Author name cluster

Yu Du

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

12 papers

2 author rows

EAAI Journal 2026 Journal Article

Data-driven slippage detection via tactile sensing for stable enveloping-grasp control under external disturbances

Yongyao Li
Yufei Liu
Xinzhao Zhang
Dongdong Zheng
Xu Song
Ming Cong
Dongchen Liu
Yu Du

Enveloping-grasp control using tactile sensors for slippage detection has garnered significant attention in recent years. However, it remains an open problem in practical applications. This work proposes a data-driven slippage identification framework to address the challenge of enveloping-grasp control. The framework employs a tactile sensor array composed of micro-electro-mechanical barometers covered with soft material, which perceives contact behavior as spatiotemporal data. In the absence of detailed knowledge of interaction dynamics, the slippage information is estimated using a tactile learning model with convolutional computations. The slippage identification output is integrated into an enveloping-grasp controller to resist slippage. Compared to previous studies, our method is cost-effective and does not require large amounts of data or high computational power. Extensive experiments validate the effectiveness and generalization capability of the proposed framework, demonstrating that the slippage identification method exhibits high classification accuracy for grasp status of both known and unknown objects.

Details DOI

AAAI Conference 2026 Conference Paper

Learning 3D Occupancy from Beam Overlap in 2D Rotating mmWave Radar

Yu Du
Ruifeng Nie
Long Ma
Chengpei Xu
Yu Liu
Weimin Wang

Robust 3D perception under adverse weather is critical for autonomous systems. While mmWave Radars are inherently weather-resistant, conventional 2D rotating Radar sensors lack direct elevation resolution, limiting their 3D perception ability. Although 4D imaging radars can provide elevation information, they typically suffer from limited coverage and range. In this work, we exploit a key observation about mechanically rotating 2D mmWave Radars: in each sweep, an overlap exists between adjacent azimuth beam coverage due to the width of the main lobe, which makes the reflected intensity difference imply object materials and geometric shapes, including elevation. With this observation, we propose a method that learns 3D occupancy by disentangling bird’s-eye view (BEV) layout and elevation estimation from one frame Radar scan. Specifically, we partition one sweep into two interleaved subsets, corresponding to overlapping beam directions, and utilize them to infer coarse geometric structure through spatial differences and intensity patterns. Extensive quantitative and qualitative evaluations on two real-world datasets demonstrate that our proposed method outperforms existing baselines. The codes will be publicly available.

PDF Details DOI

EAAI Journal 2025 Journal Article

A fruit fly-inspired path planning algorithm for unmanned aerial vehicle in underground environments based on low-discrepancy sequences

Huageng Zhong
Yu Du
Dong Liu
Minghao Wang
Ming Cong
Xiaojing Tian

Sampling planning algorithms are crucial in high-dimensional path planning for unmanned aerial vehicle (UAV), particularly in underground environments where Global Positioning System (GPS) signals are absent. The Rapidly-exploring Random Tree (RRT) algorithm, however, faces challenges due to the use of pseudo-random sequences, resulting in issues such as under-sampling, over-sampling, and they also suffer from high computational costs and redundant paths. To address these limitations, the (Halton-based Clustering) HBC-RRT algorithm is proposed. This algorithm utilizes the Halton sequence, replacing the pseudo-random sequence, which fundamentally resolves the problems of under-sampling and over-sampling in the RRT method. Additionally, a novel sampler is introduced, inspired by the fruit fly guidance mechanism, which optimizes the dual-tree sampling process by selecting either the optimal sampling candidate strategy or virtual sub-goal points. The optimal sampling candidate strategy conducts global sampling in three-dimensional space, effectively reducing sampling time. The virtual sub-goal points accelerate the dual-tree connection process, enhancing the directional guidance. The fruit fly mechanism reconstructs the path, leading to a reduction in UAV path costs. The performance of the HBC-RRT algorithm is evaluated through simulation experiments, demonstrating superior results in comparison to four baseline algorithms, including reductions in path length, convergence time, and memory usage. The practical applicability of the algorithm is further validated through real-world experiments involving a UAV and radar in an underground environment.

Details DOI

EAAI Journal 2025 Journal Article

A human-robot interaction system for automated chemical experiments based on vision and natural language processing semantics

Zhuang Yang
Yu Du
Dong Liu
Kesong Zhao
Ming Cong

Using collaborative robots to replace researchers in performing repetitive and hazardous chemical experiments can effectively enhance experimental efficiency. However, this technology still faces several challenges, including understanding researchers' natural language instructions, autonomously generating action sequences, and more. Therefore, we developed a general control framework for robots in automated chemical experiments based on visual and natural language semantic information. Firstly, starting with the recognition of keywords within Chinese language instructions, we established a domain dictionary for chemical experiment operations and proposed an instruction understanding model based on the bidirectional long-short-term memory and conditional random field(BiLSTM-CRF), enhancing the robot's cognitive ability towards user instructions. Then, a rule matching method for chemical experimental information and a multimodal information feature matching mechanism were established for command content verification and the automatic generation of multiple types of structured language. At the same time, a robot feedback mechanism was added, enabling human-computer interaction and establishing closed-loop control of the system. Finally, propose a robot action sequence generation mechanism based on hierarchical finite state machines(HFSM), transforming structured language into operational strategies for chemical experiments required by the robot. Experimental results show that on the instruction task comprehension dataset created in this paper, the proposed method improves the F1 score by up to 4. 44% in the instruction keyword extraction task compared to other models. In addition, compared to traditional manual teaching control, this method significantly reduces time costs. This verifies that the method effectively enhances the robot's ability to comprehend Chinese instructions and generates reliable executable action sequences.

Details DOI

JBHI Journal 2025 Journal Article

Deep-Learning-Based Partial Volume Correction in 99m Tc-TRODAT-1 SPECT for Parkinson’s Disease: A Preliminary Study on Clinical Translation

Haiyan Wang
Bingjie Wang
Wenbo Huang
Yibin Liu
Yu Du
Guang-Uei Hung
Zhanli Hu
Greta S. P. Mok

99m Tc-TRODAT-1 SPECT is effective for the early detection of Parkinson’s disease (PD). However, SPECT images suffer from severe partial volume effect, which impairs tissue boundary clarity and subsequent quantification accuracy. This work proposes an anatomical prior- and segmentation-free deep learning (DL)-based partial volume correction (PVC) method using an attention-based conditional generative adversarial network (Att-cGAN) for 99m Tc-TRODAT-1 SPECT. A population of 454 digital brain phantoms modelling anatomical and 99m Tc-TRODAT activity variations in different PD categories are used to generate realistic SPECT projections using the SIMIND Monte Carlo code, and then reconstructed using ordered subset expectation maximization algorithm. The dataset is split into 320, 44 and 90 used for training, validation, and testing. Att-cGAN, cGAN and U-Net are implemented based on simulated data, then directly tested on 100 retrospectively collected clinical 99m Tc-TRODAT data, with same acquisition and reconstruction parameters as in simulations. Non-DL PVC methods of Van-Cittert and iterative Yang are implemented for comparison. Physical and clinical metrics, as well as a no-gold standard technique (NGST) are applied to evaluate different PVC methods in the absence of clinical ground truth. Att-cGAN yields superior PVC performance in simulations as compared to other methods in physical and clinical evaluations. NGST assessment is generally consistent with the clinical metric evaluation. For the clinical study, Att-cGAN also obtains better NGST result than others and 4 striatal compartments can be discriminated on DL-based processed images. DL-PVC method is feasible for clinical PD SPECT using highly realistic simulated data.

Details DOI

EAAI Journal 2025 Journal Article

Multi-agent reinforcement learning for vibration control of regenerative active suspension

Xiaotian Gao
Yu Du
Shiyuan Han
Wenxiu Zhao
Jin Zhou
Tong Zhang
C.L. Philip Chen

The comfort and responsiveness of active suspension systems have surpassed those of traditional suspension systems, but their development and implementation have been significantly constrained by high power requirements. In response to the current drive for energy conservation and emission reduction, regenerative active suspension systems effectively address the issues of high power consumption and energy loss while demonstrating considerable market potential. The main contribution of the investigation lies in designing a novel regenerative active suspension system specifically for electric vehicles powered by electric motors. The system integrates an electric motor and a generator to ensure precise power delivery and energy recovery from suspension dynamics. To fulfill the dual requirements of energy regeneration and ride smoothness, the Double Proximal Policy Optimization-Multi Dimensional Output (DPPO-MDO) algorithm has been devised based on multi-agent reinforcement learning. The algorithm features two agents equipped with the Proximal Policy Optimization (PPO) algorithm, each managing the operations of the motor and generator respectively. Furthermore, to accommodate diverse scenarios and balance comfort with energy efficiency, economic and comfort modes have been developed for the regenerative active suspension through the DPPO-MDO algorithm. Comprehensive experimental analysis demonstrates that both redesigned reward function and innovative reinforcement learning framework significantly enhance the application of multi-agent reinforcement learning in regenerative active suspension systems.

Details DOI

AIIM Journal 2025 Journal Article

TIPs: Tooth instance and pulp segmentation based on hierarchical extraction and fusion of anatomical priors from cone-beam CT

Tao Zhong
Yang Ning
Xueyang Wu
Li Ye
Chichi Li
Yu Zhang
Yu Du

Accurate instance segmentation of tooth and pulp from cone-beam computed tomography (CBCT) images is essential but highly challenging due to the pulp’s small structures and indistinct boundaries. To address these critical challenges, we propose TIPs designed for Tooth Instance and Pulp segmentation. TIPs initially employs a backbone model to segment a binary mask of the tooth from CBCT images, which is then utilized to derive position prior of the tooth and shape prior of the pulp. Subsequently, we propose the Hierarchical Fusion Mamba models to leverage the strengths of both anatomical priors and CBCT images by extracting and integrating shallow and deep features from Convolution Neural Networks (CNNs) and State Space Sequence Models (SSMs), respectively. This process achieves tooth instance and pulp segmentation, which are then combined to obtain the final pulp instance segmentation. Extensive experiments on CBCT scans from 147 patients demonstrate that TIPs significantly outperforms state-of-the-art methods in terms of segmentation accuracy. Furthermore, we have encapsulated this framework into an openly accessible tool for one-click using. To our knowledge, this is the first toolbox capable of segmentation of tooth and pulp instances, with its performance validated on two external datasets comprising 59 samples from the Toothfairy2 dataset and 48 samples from the STS dataset. These results demonstrate the potential of TIPs as a practical tool to boost clinical workflows in digital dentistry, enhancing the precision and efficiency of dental diagnostics and treatment planning.

Details DOI

EAAI Journal 2024 Journal Article

HB-RRT:A path planning algorithm for mobile robots using Halton sequence-based rapidly-exploring random tree

Huageng Zhong
Ming Cong
Minghao Wang
Yu Du
Dong Liu

Path planning remains crucial for efficient robot operation. A Halton Biased Rapidly-exploring Random Tree (HB-RRT) path planning algorithm is introduced in this study. The Halton sequence, known for its uniform distribution and low discrepancy, is employed for sampling. Issues arising from the pseudo-random sequence in the standard RRT algorithm, leading to uneven distribution of sampling points, are addressed. A mouse-inspired goal-oriented strategy and a candidate sampling pool strategy are incorporated to enhance the sampling point quality, thereby addressing the challenge of insufficient memory during node expansion. Path optimization is further achieved through a multi-level planning approach, which aims to minimize redundancy. A subsequent smoothing of the path is conducted using a cubic B-spline method. Comparisons with the RRT, Bionic Target Bias-RRT, and Informed-RRT* algorithms, through both numerical simulations and real-world testing, confirm the superiority of the HB-RRT algorithm in terms of planning time, path length, and overall path quality.

Details DOI

ICML Conference 2024 Conference Paper

Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments

Runfa Chen
Ling Wang
Yu Du
Tianrui Xue
Fuchun Sun 0001
Jianwei Zhang 0001
Wenbing Huang 0001

Learning policies for multi-entity systems in 3D environments is far more complicated against single-entity scenarios, due to the exponential expansion of the global state space as the number of entities increases. One potential solution of alleviating the exponential complexity is dividing the global space into independent local views that are invariant to transformations including translations and rotations. To this end, this paper proposes Subequivariant Hierarchical Neural Networks (SHNN) to facilitate multi-entity policy learning. In particular, SHNN first dynamically decouples the global space into local entity-level graphs via task assignment. Second, it leverages subequivariant message passing over the local entity-level graphs to devise local reference frames, remarkably compressing the representation redundancy, particularly in gravity-affected environments. Furthermore, to overcome the limitations of existing benchmarks in capturing the subtleties of multi-entity systems under the Euclidean symmetry, we propose the Multi-entity Benchmark (MEBEN), a new suite of environments tailored for exploring a wide range of multi-entity reinforcement learning. Extensive experiments demonstrate significant advancements of SHNN on the proposed benchmarks compared to existing methods. Comprehensive ablations are conducted to verify the indispensability of task assignment and subequivariance.

Details

AAAI Conference 2023 Conference Paper

Coupling Artificial Neurons in BERT and Biological Neurons in the Human Brain

Xu Liu
Mengyue Zhou
Gaosheng Shi
Yu Du
Lin Zhao
Zihao Wu
David Liu
Tianming Liu

Linking computational natural language processing (NLP) models and neural responses to language in the human brain on the one hand facilitates the effort towards disentangling the neural representations underpinning language perception, on the other hand provides neurolinguistics evidence to evaluate and improve NLP models. Mappings of an NLP model’s representations of and the brain activities evoked by linguistic input are typically deployed to reveal this symbiosis. However, two critical problems limit its advancement: 1) The model’s representations (artificial neurons, ANs) rely on layer-level embeddings and thus lack fine-granularity; 2) The brain activities (biological neurons, BNs) are limited to neural recordings of isolated cortical unit (i.e., voxel/region) and thus lack integrations and interactions among brain functions. To address those problems, in this study, we 1) define ANs with fine-granularity in transformer-based NLP models (BERT in this study) and measure their temporal activations to input text sequences; 2) define BNs as functional brain networks (FBNs) extracted from functional magnetic resonance imaging (fMRI) data to capture functional interactions in the brain; 3) couple ANs and BNs by maximizing the synchronization of their temporal activations. Our experimental results demonstrate 1) The activations of ANs and BNs are significantly synchronized; 2) the ANs carry meaningful linguistic/semantic information and anchor to their BN signatures; 3) the anchored BNs are interpretable in a neurolinguistic context. Overall, our study introduces a novel, general, and effective framework to link transformer-based NLP models and neural activities in response to language and may provide novel insights for future studies such as brain-inspired evaluation and development of NLP models.

PDF Details DOI

ICML Conference 2022 Conference Paper

HyperPrompt: Prompt-based Task-Conditioning of Transformers

Yun He
Huaixiu Steven Zheng
Yi Tay
Jai Prakash Gupta 0001
Yu Du
Vamsi Aribandi
Zhe Zhao 0001
YaGuang Li

Prompt-Tuning is a new paradigm for finetuning pre-trained language models in a parameter efficient way. Here, we explore the use of HyperNetworks to generate hyper-prompts: we propose HyperPrompt, a novel architecture for prompt-based task-conditioning of self-attention in Transformers. The hyper-prompts are end-to-end learnable via generation by a HyperNetwork. HyperPrompt allows the network to learn task-specific feature maps where the hyper-prompts serve as task global memories for the queries to attend to, at the same time enabling flexible information sharing among tasks. We show that HyperPrompt is competitive against strong multi-task learning baselines with as few as 0. 14% of additional task-conditioning parameters, achieving great parameter and computational efficiency. Through extensive empirical experiments, we demonstrate that HyperPrompt can achieve superior performances over strong T5 multi-task learning baselines and parameter-efficient adapter variants including Prompt-Tuning and HyperFormer++ on Natural Language Understanding benchmarks of GLUE and SuperGLUE across many model sizes.

Details

IJCAI Conference 2017 Conference Paper

Semi-Supervised Learning for Surface EMG-based Gesture Recognition

Yu Du
Yongkang Wong
Wenguang Jin
Wentao Wei
Yu Hu
Mohan Kankanhalli
Weidong Geng

Conventionally, gesture recognition based on non-intrusive muscle-computer interfaces required a strongly-supervised learning algorithm and a large amount of labeled training signals of surface electromyography (sEMG). In this work, we show that temporal relationship of sEMG signals and data glove provides implicit supervisory signal for learning the gesture recognition model. To demonstrate this, we present a semi-supervised learning framework with a novel Siamese architecture for sEMG-based gesture recognition. Specifically, we employ auxiliary tasks to learn visual representation; predicting the temporal order of two consecutive sEMG frames; and, optionally, predicting the statistics of 3D hand pose with a sEMG frame. Experiments on the NinaPro, CapgMyo and csl-hdemg datasets validate the efficacy of our proposed approach, especially when the labeled samples are very scarce.

PDF Details