176 accepted papers
Terrestrial-aerial bimodal vehicles, which integrate the high mobility of aerial robots with the long endurance of ground robots, offer significant potential for autonomous exploration. Given the inherent energy and time constraints in practical exploration tasks, we present a hierarchical framework…
In the context of the Classification and Regression Trees (CART) algorithm, the efficient splitting of categorical features using standard criteria like GINI and Entropy is well-established. However, using the Mean Absolute Error (MAE) criterion for categorical features has traditionally relied on v
The sharp, intricate contours of lunar regolith particles hold critical clues to the Moon
Convex polytopes have compact representations and exhibit convexity, which makes them suitable for abstracting obstacle-free spaces from various environments. Existing generation methods struggle with balancing high-quality output and efficiency. Moreover, another crucial requirement for convex poly…
Reconstructing photorealistic and animatable 4D head avatars from a single portrait image remains a fundamental challenge in computer vision. While diffusion models have enabled remarkable progress in image and video generation for avatar reconstruction, existing methods primarily rely on 2D priors
Partial Label Learning (PLL) aims to train multi-class classifiers from examples where each instance is associated with a set of candidate labels, among which the ground-truth label is assumed to be included. While most existing studies assume that partial labels are both instance-independent and re
Due to the limited online computational resources and the inherent probability of hardware and software failures of real-world robots, large-scale formation planning faces two common challenges: computational intractability and agent failures. Based on the theory of sparse graphs and the maximum cli…
Optimization has been widely used to generate smooth trajectories for motion planning. However, existing trajectory optimization methods show weakness when dealing with large-scale long trajectories. Recent advances in parallel computing have accelerated optimization in some fields, but how to effic…
This paper introduces UniMERNet, a high-accuracy, computation-efficient algorithm for Mathematical Expression Recognition (MER) across diverse real-world scenarios. To facilitate UniMERNet's training, we constructed UniMER-1M, a million-scale dataset whose unprecedented diversity endows the model wi
Differential drive robots are widely used in various scenarios thanks to their straightforward principle, from household service robots to disaster response field robots. The nonholonomic dynamics and possible lateral slip of these robots lead to difficulty in getting feasible and high-quality traje…
Large components, such as wind turbine blades, often exhibit significant curvature variations, presenting substantial challenges for climbing robots. To improve the adaptability and mobility of hexapod climbing robots on such surfaces, we propose a Curvature-Adaptive Hexapod robot system. The mechan
The emergence of Satellite-Terrestrial Integrated Networks (STIN) has significantly expanded terrestrial network coverage but introduced new security threats. Current Intrusion Detection Systems (IDSs) for STIN mostly consider the distributed nature of satellites, overlooking the computational limit…
Obtaining high-precision aerodynamics in the automotive industry relies on large-scale simulations with computational fluid dynamics, which are generally time-consuming and computationally expensive. Recent advances in operator learning for partial differential equations offer promising improvements…
Traversing across adjacent planes is an important ability for legged climbing robots. While many robots can achieve autonomous ground-to-wall transitions, most are limited to scenarios where the angle between the planes has a certain value. In some cases, however, the robot needs to traverse planes
Miniature amphibious robots are capable of performing various tasks in complex terrestrial and aquatic environments due to their superior adaptability. However, the mobility of existing miniature amphibious robots in such environments is limited by their complex locomotion systems and single mode of
Generating animatable human avatars from a single image is essential for various digital human modeling applications. Existing 3D reconstruction methods often struggle to capture fine details in animatable models, while generative approaches for controllable animation, though avoiding explicit 3D mo…
Terrestrial-aerial bimodal vehicles, which integrate the high mobility of aerial robots with the long endurance of ground robots, offer significant potential for autonomous exploration. Given the inherent energy and time constraints in practical exploration tasks, we present a hierarchical framework
We introduce Bokehdiff, a novel lens blur rendering method that achieves physically accurate and visually appealing outcomes, with the help of generative diffusion prior. Previous methods are bounded by the accuracy of depth estimation, generating artifacts in depth discontinuities. Our method emplo…
Self-supervised learning (SSL) is a technique used to learn feature representations from unlabeled data. However, existing SSL frameworks either rely too heavily on domain knowledge due to their design based on feature invariance, leading to a lack of domain transferability, or they are based on aut…
We present the design and implementation of a large-scale tail-sitter aircraft with vertical takeoff and landing (VTOL) capabilities. The aircraft was designed with an H-shaped configuration and incorporated canards to enhance longitudinal stability. The structural design was optimized to balance me
Diffusion models have shown exceptional performance in visual generation tasks. Recently, these models have shifted from traditional U-Shaped CNN-Attention hybrid structures to fully transformer-based isotropic architectures. While these transformers exhibit strong scalability and performance, their…
In this paper, we present a navigation framework for wheeled robots operating in uneven environments. Considering the sparsity of the moving surface along the Z-axis, we introduce a novel map representation, namely Surfelgrid. Surfelgrid uses surfels to represent geometric features of the local area
Terrestrial-aerial bimodal vehicles (TABVs) can fly to avoid obstacles and move safely on the ground to save energy, offering enhanced adaptability and flexibility in various challenging environments. However, a robust localization approach becomes a bottleneck to stably applying the TABVs in real-w
With the increasing integration of robots into human life, their role in architectural spaces where people spend most of their time has become more prominent. While motion capabilities and accurate localization for automated robots have rapidly developed, the challenge remains to generate efficient,
Visual vibrometry has emerged as a powerful technique for remote acquisition of audio and the physical properties of materials. To capture high-frequency vibrations, frame-based approaches often require a high-speed video camera and bright lighting to compensate for the short exposure time. In this…
Animation has gained significant interest in the recent film and TV industry. Despite the success of advanced video generation models like Sora, Kling, and CogVideoX in generating natural videos, they lack the same effectiveness in handling animation videos. Evaluating animation video generation is
Coordinate initialization is the first step in accomplishing collaborative tasks within robot swarms, determining the quality of tasks. However, fast and robust coordinate initialization in vision-based drone swarms remains elusive. To this end, our letter proposes a complete system for initial rela
CoNi-MPC [1] provides an efficient framework for UAV control in air-ground cooperative tasks by relying exclusively on relative states, eliminating the need for global state estimation. However, its lack of environmental information poses significant challenges for obstacle avoidance. To address thi
In open-environment applications, data are often collected from heterogeneous modalities with distinct encodings, resulting in feature space heterogeneity. This heterogeneity inherently induces label shift, making cross-modal knowledge transfer particularly challenging when the source and target dat…
Label shift, which investigates the adaptation of label distributions between the fixed source and target domains, has attracted significant research interests and broad applications in offline settings. In real-world scenarios, however, data often arrives as a continuous stream. Addressing label sh…
While language models (LMs) paired with residual vector quantization (RVQ) tokenizers have shown promise in text-to-audio (T2A) generation, they still lag behind diffusion-based models by a non-trivial margin. We identify a critical dilemma underpinning this gap: incorporating more RVQ layers improv
We consider a large-scale incentive allocation problem where the entire trade-off curve between budget and profit has to be maintained approximately at all time. The application originally comes from assigning coupons to users of the ride-sharing apps, where each user can have a limit on the number
In the context of autonomous driving, monocular 3D detection is regarded as a fundamental and essential task due to its convenience, speed, and low cost. However, the lack of depth information in monocular images presents significant challenges for predicting object 3D information. Although existing
Image-text interleaved data, consisting of multiple images and texts arranged in a natural document format, aligns with the presentation paradigm of internet data and closely resembles human reading habits. Recent studies have shown that such data aids multimodal in-context learning and maintains th…
Document content extraction is a critical task in computer vision, underpinning the data needs of large language models (LLMs) and retrieval-augmented generation (RAG) systems. Despite recent progress, current document parsing methods have not been fairly and comprehensively evaluated due to the nar…
In many real applications, the data attributes are incremental and the samples are stored with accumulated feature spaces gradually. Although there are several elegant approaches to tackling this problem, the theoretical analysis is still limited. There exist at least two challenges and fundamental
Obtaining planetary images with good visual quality is not an easy task since they are usually degenerated by atmospheric turbulence during the imaging procedure. Existing atmospheric turbulence mitigation methods designed for conventional images cannot be applied to planetary images, since the obje…
Shadow is a phenomenon that degenerates image quality and decreases the performance of downstream vision algorithms. Despite the fact that current image shadow removal methods have achieved promising progress, many of them require an externally obtained shadow mask as a necessary part of the input d…
Terrain analysis is critical for the practical application of ground mobile robots in real-world tasks, especially in outdoor unstructured environments. In this paper, we propose a novel spatial-temporal traversability assessment method, which aims to enable autonomous robots to effectively navigate
Autonomous navigation of car-like robots on uneven terrain poses unique challenges compared to flat terrain, particularly in traversability assessment and terrain-associated kinematic modelling for motion planning. This paper introduces SEB-Naver, a novel SE(2)-based local navigation framework desig
Video-to-audio generation is essential for synthesizing realistic audio tracks that synchronize effectively with silent videos.Following the perspective of extracting essential signals from videos that can precisely control the mature text-to-audio generative diffusion models, this paper presents ho…
Optimization has been widely used to generate smooth trajectories for motion planning. However, existing trajectory optimization methods show weakness when dealing with large-scale long trajectories. Recent advances in parallel computing have accelerated optimization in some fields, but how to effic
Most existing NeRF methods rely on RGB images, making them unsuitable for scenarios with darkness, low light, or adverse weather conditions. To address this limitation, we propose TeX-NeRF, a NeRF framework based on heat sensing, designed for a new task: novel HADAR view synthesis. Our approach leve
Terrestrial and aerial bimodal vehicles have gained significant interest due to their energy efficiency and versatile maneuverability across different domains. However, most existing passive-wheeled bimodal vehicles rely on attitude regulation to generate forward thrust, which inevitably results in
Representation Alignment (REPA) that aligns Diffusion Transformer (DiT) hidden-states with ViT visual encoders has proven highly effective in DiT training, demonstrating superior convergence properties, but it has not been validated on the canonical diffusion U-Net architecture that shows faster con…
Drone racing has become a popular international competition and has attained wide attention in recent years. However, the requirements of high-level operation keep the novice pilots away from participating in it. This paper presents a trajectory-based flight assistive system that enables various ope…
Perception is necessary for autonomous navigation in an unknown area crowded with obstacles. It’s challenging for a robot to navigate safely without any sensors that can sense the environment, resulting in a blind robot, and becomes more difficult when comes to a group of robots. However, it could b…
Multi-robot teams have attracted attention from industry and academia for their ability to perform collaborative tasks in unstructured environments, such as wilderness rescue and collaborative transportation. In this letter, we propose a trajectory planning method for a non-holonomic robotic team wi
Reliable hand mesh reconstruction (HMR) from commonly-used color and depth sensors is challenging especially under scenarios with varied illuminations and fast motions. Event camera is a highly promising alternative for its high dynamic range and dense temporal resolution properties but it lacks key…
Multi-robot system is desired to achieve global cost-efficiency by fully utilizing individual advantages. For example, leveraging unmanned aerial vehicles' (UAVs') agility for inspection and ground vehicles' (UGVs') capability for heavy-duty tasks. Coordinating the motion of multiple robots smartly
Separating the direct and global components of a scene aids in shape recovery and basic material understanding. Conventional methods capture multiple frames under high frequency illumination patterns or shadows requiring the scene to keep stationary during the image acquisition process. Single-frame…
In this paper we abstract the process of people hearing speech extracting meaningful cues and creating various dynamically audio-consistent talking faces termed Listening and Imagining into the task of high-fidelity diverse talking faces generation from a single audio. Specifically it involves two c…
State-of-the-art robotics simulators are equipped with well-established mapping, planning, and control systems. However, they lack modularity and the convenience of plug-and-play functionality. In this work, we present FastSim, a high-fidelity and user-friendly simulation framework based on the Unit
In many situations such as city delivery and wild inspection, quadrotors are often required to follow a predefined reference trajectory. However, these reference trajectories cannot be perfectly safe, resulting in conflicts between tracking the reference precisely, flying safely, and finishing the m…
Active reconstruction technique enables robots to autonomously collect scene data for full coverage, relieving users from tedious and time-consuming data capturing process. However, designed based on unsuitable scene representations, existing methods show unrealistic reconstruction results or the in…
Needle interventions are crucial in neurosurgery, requiring high precision and stability. This paper presents a 5-DoF head-mounted hydraulic needle robot designed for accurate and targeted needle insertion and neuroimaging in the deep brain. The robot is compact and lightweight by utilizing a hydrau…
Super-Resolution (SR) reconstructs high-resolution images from low-resolution ones. CNNs and window-attention methods are two major categories of canonical SR models. However these measures are rigid: in both operations each pixel gathers the same number of neighboring pixels hindering their effecti…
Autonomous target tracking with quadrotors has wide applications in many scenarios, such as cinematographic follow-up shooting or suspect chasing. Target motion prediction is necessary when designing the tracking planner. However, the widely used constant velocity or constant rotation assumption can…
Just as humans can become disoriented in featureless deserts or thick fogs, not all environments are conducive to the Localization Accuracy and Stability (LAS) of autonomous robots. This paper introduces an efficient framework designed to enhance LiDAR-based LAS through strategic trajectory generati…
In order to reduce the computational complexity of large language models, great efforts have been made to to improve the efficiency of transformer models such as linear attention and flash-attention. However, the model size and corresponding computational complexity are constantly scaled up in pursu…
"We present a novel pipeline for learning high-quality triangular human avatars from multi-view videos. Recent methods for avatar learning are typically based on neural radiance fields (NeRF), which is not compatible with traditional graphics pipeline and poses great challenges for operations like e…
Open-world 3D reconstruction models have recently garnered significant attention. However, without sufficient 3D inductive bias, existing methods typically entail expensive training costs and struggle to extract high-quality 3D meshes. In this work, we introduce MeshFormer, a sparse-view reconstruct…
In recent years, multirotors have become more and more widely used, such as in aerial photography and delivery. Ensuring a safe landing in emergencies is the most basic requirement, and it is important to make full use of all the sensors of the multirotor. To improve the safety of UAV landing in unk…
Recent releases of Large Language Models (LLMs), e.g. ChatGPT, are astonishing at generating human-like texts, but they may impact the authenticity of texts. Previous works proposed methods to detect these AI-generated texts, including simple ML classifiers, pretrained-model-based zero-shot methods,…
The removal of atmospheric turbulence is crucial for long-distance imaging. Leveraging the stochastic nature of atmospheric turbulence numerous algorithms have been developed that employ multi-frame input to mitigate the turbulence. However when limited to a single frame existing algorithms face sub…
Among the numerous efforts towards digitally recovering the physical world Neural Radiance Fields (NeRFs) have proved effective in most cases. However underwater scene introduces unique challenges due to the absorbing water medium the local change in lighting and the dynamic contents in the scene. W…
Tracked robots with reconfigurable mechanisms exhibit great maneuverability due to their adaptability to complex ground conditions. Reconfigurable tracked robots with geometry-changing tracks show further obstacle-crossing capabilities with compact dimensions. However, existing systems face deployme…
Recent advancements in open-world 3D object generation have been remarkable with image-to-3D methods offering superior fine-grained control over their text-to-3D counterparts. However most existing models fall short in simultaneously providing rapid generation speeds and high fidelity to input image…
Rotary Position Embedding (RoPE) is an efficient position encoding approach and is widely utilized in numerous large language models (LLMs). Recently, a lot of methods have been put forward to further expand the context window based on RoPE. The core concept of those methods is to predefine or searc…
Polarimetric imaging is a challenging problem in the field of polarization-based vision, since setting a short exposure time reduces the signal-to-noise ratio, making the degree of polarization (DoP) and the angle of polarization (AoP) severely degenerated, while if setting a relatively long exposur…
This paper focuses on advancing the applicability of human avatar learning methods by proposing RAM-Avatar which learns a Real-time photo-realistic Avatar that supports full-body control from Monocular videos. To achieve this goal RAM-Avatar leverages two statistical templates responsible for modeli…
We propose SPHINX-X, an extensive Multi-modality Large Language Model (MLLM) series developed upon SPHINX. To improve the architecture and training efficiency, we modify the SPHINX framework by removing redundant visual encoders, bypassing fully-padded sub-images with skip tokens, and simplifying mu…
Mutual localization stands as a foundational component within various domains of multi-robot systems. Nevertheless, in relative pose estimation, time synchronization is usually underappreciated and rarely addressed, although it significantly influences estimation accuracy. In this paper, we introduc…
In this letter, we present a novel bi-modal bi-copter robot called Skater, which is adaptable to air and various ground surfaces. Skater consists of a bi-copter moving along its longitudinal direction with two passive wheels on both sides. Using a longitudinally arranged bi-copter as the unified act
"Open-world 3D generation has recently attracted considerable attention. While many single-image-to-3D methods have yielded visually appealing outcomes, they often lack sufficient controllability and tend to produce hallucinated regions that may not align with users’ expectations. In this paper, we…
The spiking camera is an emerging neuromorphic vision sensor that records high-speed motion scenes by asynchronously firing continuous binary spike streams. Prevailing image reconstruction methods, generating intermediate frames from these spike streams, often rely on complex step-by-step network ar…
Miniature rotation actuators have been extensively developed and utilized in optical coherence tomography (OCT) endoscopy, enabling distortion-free OCT imaging in complex and tortuous environments. However, the use of electrical-driven rotation actuators raises safety concerns. Although magnetic-dri…
Diffusion Transformers (DiTs) introduce the transformer architecture to diffusion tasks for latent-space image generation. With an isotropic architecture that chains a series of transformer blocks, DiTs demonstrate competitive performance and good scalability; but meanwhile, the abandonment of U-Net…
Collision evaluation is of essential importance in various applications. However, existing methods are either cumbersome to calculate or not exact. Therefore, considering the cost of implementation, most whole-body planning works, which require evaluating collision between robots and environments, s…
Autonomous navigation of ground robots on uneven terrain is being considered in more and more tasks. However, uneven terrain will bring two problems to motion planning: how to assess the traversability of the terrain and how to cope with the dynamics model of the robot associated with the terrain. T…
The advance of unmanned aerial vehicles (UAVs) has enabled customers and directors to film from the air. However, operating the drone to produce desired videos upon a moving object is hard to achieve. This letter proposes an autonomous aerial videography system that integrates customized shots and d
Mutual localization provides a consensus of reference frame as an essential basis for cooperation in multi-robot systems. Previous works have developed certifiable and robust solvers for relative transformation estimation between each pair of robots. However, recovering relative poses for robotic sw
Mutual localization plays a crucial role in multi-robot cooperation. CREPES, a novel system that focuses on six degrees of freedom (DOF) relative pose estimation for multi-robot systems, is proposed in this paper. CREPES has a compact hardware design using active infrared (IR) LEDs, an IR fish-eye c…
The development of autonomous rotary-wing UAVs has shown an evident tendency in miniaturization. However, the side effects brought by miniaturization, such as decreased load capability, shorter flight duration and reduced autonomous ability, seriously hinder its process. In this paper, we first inve…
This letter presents a novel solution for UAV control in cooperative multi-robot systems, which can be used in various scenarios such as leader-following, landing on a moving base, or specific relative motion with a target. Unlike classical methods that tackle UAV control in the world frame, we dire
Optimization-based trajectory generation methods are widely used in whole-body planning for robots. However, existing work either oversimplifies the robot's geometry and environment representation, resulting in a conservative trajectory or suffers from a huge overhead in maintaining additional infor…
This paper proposes a client selection (CS) method to tackle the communication bottleneck of federated learning (FL) while concurrently coping with FL’s data heterogeneity issue. Specifically, we first analyze the effect of CS in FL and show that FL training can be accelerated by adequately choosing…
Robot swarm is a hot spot in robotic research community. In this paper, we propose a decentralized framework for car-like robotic swarm which is capable of real-time planning in cluttered environments. In this system, path finding is guided by environmental topology information to avoid frequent top…
For years, researchers have been devoted to generalizable object perception and manipulation, where cross-category generalizability is highly desired yet underexplored. In this work, we propose to learn such cross-category skills via Generalizable and Actionable Parts (GAParts). By identifying and d…
Recently, emotional talking face generation has received considerable attention. However, existing methods only adopt one-hot coding, image, or audio as emotion conditions, thus lacking flexible control in practical applications and failing to handle unseen emotion styles due to limited semantics. T…
Terrestrial and aerial bimodal vehicles have gained widespread attention due to their cross-domain maneuverability. Nevertheless, their bimodal dynamics significantly increase the complexity of motion planning and control, thus hindering robust and efficient autonomous navigation in unknown environm…
Recently, the sizes of deep neural networks and training datasets both increase drastically to pursue better performance in a practical sense. With the prevalence of transformer-based models in vision tasks, even more pressure is laid on the GPU platforms to train these heavy models, which consumes…
Road rage is a social problem that deserves attention, but few research has been done so far. In this paper, based on the biological topology of multi-channel electroencephalogram (EEG) signals, we propose a model which combines transferable attention (TA) and regularized graph neural network (RGNN)…
Single image 3D reconstruction is an important but challenging task that requires extensive knowledge of our natural world. Many existing methods solve this problem by optimizing a neural radiance field under the guidance of 2D diffusion models but suffer from lengthy optimization time, 3D inconsist…
Polarization-based vision algorithms have found uses in various applications since polarization provides additional physical constraints. However, in low-light conditions, their performance would be severely degenerated since the captured polarized images could be noisy, leading to noticeable degrad…
In recent years, there is a noteworthy advance-ment in autonomous drone racing. However, the primary focus is on attaining execution times, while scant attention is given to the challenges of dynamic environments. The high-speed nature of racing scenarios, coupled with the potential for unforeseeabl…
This letter presents a novel and retractable ring-shaped quadrotor called Ring-Rotor that can adjust the vehicle's length and width simultaneously. Unlike other morphing quadrotors with high platform complexity and poor controllability, Ring-Rotor uses only one servo motor for morphing but reduces t
For letting mobile robots travel flexibly through complicated environments, increasing attention has been paid to the whole-body collision evaluation. Most existing works either opt for the conservative corridor-based methods that impose strict requirements on the corridor generation, or ESDF-based…
In constrained solution spaces with a huge number of homotopy classes, standalone sampling-based kinodynamic planners suffer low efficiency in convergence. Local optimization is integrated to alleviate this problem. In this paper, we propose to thrive the trajectory tree growing by optimizing the tr…
By taking the complementary advantage of multicopters and ground vehicles, air-ground vehicles have shown great potential in various fields due to their superior mobility and outstanding endurance. However, most of the previous works adopt complicated mechanisms, and fail to develop a controller wit
With the development of robotics, ground robots are no longer limited to planar motion. Passive height variation due to complex terrain and active height control provided by special structures on robots require a more general navigation planning framework beyond 2D. Existing methods rarely considers…
Convolutional Neural Networks (CNNs) are hard to deploy on edge devices due to its high computation and storage complexities. As a common practice for model compression, network pruning consists of two major categories: unstructured and structured pruning, where unstructured pruning constantly perfo…
Service robots have attracted extensive attention due to specially designed functions, such as mobile manipulators or robots with extra structures. For robots that have changing shapes, autonomous navigation in the real world presents new challenges. In this paper, we propose a trajectory optimizati…
In the field of computer vision, recent works show that a pure MLP architecture mainly stacked by fully-connected layers can achieve competing performance with CNN and transformer. An input image of vision MLP is usually split into multiple tokens (patches), while the existing MLP models directly ag…
Online trajectory planners enable quadrotors to safely and smoothly navigate in unknown cluttered environments. However, tuning parameters is challenging since modern planners have become too complex to mathematically model and predict their interaction with unstructured environments. This work take…
Terrestrial-aerial bimodal vehicles bloom in both academia and industry because they incorporate both the high mobility of aerial vehicles and the long endurance of ground vehicles. In this work, we present an autonomous and adaptive navigation framework to bring complete autonomy to this class of v
Mutual localization is essential for coordination and cooperation in multi-robot systems. Previous works have tackled this problem by assuming available correspondences between measurements and received odometry estimations. However, the correspondence is difficult to acquire, especially for unified
"3D human pose estimation from a monocular video has recently seen significant improvements. However, most state-of-the-art methods are kinematics-based, which are prone to physically implausible motions with pronounced artifacts. Current dynamics-based methods can predict physically plausible motio…
In this work, we propose an interoceptive-only state estimation system for a quadrotor with deep neural network processing, where the quadrotor dynamics is considered as a perceptive supplement of the inertial kinematics. To improve the precision of multi-sensor fusion, we train cascaded networks on
"Face reenactment and swapping share a similar identity and attribute manipulating pattern, but most methods treat them separately, which is redundant and practical-unfriendly. In this paper, we propose an effective end-to-end unified framework to achieve both tasks. Unlike existing methods that dir…
For aerial swarms, navigation in a prescribed formation is widely practiced in various scenarios. However, the associated planning strategies typically lack the capability of avoiding obstacles in cluttered environments. To address this deficiency, we present an optimization-based method that ensure…
Free-space-oriented roadmaps typically generate a series of convex geometric primitives, which constitute the safe region for motion planning. However, a static environment is assumed for this kind of roadmap. This assumption makes it unable to deal with dynamic obstacles and limits its applications…
For real-time multirotor kinodynamic planning, the efficiency of sampling-based methods is usually hindered by difficult-to-sample homotopy classes like narrow passages. In this paper, we address this issue by a hybrid scheme. We firstly propose a fast regional optimizer exploiting the information o…
This paper proposes Elastic Tracker, a flexible trajectory planning framework that can deal with challenging tracking tasks with guaranteed safety and visibility. Firstly, an object detection and intension-free motion prediction method is designed. Then an occlusion-aware path finding method is prop…
We study the problem of learning from positive and unlabeled (PU) data in the federated setting, where each client only labels a little part of their dataset due to the limitation of resources and time. Different from the settings in traditional PU learning where the negative class consists of a sin…
Gaze isan intuitive and direct way to represent the intentions of an individual. However, when it comes to assistive aerial teleoperation which aims to perform operators’ intention, rare attention has been paid to gaze. Existing methods obtain intention directly from the remote controller (RC) input
Light-weight convolutional neural networks (CNNs) are specially designed for applications on mobile devices with faster inference speed. The convolutional operation can only capture local information in a window region, which prevents performance from being further improved. Introducing self-attent…
Previous vision MLPs such as MLP-Mixer and ResMLP accept linearly flattened image patches as input, making them inflexible for different input sizes and hard to capture spatial information. Such approach withholds MLPs from getting comparable performance with their transformer-based counterparts and…
Decision trees are well-known due to their ease of interpretability. To improve accuracy, we need to grow deep trees or ensembles of trees. These are hard to interpret, offsetting their original benefits. Shapley values have recently become a popular way to explain the predictions of tree-based mac…
This letter presents a complete framework Meeting-Merging-Mission for multi-robot exploration under communication restriction. Considering communication is limited in both bandwidth and range in the real world, we propose a lightweight environment presentation method and an efficient cooperative exp…
This paper studies the efficiency problem for visual transformers by excavating redundant calculation in given networks. The recent transformer architecture has demonstrated its effectiveness for achieving excellent performance on a series of computer vision tasks. However, similar to that of convol…
This paper presents a novel trajectory planning method for aerial perching. Compared with the existing work, the terminal states and the trajectory durations can be adjusted adaptively, instead of being determined in advance. Further-more, our planner is able to minimize the tangential relative spee…
This paper presents a novel Region-Aware Face Swapping (RAFSwap) network to achieve identity-consistent harmonious high-resolution face generation in a local-global manner: 1) Local Facial Region-Aware (FRA) branch augments local identity-relevant features by introducing the Transformer to effective…
In this paper, we describe a robust multi-drone planning framework for high-speed trajectories in large scenes. It uses a free-space-oriented map to free the optimization from cumbersome environment data. A capsule-like safety constraint is designed to avoid reciprocal collisions when vehicles devia…
In the practical application of restoring low-resolution gray-scale images, we generally need to run three separate processes of image colorization, super-resolution, and dows-sampling operation for the target device. However, this pipeline is redundant and inefficient for the independent processes,…
Domain Adaptation aims to transfer the knowledge learned from a labeled source domain to an unlabeled target domain whose data distributions are different. However, the training data in source domain required by most of the existing methods is usually unavailable in real-world applications due to pr…
The visible capability is critical in many robot applications, such as inspection and surveillance, etc. Without the assurance of the visibility to targets, some tasks end up not being complete or even failing. In this paper, we propose a visibility guaranteed planner by star-convex constrained opti…
Recently, the community has witnessed numerous datasets built for developing and testing state estimators. However, for some applications such as aerial transportation or search-and-rescue, the contact force or other disturbance must be perceived for robust planning and control, which is beyond the…
Inspired by biological evolution, we explain the rationality of Vision Transformer by analogy with the proven practical Evolutionary Algorithm (EA) and derive that both of them have consistent mathematical representation. Analogous to the dynamic local population in EA, we improve the existing trans…
Transformer models have achieved great progress on computer vision tasks recently. The rapid development of vision transformers is mainly contributed by their high representation ability for extracting informative features from input images. However, the mainstream transformer models are designed wi…
In this paper, we introduce a complete system for autonomous flight of quadrotors in dynamic environments with onboard sensing. Extended from existing work, we develop an occlusion-aware dynamic perception method based on depth images, which classifies obstacles as dynamic and static. For representi…
Gradient-based planners are widely used for quadrotor local planning, in which a Euclidean Signed Distance Field (ESDF) is crucial for evaluating gradient magnitude and direction. Nevertheless, computing such a field has much redundancy since the trajectory optimization procedure only covers a very
This paper presents a decentralized and asynchronous systematic solution for multi-robot autonomous navigation in unknown obstacle-rich scenes using merely onboard resources. The planning system is formulated under gradient-based local planning framework, where collision avoidance is achieved by for…
The quadrotor is popularly used in challenging environments due to its superior agility and flexibility. In these scenarios, trajectory planning plays a vital role in generating safe motions to avoid obstacles while ensuring flight smoothness. Although many works on quadrotor planning have been prop…
An event camera detects the scene radiance changes and sends a sequence of asynchronous event streams with high dynamic range, high temporal resolution, and low latency. However, the spatial resolution of event cameras is limited as a trade-off for these outstanding properties. To reconstruct high-r…
Adaptive autonomous navigation with no prior knowledge of extraneous disturbance is of great significance for quadrotors in a complex and unknown environment. The mainstream approach that considers external disturbance is to implement disturbance-rejected control and path tracking. However, the robu
The development of aerial autonomy has enabled aerial robots to fly agilely in complex environments. However, dodging fast-moving objects in flight remains a challenge, limiting the further application of unmanned aerial vehicles (UAVs). The bottleneck of solving this problem is the accurate percept…
With the autonomy of aerial robots advances in recent years, autonomous drone racing has drawn increasing attention. In a professional pilot competition, a skilled operator always controls the drone to agilely avoid obstacles in aggressive attitudes, for reaching the destination as fast as possible.
This paper proposes a systematic solution that uses an unmanned aerial vehicle (UAV) to aggressively and safely track an agile target. It properly handles the challenging situations where the intent of the target and the dense environments are unknown. Our work is divided into two parts: target moti…
For quadrotor trajectory planning, describing a polynomial trajectory through coefficients and end-derivatives both enjoy their own convenience in energy minimization. We name them double descriptions of polynomial trajectories. The transformation between them, causing most of the inefficiency and i…
Neural Architecture Search (NAS) aims to automatically discover optimal architectures. In this paper, we propose an hourglass-inspired approach (HourNAS) for extremely fast NAS. It is motivated by the fact that the effects of the architecture often proceed from the vital few blocks. Acting like the…
Model-based 3D pose and shape estimation methods reconstruct a full 3D mesh for the human body by estimating several parameters. However, learning the abstract parameters is a highly non-linear process and suffers from image-model misalignment, leading to mediocre model performance. In contrast, 3D…
Data-free learning for student networks is a new paradigm for solving users' anxiety caused by the privacy problem of using original training data. Since the architectures of modern convolutional neural networks (CNNs) are compact and sophisticated, the alternative images or meta-data generated from…
Haze, a common kind of bad weather caused by atmospheric scattering, decreases the visibility of scenes and degenerates the performance of computer vision algorithms. Single-image dehazing methods have shown their effectiveness in a large variety of scenes, however, they are based on handcrafted pri…
In autonomous navigation, sensors suffer from massive occlusion in cluttered environments, leaving a significant amount of space unknown. In practice, treating the unknown space in optimistic or pessimistic ways both set limitations on planning performance. Therefore, aggressiveness and safety canno…
Neural network pruning is an essential approach for reducing the computational complexity of deep models so that they can be well deployed on resource-limited devices. Compared with conventional methods, the recently developed dynamic pruning methods determine redundant filters variant to each input…
Maintaining a map online is resource-consuming while a robust navigation system usually needs environment abstraction via a well-fused map. In this paper, we propose a mapless local planner which directly conducts such abstraction on the unfused sensor data. A limited-memory data structure with a re…
As the computing power of modern hardware is increasing strongly, pre-trained deep learning models (e.g., BERT, GPT-3) learned on large-scale datasets have shown their effectiveness over conventional methods. The big progress is mainly contributed to the representation ability of transformer and its…
In this letter, we propose a lightweight yet effective Topology Guided Kinodynamic planner (TGK-Planner) for quadrotor aggressive flights with limited onboard computing resources. The proposed system follows the traditional hierarchical planning workflow, with novel designs to improve the robustness
Recently, quadrotors are gaining significant attention in aerial transportation and delivery. In these scenarios, an accurate estimation of the external force is as essential as the six degree-of-freedom (DoF) pose since it is of vital importance for planning and control of the vehicle. To this end,…
The visibility of targets determines performance and even success rate of various applications, such as active slam, exploration, and target tracking. Therefore, it is crucial to take the visibility of targets into explicit account in trajectory planning. In this paper, we propose a general metric f…
Multicopters are able to perform high maneuverability yet their potential have not been fully achieved. In this work, we propose a full-body, optimization-based motion planning framework that takes shape and attitude of aerial robot into consideration such that the aggressiveness of drone maneuverin…
Neural architecture search (NAS) aims to automatically design deep neural networks of satisfactory performance. Wherein, architecture performance predictor is critical to efficiently value an intermediate neural architecture. But for the training of this predictor, a number of neural architectures a…
Compared with cheap addition operation, multiplication operation is of much higher computation complexity. The widely-used convolutions in deep neural networks are exactly cross-correlation to measure the similarity between input feature and convolution filters, which involves massive multiplication…
With much research has been conducted into trajectory planning for quadrotors, planning with spatial and temporal optimal trajectories in real-time is still challenging. In this letter, we propose a framework for large-scale waypoint-based polynomial trajectory generation, with highlights on its sup
Searching techniques in most of existing neural architecture search (NAS) algorithms are mainly dominated by differentiable methods for the efficiency reason. In contrast, we develop an efficient continuous evolutionary approach for searching neural networks. Architectures in the population that sha…
This paper presents a novel end-to-end dynamic time-lapse video generation framework, named DTVNet, to generate diversified time-lapse videos from a single landscape image, which are conditioned on normalized motion vectors. The proposed DTVNet consists of two submodules: mph{Optical Flow Encoder} (…
This paper studies the compression and acceleration of 3-dimensional convolutional neural networks (3D CNNs). To reduce the memory cost and computational complexity of deep neural networks, a number of algorithms have been explored by discovering redundant parameters in pre-trained networks. However…
Reconstruction of high dynamic range image from a single low dynamic range image captured by a frame-based conventional camera, which suffers from over- or under-exposure, is an ill-posed problem. In contrast, recent neuromorphic cameras are able to record high dynamic range scenes in the form of an…
This paper defines a positive and unlabeled classification problem for standard GANs, which then leads to a novel technique to stabilize the training of the discriminator in GANs. Traditionally, real data are taken as positive while generated data are negative. This positive-negative classification…
This paper proposes a reliable neural network pruning algorithm by setting up a scientific control. Existing pruning methods have developed various hypotheses to approximate the importance of filters to the network and then execute filter pruning accordingly. To increase the reliability of the resul…
Quantized neural networks with low-bit weights and activations are attractive for developing AI accelerators. However, the quantization functions used in most conventional quantization methods are non-differentiable, which increases the optimization difficulty of quantized networks. Compared with fu…
A conventional camera often suffers from over- or under-exposure when recording a real-world scene with a very high dynamic range (HDR). In contrast, a modulo camera with a Markov random field (MRF) based unwrapping algorithm can theoretically accomplish unbounded dynamic range but shows degenerate…
Learning portable neural networks is very essential for computer vision for the purpose that pre-trained heavy deep models can be well applied on edge devices such as mobile phones and micro sensors. Most existing deep neural network compression and speed-up methods are very effective for training c…
Bad training data would challenge the learning model from understanding the underlying data-generating scheme, which then increases the difficulty in achieving satisfactory performance on unseen test data. We suppose the real data distribution lies in a distribution set supported by the empirical di…
This paper aims to build efficient convolutional neural networks using a set of Lego filters. Many successful building blocks, e.g., inception and residual modules, have been designed to refresh state-of-the-art records of CNNs on visual recognition tasks. Beyond these high-level modules, we suggest…
Crowd counting is the task of estimating people numbers in crowd images. Modern crowd counting methods employ deep neural networks to estimate crowd counts via crowd density regressions. A major challenge of this task lies in the perspective distortion, which results in drastic person scale change i…
High-dimensional data in many areas such as computer vision and machine learning tasks brings in computational and analytical difficulty. Feature selection which selects a subset from observed features is a widely used approach for improving performance and effectiveness of machine learning models w…
Recent advances in multi-stage algorithms have shown great promise, but two important problems still remain. First of all, at inference time, information can't feed back from downstream to upstream. Second, at training time, end-to-end training is not possible if the overall pipeline involves non-di…
This paper introduces versatile filters to construct efficient convolutional neural network. Considering the demands of efficient deep learning techniques running on cost-effective hardware, a number of methods have been developed to learn compact neural networks. Most of these works aim to slim dow…
Convolutional neural networks (CNNs) have shown extraordinary performance in a number of applications, but they are usually of heavy design for the accuracy reason. Beyond compressing the filters in CNNs, this paper focuses on the redundancy in the feature maps derived from the large number of filte…
Multi-view representations are widely existed in practical applications, the quality of latent representation learned from multi-view observations often suffer from noise and outliers in original data. In this work, we propose an auto encoder based deep multi-view robust representation learning (DMR…
Pre-learnt subspace methods, e.g., 3DMMs, are significant exploration for the synthesis of 3D faces by assuming that faces are in a linear class. However, the human face is in a nonlinear manifold, and a new test are always not in the pre-learnt subspace accurately because of the disparity brought b…
Deep convolutional neural networks (CNNs) are successfully used in a number of applications. However, their storage and computational requirements have largely prevented their widespread use on mobile devices. Here we present an effective CNN compression approach in the frequency domain, which focus…