Searcharxiv⌕ Search

arXiv subjects

Tao Huang

Publications and source records attributed to Tao Huang.

At least 217 records · Page 12Linked to original sources
arXiv2023

Localization-Guided Track: A Deep Association Multi-Object Tracking Framework Based on Localization Confidence of Detections

In currently available literature, no tracking-by-detection (TBD) paradigm-based tracking method has considered the localization confidence of detection boxes. In most TBD-based methods, it is considered that objects of low detection confidence are highly occluded and thus it is a normal practice to directly disregard such objects or to reduce their priority in matching. In addition, appearance similarity is not a factor to consider for matching these objects. However, in terms of the detection confidence fusing classification and localization, objects of low detection confidence may have inaccurate localization but clear appearance; similarly, objects of high detection confidence may have inaccurate localization or unclear appearance; yet these objects are not further classified. In view of these issues, we propose Localization-Guided Track (LG-Track). Firstly, localization confidence is applied in MOT for the first time, with appearance clarity and localization accuracy of detection boxes taken into account, and an effective deep association mechanism is designed; secondly, based on the classification confidence and localization confidence, a more appropriate cost matrix can be selected and used; finally, extensive experiments have been conducted on MOT17 and MOT20 datasets. The results show that our proposed method outperforms the compared state-of-art tracking methods. For the benefit of the community, our code has been made publicly at https://github.com/mengting2023/LG-Track.

cs.CV↗
arXiv2023

Homography matrix based trajectory planning method for robot uncalibrated visual servoing

In view of the classical visual servoing trajectory planning method which only considers the camera trajectory, this paper proposes one homography matrix based trajectory planning method for robot uncalibrated visual servoing. Taking the robot-end-effector frame as one generic case, eigenvalue decomposition is utilized to calculate the infinite homography matrix of the robot-end-effector trajectory, and then the image feature-point trajectories corresponding to the camera rotation is obtained, while the image feature-point trajectories corresponding to the camera translation is obtained by the homography matrix. According to the additional image corresponding to the robot-end-effector rotation, the relationship between the robot-end-effector rotation and the variation of the image feature-points is obtained, and then the expression of the image trajectories corresponding to the optimal robot-end-effector trajectories (the rotation trajectory of the minimum geodesic and the linear translation trajectory) are obtained. Finally, the optimal image trajectories of the uncalibrated visual servoing controller is modified to track the image trajectories. Simulation experiments show that, compared with the classical IBUVS method, the proposed trajectory planning method can obtain the shortest path of any frame and complete the robot visual servoing task with large initial pose deviation.

cs.RO↗
arXiv2023

AI-Generated Network Design: A Diffusion Model-based Learning Approach

The future networks pose intense demands for intelligent and customized designs to cope with the surging network scale, dynamically time-varying environments, diverse user requirements, and complicated manual configuration. However, traditional rule-based solutions heavily rely on human efforts and expertise, while data-driven intelligent algorithms still lack interpretability and generalization. In this paper, we propose the AIGN (AI-Generated Network), a novel intention-driven paradigm for network design, which allows operators to quickly generate a variety of customized network solutions and achieve expert-free problem optimization. Driven by the diffusion model-based learning approach, AIGN has great potential to learn the reward-maximizing trajectories, automatically satisfy multiple constraints, adapt to different objectives and scenarios, or even intelligently create novel designs and mechanisms unseen in existing network environments. Finally, we conduct a use case to demonstrate that AIGN can effectively guide the design of transmit power allocation in digital twin-based access networks.

cs.NI↗
arXiv2023

Value-Informed Skill Chaining for Policy Learning of Long-Horizon Tasks with Surgical Robot

Reinforcement learning is still struggling with solving long-horizon surgical robot tasks which involve multiple steps over an extended duration of time due to the policy exploration challenge. Recent methods try to tackle this problem by skill chaining, in which the long-horizon task is decomposed into multiple subtasks for easing the exploration burden and subtask policies are temporally connected to complete the whole long-horizon task. However, smoothly connecting all subtask policies is difficult for surgical robot scenarios. Not all states are equally suitable for connecting two adjacent subtasks. An undesired terminate state of the previous subtask would make the current subtask policy unstable and result in a failed execution. In this work, we introduce value-informed skill chaining (ViSkill), a novel reinforcement learning framework for long-horizon surgical robot tasks. The core idea is to distinguish which terminal state is suitable for starting all the following subtask policies. To achieve this target, we introduce a state value function that estimates the expected success probability of the entire task given a state. Based on this value function, a chaining policy is learned to instruct subtask policies to terminate at the state with the highest value so that all subsequent policies are more likely to be connected for accomplishing the task. We demonstrate the effectiveness of our method on three complex surgical robot tasks from SurRoL, a comprehensive surgical simulation platform, achieving high task success rates and execution efficiency. Code is available at $\href{https://github.com/med-air/ViSkill}{\text{https://github.com/med-air/ViSkill}}$.

cs.RO↗
arXiv2023

Convex Optimal Power Flow Based on Power Injection-based Equations and Its Application in Bipolar DC Distribution Network

Optimal power flow (OPF) is a fundamental tool for analyzing the characteristics of bipolar DC distribution network (DCDN). However, existing OPF models face challenges in reflecting the power distribution and exchange of bipolar DCDN directly since its decision variables are voltage and current. This paper addresses this issue by establishing a convex OPF model that can be used for the planning and operation of bipolar DCDN. First, the power flow characteristics of bipolar DCDN are revealed through power injection-based equations, upon which the original OPF model is established. Next, the original OPF model undergoes a transformation into a convex OPF model based on second-order cone programming (SOCP) through variable substitution, secondorder cone relaxation, McCormick relaxation, and first-order Taylor expansion, respectively. Finally, the sequence bound tightening algorithm (STBA) is employed to tighten the boundaries of McCormick envelopes in each iteration to ensure the exactness of the convex OPF model. The effectiveness of this novel OPF model for bipolar DCDN is verified through two case studies, i.e., capacity configuration of distributed generation (DG) and operation optimization of bipolar DCDN.

eess.SY↗
arXiv2023

A step towards digital operations -- A novel grey-box approach for modelling the heat dynamics of Ultra-low temperature freezing chambers

Ultra-low temperature (ULT) freezers store perishable bio-contents and have high energy consumption, which highlight a demand for reliable methods for intelligent surveillance and smart energy management. This study introduces a novel grey-box modelling approach based on stochastic differential equations to describe the heat dynamics of the ULT freezing chambers. The proposed modelling approach only requires temperature data measured by the embedded sensors and uses data from the regular operation periods for model identification. The model encompasses three states: chamber temperature, envelope temperature, and local evaporator temperature. Special attention is given to the local evaporator temperature state, which is modelled as a time-variant system, to characterize the time delay and dynamic variations in cooling intensity. Two ULT freezers with different operational patterns are modelled. The unknown model parameters are estimated using the maximum likelihood method. The results demonstrate that the models can accurately predict the chamber temperature measured by the control probe (RMSE < 0.19 °C) and are promising to be applied for forecasting future states. In addition, the model for local evaporator temperature can effectively adapt to different operational patterns and provide insight into the local cooling supply status. The proposed approach greatly promotes the practical feasibility of grey-box modelling of the heat dynamics for ULT freezers and can serve several potential digital applications. A major limitation of the modelling approach is the low identifiability, which can potentially be addressed by inferring model parameters based on relative parameter changes.

eess.SY↗
arXiv2023

Human-in-the-loop Embodied Intelligence with Interactive Simulation Environment for Surgical Robot Learning

Surgical robot automation has attracted increasing research interest over the past decade, expecting its potential to benefit surgeons, nurses and patients. Recently, the learning paradigm of embodied intelligence has demonstrated promising ability to learn good control policies for various complex tasks, where embodied AI simulators play an essential role to facilitate relevant research. However, existing open-sourced simulators for surgical robot are still not sufficiently supporting human interactions through physical input devices, which further limits effective investigations on how the human demonstrations would affect policy learning. In this work, we study human-in-the-loop embodied intelligence with a new interactive simulation platform for surgical robot learning. Specifically, we establish our platform based on our previously released SurRoL simulator with several new features co-developed to allow high-quality human interaction via an input device. We showcase the improvement of our simulation environment with the designed new features, and validate effectiveness of incorporating human factors in embodied intelligence through the use of human demonstrations and reinforcement learning as a representative example. Promising results are obtained in terms of learning efficiency. Lastly, five new surgical robot training tasks are developed and released, with which we hope to pave the way for future research on surgical embodied intelligence. Our learning platform is publicly released and will be continuously updated in the website: https://med-air.github.io/SurRoL.

cs.RO↗
arXiv2023

Masked Distillation with Receptive Tokens

Distilling from the feature maps can be fairly effective for dense prediction tasks since both the feature discriminability and localization priors can be well transferred. However, not every pixel contributes equally to the performance, and a good student should learn from what really matters to the teacher. In this paper, we introduce a learnable embedding dubbed receptive token to localize those pixels of interests (PoIs) in the feature map, with a distillation mask generated via pixel-wise attention. Then the distillation will be performed on the mask via pixel-wise reconstruction. In this way, a distillation mask actually indicates a pattern of pixel dependencies within feature maps of teacher. We thus adopt multiple receptive tokens to investigate more sophisticated and informative pixel dependencies to further enhance the distillation. To obtain a group of masks, the receptive tokens are learned via the regular task loss but with teacher fixed, and we also leverage a Dice loss to enrich the diversity of learned masks. Our method dubbed MasKD is simple and practical, and needs no priors of tasks in application. Experiments show that our MasKD can achieve state-of-the-art performance consistently on object detection and semantic segmentation benchmarks. Code is available at: https://github.com/hunto/MasKD .

cs.CV↗
arXiv2023

Long-time dynamics of Ericksen-Leslie system on $\mathbb S^2$

In this paper, we study the long-time behavior of full Ericksen-Leslie system modeling the hydrodynamics of nematic liquid crystals between two dimensional unit spheres. Under a weaker assumption for Leslie's coefficients, we give the key energy inequality for the global weak solution. At last, inspired by the conditions on the simplified system, we establish several sufficient conditions which guarantee the uniform convergence of the system in $L^2$ and $H^k$ spaces as time tends to infinity under small initial data.

math.AP↗
arXiv2023

Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robot

Task automation of surgical robot has the potentials to improve surgical efficiency. Recent reinforcement learning (RL) based approaches provide scalable solutions to surgical automation, but typically require extensive data collection to solve a task if no prior knowledge is given. This issue is known as the exploration challenge, which can be alleviated by providing expert demonstrations to an RL agent. Yet, how to make effective use of demonstration data to improve exploration efficiency still remains an open challenge. In this work, we introduce Demonstration-guided EXploration (DEX), an efficient reinforcement learning algorithm that aims to overcome the exploration problem with expert demonstrations for surgical automation. To effectively exploit demonstrations, our method estimates expert-like behaviors with higher values to facilitate productive interactions, and adopts non-parametric regression to enable such guidance at states unobserved in demonstration data. Extensive experiments on $10$ surgical manipulation tasks from SurRoL, a comprehensive surgical simulation platform, demonstrate significant improvements in the exploration efficiency and task success rates of our method. Moreover, we also deploy the learned policies to the da Vinci Research Kit (dVRK) platform to show the effectiveness on the real robot. Code is available at https://github.com/med-air/DEX.

cs.RO↗
arXiv2023

A Flexible and Parsimonious Modelling Strategy for Clustered Data Analysis

Statistical modelling strategy is the key for success in data analysis. The trade-off between flexibility and parsimony plays a vital role in statistical modelling. In clustered data analysis, in order to account for the heterogeneity between the clusters, certain flexibility is necessary in the modelling, yet parsimony is also needed to guard against the complexity and account for the homogeneity among the clusters. In this paper, we propose a flexible and parsimonious modelling strategy for clustered data analysis. The strategy strikes a nice balance between flexibility and parsimony, and accounts for both heterogeneity and homogeneity well among the clusters, which often come with strong practical meanings. In fact, its usefulness has gone beyond clustered data analysis, it also sheds promising lights on transfer learning. An estimation procedure is developed for the unknowns in the resulting model, and asymptotic properties of the estimators are established. Intensive simulation studies are conducted to demonstrate how well the proposed methods work, and a real data analysis is also presented to illustrate how to apply the modelling strategy and associated estimation procedure to answer some real problems arising from real life.

stat.ME↗
arXiv2023

GNN-PMB: A Simple but Effective Online 3D Multi-Object Tracker without Bells and Whistles

Multi-object tracking (MOT) is among crucial applications in modern advanced driver assistance systems (ADAS) and autonomous driving (AD) systems. The global nearest neighbor (GNN) filter, as the earliest random vector-based Bayesian tracking framework, has been adopted in most of state-of-the-arts trackers in the automotive industry. The development of random finite set (RFS) theory facilitates a mathematically rigorous treatment of the MOT problem, and different variants of RFS-based Bayesian filters have then been proposed. However, their effectiveness in the real ADAS and AD application is still an open problem. In this paper, it is demonstrated that the latest RFS-based Bayesian tracking framework could be superior to typical random vector-based Bayesian tracking framework via a systematic comparative study of both traditional random vector-based Bayesian filters with rule-based heuristic track maintenance and RFS-based Bayesian filters on the nuScenes validation dataset. An RFS-based tracker, namely Poisson multi-Bernoulli filter using the global nearest neighbor (GNN-PMB), is proposed to LiDAR-based MOT tasks. This GNN-PMB tracker is simple to use, and it achieves competitive results on the nuScenes dataset. Specifically, the proposed GNN-PMB tracker outperforms most state-of-the-art LiDAR-only trackers and LiDAR and camera fusion-based trackers, ranking the $3^{rd}$ among all LiDAR-only trackers on nuScenes 3D tracking challenge leader board at the time of submission.

eess.SY↗
arXiv2023

Contrastive Learning for Automotive mmWave Radar Detection Points Based Instance Segmentation

The automotive mmWave radar plays a key role in advanced driver assistance systems (ADAS) and autonomous driving. Deep learning-based instance segmentation enables real-time object identification from the radar detection points. In the conventional training process, accurate annotation is the key. However, high-quality annotations of radar detection points are challenging to achieve due to their ambiguity and sparsity. To address this issue, we propose a contrastive learning approach for implementing radar detection points-based instance segmentation. We define the positive and negative samples according to the ground-truth label, apply the contrastive loss to train the model first, and then perform fine-tuning for the following downstream task. In addition, these two steps can be merged into one, and pseudo labels can be generated for the unlabeled data to improve the performance further. Thus, there are four different training settings for our method. Experiments show that when the ground-truth information is only available for a small proportion of the training data, our method still achieves a comparable performance to the approach trained in a supervised manner with 100% ground-truth information.

cs.CV↗
arXiv2023

Deep Instance Segmentation with Automotive Radar Detection Points

Automotive radar provides reliable environmental perception in all-weather conditions with affordable cost, but it hardly supplies semantic and geometry information due to the sparsity of radar detection points. With the development of automotive radar technologies in recent years, instance segmentation becomes possible by using automotive radar. Its data contain contexts such as radar cross section and micro-Doppler effects, and sometimes can provide detection when the field of view is obscured. The outcome from instance segmentation could be potentially used as the input of trackers for tracking targets. The existing methods often utilize a clustering-based classification framework, which fits the need of real-time processing but has limited performance due to minimum information provided by sparse radar detection points. In this paper, we propose an efficient method based on clustering of estimated semantic information to achieve instance segmentation for the sparse radar detection points. In addition, we show that the performance of the proposed approach can be further enhanced by incorporating the visual multi-layer perceptron. The effectiveness of the proposed method is verified by experimental results on the popular RadarScenes dataset, achieving 89.53% mean coverage and 86.97% mean average precision with the IoU threshold of 0.5, which is superior to other approaches in the literature. More significantly, the consumed memory is around 1MB, and the inference time is less than 40ms, indicating that our proposed algorithm is storage and time efficient. These two criteria ensure the practicality of the proposed method in real-world systems.

cs.CV↗
arXiv2023

Cooperative trajectory planning algorithm of USV-UAV with hull dynamic constraints

Efficient trajectory generation in complex dynamic environments remains an open problem in the unmanned surface vehicle (USV). The perception of the USV is usually interfered with by the swing of the hull and the ambient weather, making it challenging to plan the optimal USV trajectories. In this paper, a cooperative trajectory planning algorithm for the coupled USV-UAV system is proposed to ensure that USV can execute a safe and smooth path in the process of autonomous advance in multi-obstacle maps. Specifically, the unmanned aerial vehicle (UAV) plays the role of a flight sensor, providing real-time global map and obstacle information with a lightweight semantic segmentation network and 3D projection transformation. And then, an initial obstacle avoidance trajectory is generated by a graph-based search method. Concerning the unique under-actuated kinematic characteristics of the USV, a numerical optimization method based on hull dynamic constraints is introduced to make the trajectory easier to be tracked for motion control. Finally, a motion control method based on NMPC with the lowest energy consumption constraint during execution is proposed. Experimental results verify the effectiveness of the whole system, and the generated trajectory is locally optimal for USV with considerable tracking accuracy.

cs.RO↗
arXiv2022

Knowledge Distillation from A Stronger Teacher

Unlike existing knowledge distillation methods focus on the baseline settings, where the teacher models and training strategies are not that strong and competing as state-of-the-art approaches, this paper presents a method dubbed DIST to distill better from a stronger teacher. We empirically find that the discrepancy of predictions between the student and a stronger teacher may tend to be fairly severer. As a result, the exact match of predictions in KL divergence would disturb the training and make existing methods perform poorly. In this paper, we show that simply preserving the relations between the predictions of teacher and student would suffice, and propose a correlation-based loss to capture the intrinsic inter-class relations from the teacher explicitly. Besides, considering that different instances have different semantic similarities to each class, we also extend this relational match to the intra-class level. Our method is simple yet practical, and extensive experiments demonstrate that it adapts well to various architectures, model sizes and training strategies, and can achieve state-of-the-art performance consistently on image classification, object detection, and semantic segmentation tasks. Code is available at: https://github.com/hunto/DIST_KD .

cs.CV↗
arXiv2022

Electrokinetic Janus micromotors moving on topographically flat chemical patterns

Ionic and molecular selectivity is considered unique for the nanoscale and not realizable in microfluidics. This is due to the scale-matching problem -- a difficulty to match the dimensions of ions and electrostatic potential screening lengths with the micron-sized confinements. Here, we demonstrate a microscale realization of the ionic transport processes closely resembling those specific to ionic channels or in nanofluidic junctions, including selectivity, guidance through complex geometries and flow focusing. As a model system, we explore electrokinetic spherical Janus micromotors moving over charged surfaces with a complex spatial charge distribution and without any topographical wall. We discuss peculiarities of the long-range electrostatic interaction on the behavior of the system including interface crossing and reflection of positively charged particles from negatively charged interfaces. These results are crucial for understanding the electrokinetic transport of biochemical species under confinement, have the potential to increase the precision of lab-on-chip-based assays, as well as broadening use cases and control strategies of nano-/micromachinery.

cond-mat.soft↗