real reward function, while a model with high complexity leads to substantial computation cost and risks overfitting. This paper addresses this trade-off in IRL model selection by introducing the structural risk minimization (SRM) method from statistical learning. SRM selects an optimal reward function class from a hypothesis set minimizing both estimation error and model complexity. To formulate an SRM scheme for IRL, we estimate policy gradient by demonstration serving as empirical risk and establish the upper bound of Rademacher complexity of hypothesis classes as model penalty. The learning guarantee is further presented. In particular, we provide explicit SRM for the common linear weighted sum setting in IRL. Simulations demonstrate the performance and efficiency of our scheme.

Our work aims to reconstruct a 3D object that is held and rotated by a hand in front of a static RGB camera. Previous methods that use implicit neural representations to recover the geometry of a generic hand-held object from multi-view images achieved compelling results in the visible part of the object. However, these methods falter in accurately capturing the shape within the hand-object contact region due to occlusion. In this paper, we propose a novel method that deals with surface reconstruction under occlusion by incorporating priors of 2D occlusion elucidation and physical contact constraints. For the former, we introduce an object amodal completion network to infer the 2D complete mask of objects under occlusion. To ensure the accuracy and view consistency of the predicted 2D amodal masks, we devise a joint optimization method for both amodal mask refinement and 3D reconstruction. For the latter, we impose penetration and attraction constraints on the local geometry in contact regions. We evaluate our approach on HO3D and HOD datasets and demonstrate that it outperforms the state-of-the-art methods in terms of reconstruction surface quality, with an improvement of $52\%$ on HO3D and $20\%$ on HOD. Project webpage: https://east-j.github.io/ihor., Comment: Accepted by AAAI2024

Anomaly detection in multivariate time series (MTS) has been widely studied in one-class classification (OCC) setting. The training samples in OCC are assumed to be normal, which is difficult to guarantee in practical situations. Such a case may degrade the performance of OCC-based anomaly detection methods which fit the training distribution as the normal distribution. In this paper, we propose MTGFlow, an unsupervised anomaly detection approach for MTS anomaly detection via dynamic Graph and entity-aware normalizing Flow. MTGFlow first estimates the density of the entire training samples and then identifies anomalous instances based on the density of the test samples within the fitted distribution. This relies on a widely accepted assumption that anomalous instances exhibit more sparse densities than normal ones, with no reliance on the clean training dataset. However, it is intractable to directly estimate the density due to complex dependencies among entities and their diverse inherent characteristics. To mitigate this, we utilize the graph structure learning model to learn interdependent and evolving relations among entities, which effectively captures complex and accurate distribution patterns of MTS. In addition, our approach incorporates the unique characteristics of individual entities by employing an entity-aware normalizing flow. This enables us to represent each entity as a parameterized normal distribution. Furthermore, considering that some entities present similar characteristics, we propose a cluster strategy that capitalizes on the commonalities of entities with similar characteristics, resulting in more precise and detailed density estimation. We refer to this cluster-aware extension as MTGFlow_cluster. Extensive experiments are conducted on six widely used benchmark datasets, in which MTGFlow and MTGFlow cluster demonstrate their superior detection performance., Comment: arXiv admin note: substantial text overlap with arXiv:2208.02108

Semantic communication has emerged as a promising approach for improving efficient transmission in the next generation of wireless networks. Inspired by the success of semantic communication in different areas, we aim to provide a new semantic communication scheme from the semantic level. In this paper, we propose a novel DL-based semantic communication system for video transmission, which compacts semantic-related information to improve transmission efficiency. In particular, we utilize the Bi-optical flow to estimate residual information of inter-frame details. We also propose a feature choice module and a feature fusion module to drop semantically redundant features while paying more attention to the important semantic-related content. We employ a frame prediction module to reconstruct semantic features of the prediction frame from the received signal at the receiver. To enhance the system's robustness, we propose a noise attention module that assigns different importance weights to the extracted features. Simulation results indicate that our proposed method outperforms existing approaches in terms of transmission efficiency, achieving about 33.3\% reduction in the number of transmitted symbols while improving the peak signal-to-noise ratio (PSNR) performance by an average of 0.56dB.

Transformer-based large language models (LLMs) have demonstrated impressive capabilities in a variety of natural language processing (NLP) tasks. Nonetheless, it is challenging to deploy and fine-tune LLMs on mobile edge devices with limited computing, memory, and energy budgets. In this paper, we propose Confidant, a multi-backend collaborative training framework for customizing state-of-the-art LLMs on commodity mobile devices like smartphones. Confidant partitions an LLM into several sub-models so that each fits into a mobile device's memory. A pipeline parallel training mechanism is further developed to ensure fast and efficient distributed training. In addition, we propose a novel backend scheduler to allocate different attention heads to heterogeneous compute hardware, including mobile CPU and GPUs, to maximize the compute resource utilization on each edge device. Our preliminary experimental results show that Confidant achieves at most 45.3% memory reduction and 8.03x inference speedup in practical settings., Comment: 6 pages, 7 figures; Submitted to HotMobile 2024

It is usually infeasible to fit and train an entire large deep neural network (DNN) model using a single edge device due to the limited resources. To facilitate intelligent applications across edge devices, researchers have proposed partitioning a large model into several sub-models, and deploying each of them to a different edge device to collaboratively train a DNN model. However, the communication overhead caused by the large amount of data transmitted from one device to another during training, as well as the sub-optimal partition point due to the inaccurate latency prediction of computation at each edge device can significantly slow down training. In this paper, we propose AccEPT, an acceleration scheme for accelerating the edge collaborative pipeline-parallel training. In particular, we propose a light-weight adaptive latency predictor to accurately estimate the computation latency of each layer at different devices, which also adapts to unseen devices through continuous learning. Therefore, the proposed latency predictor leads to better model partitioning which balances the computation loads across participating devices. Moreover, we propose a bit-level computation-efficient data compression scheme to compress the data to be transmitted between devices during training. Our numerical results demonstrate that our proposed acceleration approach is able to significantly speed up edge pipeline parallel training up to 3 times faster in the considered experimental settings.

Zero-shot anomaly detection (ZSAD) requires detection models trained using auxiliary data to detect anomalies without any training sample in a target dataset. It is a crucial task when training data is not accessible due to various concerns, eg, data privacy, yet it is challenging since the models need to generalize to anomalies across different domains where the appearance of foreground objects, abnormal regions, and background features, such as defects/tumors on different products/organs, can vary significantly. Recently large pre-trained vision-language models (VLMs), such as CLIP, have demonstrated strong zero-shot recognition ability in various vision tasks, including anomaly detection. However, their ZSAD performance is weak since the VLMs focus more on modeling the class semantics of the foreground objects rather than the abnormality/normality in the images. In this paper we introduce a novel approach, namely AnomalyCLIP, to adapt CLIP for accurate ZSAD across different domains. The key insight of AnomalyCLIP is to learn object-agnostic text prompts that capture generic normality and abnormality in an image regardless of its foreground objects. This allows our model to focus on the abnormal image regions rather than the object semantics, enabling generalized normality and abnormality recognition on diverse types of objects. Large-scale experiments on 17 real-world anomaly detection datasets show that AnomalyCLIP achieves superior zero-shot performance of detecting and segmenting anomalies in datasets of highly diverse class semantics from various defect inspection and medical imaging domains. Code will be made available at https://github.com/zqhang/AnomalyCLIP., Comment: ICLR 2024

Precise and long-term stable localization is essential in parking lots for tasks like autonomous driving or autonomous valet parking, \textit{etc}. Existing methods rely on a fixed and memory-inefficient map, which lacks robust data association approaches. And it is not suitable for precise localization or long-term map maintenance. In this paper, we propose a novel mapping, localization, and map update system based on ground semantic features, utilizing low-cost cameras. We present a precise and lightweight parameterization method to establish improved data association and achieve accurate localization at centimeter-level. Furthermore, we propose a novel map update approach by implementing high-quality data association for parameterized semantic features, allowing continuous map update and refinement during re-localization, while maintaining centimeter-level accuracy. We validate the performance of the proposed method in real-world experiments and compare it against state-of-the-art algorithms. The proposed method achieves an average accuracy improvement of 5cm during the registration process. The generated maps consume only a compact size of 450 KB/km and remain adaptable to evolving environments through continuous update., Comment: 6 pages, 8 figures

Robust and accurate pose estimation in unknown environments is an essential part of robotic applications. We focus on LiDAR-based point-to-point ICP combined with effective semantic information. This paper proposes a novel semantic information-assisted ICP method named SAGE-ICP, which leverages semantics in odometry. The semantic information for the whole scan is timely and efficiently extracted by a 3D convolution network, and these point-wise labels are deeply involved in every part of the registration, including semantic voxel downsampling, data association, adaptive local map, and dynamic vehicle removal. Unlike previous semantic-aided approaches, the proposed method can improve localization accuracy in large-scale scenes even if the semantic information has certain errors. Experimental evaluations on KITTI and KITTI-360 show that our method outperforms the baseline methods, and improves accuracy while maintaining real-time performance, i.e., runs faster than the sensor frame rate., Comment: 6+1 pages, 4 figures

Sparse keypoint matching based on distinct 3D feature representations can improve the efficiency and robustness of point cloud registration. Existing learning-based 3D descriptors and keypoint detectors are either independent or loosely coupled, so they cannot fully adapt to each other. In this work, we propose a tightly coupled keypoint detector and descriptor (TCKDD) based on a multi-task fully convolutional network with a probabilistic detection loss. In particular, this self-supervised detection loss fully adapts the keypoint detector to any jointly learned descriptors and benefits the self-supervised learning of descriptors. Extensive experiments on both indoor and outdoor datasets show that our TCKDD achieves state-of-the-art performance in point cloud registration. Furthermore, we design a keypoint detector and descriptors-assisted LiDAR odometry and mapping framework (KDD-LOAM), whose real-time odometry relies on keypoint descriptor matching-based RANSAC. The sparse keypoints are further used for efficient scan-to-map registration and mapping. Experiments on KITTI dataset demonstrate that KDD-LOAM significantly surpasses LOAM and shows competitive performance in odometry.