Publications (54)
asRoBallet: Closing the Sim2Real Gap via Friction-Aware Reinforcement Learning for Underactuated Spherical Dynamics
Fang Wan, Guangyi Huang, Tianyu Wu +5
We introduce asRoBallet, to the best of our knowledge, the first end-to-end reinforcement learning (RL) locomotion policy deployed on a humanoid ballbot hardware platform. Historic…
Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection
Feng Liu, Xiaosong Zhang, Zhiliang Peng +4
Modern object detectors have taken the advantages of backbone networks pre-trained on large scale datasets. Except for the backbone networks, however, other components such as the…
A Dataset and Benchmark for Robotic Cloth Unfolding Grasp Selection: The ICRA 2024 Cloth Competition
Victor-Louis De Gusseme, Thomas Lips, Remko Proesmans +59
Robotic cloth manipulation suffers from a lack of standardized benchmarks and shared datasets for evaluating and comparing different approaches. To address this, we created a bench…
Utilizing the Instability in Weakly Supervised Object Detection
Yan Gao, Boxiao Liu, Nan Guo +4
Weakly supervised object detection (WSOD) focuses on training object detector with only image-level annotations, and is challenging due to the gap between the supervision and the o…
Design of an Optoelectronically Innervated Gripper for Rigid-Soft Interactive Grasping
Linhan Yang, Xudong Han, Weijie Guo +4
Over the past few decades, efforts have been made towards robust robotic grasping, and therefore dexterous manipulation. The soft gripper has shown their potential in robust graspi…
Utilising high-dimensional data in randomised clinical trials: a review of methods and practice
Svetlana Cherlin, Theophile Bigirumurame, Michael J Grayling +6
Introduction: Even in effectively conducted randomised trials, the probability of a successful study remains relatively low. With recent advances in the next-generation sequencing…
Underwater Intention Recognition using Head Motion and Throat Vibration for Supernumerary Robotic Assistance
Yuqin Guo, Rongzheng Zhang, Wanghongjie Qiu +3
This study presents a multi-modal mechanism for recognizing human intentions while diving underwater, aiming to achieve natural human-robot interactions through an underwater super…
Hybrid Actuator Design for a Gait Augmentation Wearable
Fang Wan, Zheng Wang, Brooke Franchuk +3
We describe a fluidic actuator design that replaces the sealed chamber of a hydraulic cylinder using a soft actuator to provide compliant linear compression with a large force ($\g…
MagiClaw: A Dual-Use, Vision-Based Soft Gripper for Bridging the Human Demonstration to Robotic Deployment Gap
Tianyu Wu, Xudong Han, Haoran Sun +4
The transfer of manipulation skills from human demonstration to robotic execution is often hindered by a "domain gap" in sensing and morphology. This paper introduces MagiClaw, a v…
Jigsaw-based Benchmarking for Learning Robotic Manipulation
Xiaobo Liu, Fang Wan, Sheng Ge +3
Benchmarking provides experimental evidence of the scientific baseline to enhance the progression of fundamental research, which is also applicable to robotics. In this paper, we p…
Evolutionary Morphology Towards Overconstrained Locomotion via Large-Scale, Multi-Terrain Deep Reinforcement Learning
Yenan Chen, Chuye Zhang, Pengxi Gu +10
While the animals' Fin-to-Limb evolution has been well-researched in biology, such morphological transformation remains under-adopted in the modern design of advanced robotic limbs…
One-DoF Robotic Design of Overconstrained Limbs with Energy-Efficient, Self-Collision-Free Motion
Yuping Gu, Bangchao Huang, Haoran Sun +6
While it is expected to build robotic limbs with multiple degrees of freedom (DoF) inspired by nature, a single DoF design remains fundamental, providing benefits that include, but…
Multiple instance active learning for object detection
Tianning Yuan, Fang Wan, Mengying Fu +4
Despite the substantial progress of active learning for image recognition, there still lacks an instance-level active learning method specified for object detection. In this paper,…
Learning-based Optoelectronically Innervated Tactile Finger for Rigid-Soft Interactive Grasping
Linhan Yang, Xudong Han, Weijie Guo +3
This paper presents a novel design of a soft tactile finger with omni-directional adaptation using multi-channel optical fibers for rigid-soft interactive grasping. Machine learnin…
Vorch-Omni: Multi-Task Orchestration of Sight and Sound
Vorch Team, Xiaoyu Chen, Yang Ding +25
Recent advances in generative video modeling have enabled diverse generation, reference-based synthesis, extension, and editing, but existing approaches often rely on fragmented ta…
Logical Learning Through a Hybrid Neural Network with Auxiliary Inputs
Fang Wan, Chaoyang Song
The human reasoning process is seldom a one-way process from an input leading to an output. Instead, it often involves a systematic deduction by ruling out other possible outcomes…
Min-Entropy Latent Model for Weakly Supervised Object Detection
Fang Wan, Pengxu Wei, Zhenjun Han +2
Weakly supervised object detection is a challenging task when provided with image category supervision but required to learn, at the same time, object locations and object detector…
SIXray : A Large-scale Security Inspection X-ray Benchmark for Prohibited Item Discovery in Overlapping Images
Caijing Miao, Lingxi Xie, Fang Wan +4
In this paper, we present a large-scale dataset and establish a baseline for prohibited item discovery in Security Inspection X-ray images. Our dataset, named SIXray, consists of 1…
Data-driven controlled subgroup selection in clinical trials
Manuel M. Müller, Björn Bornkamp, Frank Bretz +7
Subgroup selection in clinical trials is essential for identifying patient groups that react differently to a treatment, thereby enabling personalised medicine. In particular, subg…
Robotic Cane as a Soft SuperLimb for Elderly Sit-to-Stand Assistance
Xia Wu, Haiyuan Liu, Ziqi Liu +6
Many researchers have identified robotics as a potential solution to the aging population faced by many developed and developing countries. If so, how should we address the cogniti…
Can Data-Driven Dynamics Reveal Hidden Physics? There Is A Need for Interpretable Neural Operators
Wenhan Gao, Jian Luo, Fang Wan +4
Recently, neural operators have emerged as powerful tools for learning mappings between function spaces, enabling data-driven simulations of complex dynamics. Despite their success…
Active Surface with Passive Omni-Directional Adaptation of Soft Polyhedral Fingers for In-Hand Manipulation
Sen Li, Fang Wan, Chaoyang Song
Track systems effectively distribute loads, augmenting traction and maneuverability on unstable terrains, leveraging their expansive contact areas. This tracked locomotion capabili…
Rigid-Soft Interactive Learning for Robust Grasping
Linhan Yang, Fang Wan, Haokun Wang +4
Inspired by widely used soft fingers on grasping, we propose a method of rigid-soft interactive learning, aiming at reducing the time of data collection. In this paper, we classify…
Proprioceptive Learning with Soft Polyhedral Networks
Xiaobo Liu, Xudong Han, Wei Hong +2
Proprioception is the "sixth sense" that detects limb postures with motor neurons. It requires a natural integration between the musculoskeletal systems and sensory receptors, whic…
Confidence Sets for a level set in linear regression
Fang Wan, Wei Liu, Frank Bretz
Regression modeling is the workhorse of statistics and there is a vast literature on estimation of the regression function. It is realized in recent years that in regression analys…
Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection
Feng Liu, Tengteng Huang, Qianjing Zhang +5
Multi-view 3D object detection systems often struggle with generating precise predictions due to the challenges in estimating depth from images, increasing redundant and incorrect…
One Fling to Goal: Environment-aware Dynamics for Goal-conditioned Fabric Flinging
Linhan Yang, Lei Yang, Haoran Sun +5
Fabric manipulation dynamically is commonly seen in manufacturing and domestic settings. While dynamically manipulating a fabric piece to reach a target state is highly efficient,…
Geometric-Mean Policy Optimization
Yuzhong Zhao, Yue Liu, Junpeng Liu +9
Group Relative Policy Optimization (GRPO) has significantly enhanced the reasoning capability of large language models by optimizing the arithmetic mean of token-level rewards. Unf…
Proprioceptive State Estimation for Amphibious Tactile Sensing
Ning Guo, Xudong Han, Shuqiao Zhong +5
This paper presents a novel vision-based proprioception approach for a soft robotic finger that can estimate and reconstruct tactile interactions in both terrestrial and aquatic en…
Reconfigurable Design for Omni-adaptive Grasp Learning
Fang Wan, Haokun Wang, Jiyuan Wu +3
The engineering design of robotic grippers presents an ample design space for optimization towards robust grasping. In this paper, we adopt the reconfigurable design of the robotic…
DeepClaw: A Robotic Hardware Benchmarking Platform for Learning Object Manipulation
Fang Wan, Haokun Wang, Xiaobo Liu +2
We present DeepClaw as a reconfigurable benchmark of robotic hardware and task hierarchy for robot learning. The DeepClaw benchmark aims at a mechatronics perspective of the robot…
Autoencoding a Soft Touch to Learn Grasping from On-land to Underwater
Ning Guo, Xudong Han, Xiaobo Liu +6
Robots play a critical role as the physical agent of human operators in exploring the ocean. However, it remains challenging to grasp objects reliably while fully submerging under…
DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution
Yuzhong Zhao, Feng Liu, Yue Liu +4
One fundamental task of multimodal models is to translate referred image regions to human preferred language descriptions. Existing methods, however, ignore the resolution adaptabi…
Thinking with Images via Self-Calling Agent
Wenxi Yang, Yuzhong Zhao, Fang Wan +1
Thinking-with-images paradigms have showcased remarkable visual reasoning capability by integrating visual information as dynamic elements into the Chain-of-Thought (CoT). However,…
TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization
Wei Gao, Fang Wan, Xingjia Pan +5
Weakly supervised object localization (WSOL) is a challenging problem when given image category labels but requires to learn object localization models. Optimizing a convolutional…
A Lobster-inspired Robotic Glove for Hand Rehabilitation
Yaohui Chen, Sing Le, Qiao Chu Tan +3
This paper presents preliminary results of the design, development, and evaluation of a hand rehabilitation glove fabricated using lobster-inspired hybrid design with rigid and sof…
Close the Sim2real Gap via Physically-based Structured Light Synthetic Data Simulation
Kaixin Bai, Lei Zhang, Zhaopeng Chen +2
Despite the substantial progress in deep learning, its adoption in industrial robotics projects remains limited, primarily due to challenges in data acquisition and labeling. Previ…
Scalable Tactile Sensing for an Omni-adaptive Soft Robot Finger
Zeyi Yang, Sheng Ge, Fang Wan +2
Robotic fingers made of soft material and compliant structures usually lead to superior adaptation when interacting with the unstructured physical environment. In this paper, we pr…
A Reconfigurable Hybrid Actuator with Rigid and Soft Components
Yaohui Chen, Sing Le, Qiao Chu Tan +3
Classical rigid-bodied robotic systems are presented with proven success in theoretical development and industrial applications, are recently challenged by the emergence of soft ro…
Uncertainty-Calibrated Diffusion for Reliable 3D Molecular Graph Generation
Fang Wan, Jingxiang Qu, Yi Liu
Bayesian inference provides a principled framework for modeling epistemic uncertainty in neural networks by treating predictions as distributions rather than deterministic values.…
On Flange-based 3D Hand-Eye Calibration for Soft Robotic Tactile Welding
Xudong Han, Ning Guo, Yu Jie +3
This paper investigates the direct application of standardized designs on the robot for conducting robot hand-eye calibration by employing 3D scanners with collaborative robots. Th…
Generative Prompt Model for Weakly Supervised Object Localization
Yuzhong Zhao, Qixiang Ye, Weijia Wu +2
Weakly supervised object localization (WSOL) remains challenging when learning object localization models from image category labels. Conventional methods that discriminatively tra…
Describing Robots from Design to Learning: Towards an Interactive Lifecycle Representation of Robots
Nuofan Qiu, Fang Wan, Chaoyang Song
The robot development process is divided into several stages, which create barriers to the exchange of information between these different stages. We advocate for an interactive li…
Overconstrained Locomotion
Haoran Sun, Bangchao Huang, Zishang Zhang +11
This paper studies the design, control, and learning of a novel robotic limb that produces overconstrained locomotion by employing the Bennett linkage for motion generation, capabl…
ControlCap: Controllable Region-level Captioning
Yuzhong Zhao, Yue Liu, Zonghao Guo +4
Region-level captioning is challenged by the caption degeneration issue, which refers to that pre-trained multimodal models tend to predict the most frequent captions but miss the…
Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning
Zhekun Luo, Devin Guillory, Baifeng Shi +4
Weakly-supervised action localization requires training a model to localize the action segments in the video given only video level action label. It can be solved under the Multipl…
Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
Feng Liu, Shiwei Zhang, Xiaofeng Wang +6
As a fundamental backbone for video generation, diffusion models are challenged by low inference speed due to the sequential nature of denoising. Previous methods speed up the mode…
Correspondence-Guided SfM-Free 3D Gaussian Splatting for NVS
Wei Sun, Xiaosong Zhang, Fang Wan +4
Novel View Synthesis (NVS) without Structure-from-Motion (SfM) pre-processed camera poses--referred to as SfM-free methods--is crucial for promoting rapid response capabilities and…
Domain Contrast for Domain Adaptive Object Detection
Feng Liu, Xiaoxong Zhang, Fang Wan +2
We present Domain Contrast (DC), a simple yet effective approach inspired by contrastive learning for training domain adaptive detectors. DC is deduced from the error bound minimiz…
Multi-Layered Reasoning from a Single Viewpoint for Learning See-Through Grasping
Fang Wan, Chaoyang Song
Sensory substitution enables biological systems to perceive stimuli that are typically perceived by another organ, which is inspirational for physical agents. Multimodal perception…
Evaluation of Text-to-Video Generation Models: A Dynamics Perspective
Mingxiang Liao, Hannan Lu, Xinyu Zhang +6
Comprehensive and constructive evaluation protocols play an important role in the development of sophisticated text-to-video (T2V) generation models. Existing evaluation protocols…
Subgroup analysis of treatment effects for misclassified biomarkers with time-to-event data
Fang Wan, Andrew C. Titman, Thomas F. Jaki
Analysing subgroups defined by biomarkers is of increasing importance in clinical research. In some situations the biomarker is subject to misclassification error, meaning the true…
FreeAnchor: Learning to Match Anchors for Visual Object Detection
Xiaosong Zhang, Fang Wan, Chang Liu +2
Modern CNN-based object detectors assign anchors for ground-truth objects under the restriction of object-anchor Intersection-over-Unit (IoU). In this study, we propose a learning-…
C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection
Fang Wan, Chang Liu, Wei Ke +3
Weakly supervised object detection (WSOD) is a challenging task when provided with image category supervision but required to simultaneously learn object locations and object detec…