38 accepted papers
Robotic grippers aim to replicate the remarkable functionalities of the human hand by providing advanced perception, adaptability, stability, and dexterity for complex tasks. Achieving these capabilities demands a sophisticated design hierarchy and robust perception mechanisms that ensure accurate m…
Natural videos exhibit heterogeneous temporal dynamics, with certain segments undergoing high-dynamic scene transitions and others dominated by low-dynamic visual changes. However, treating all frames identically, a common practice in most MLLMs, leads to redundant visual encoding, which results in
Group Relative Policy Optimization (GRPO) has significantly enhanced the reasoning capability of large language models by optimizing the arithmetic mean of token-level rewards. Unfortunately, GRPO is observed to suffer from unstable policy updates when facing tokens with outlier importance-weighted…
Addressing the critical trade-off between compliance and grasping force in underwater manipulation, this letter presents a novel topology optimization framework to automate the design of soft, variable-stiffness fingers from a single material. By employing multiple load cases within the optimization
We introduce asRoBallet, to the best of our knowledge, the first successful deployment of reinforcement learning (RL) on a humanoid ballbot hardware. Historically, ballbots have served as a canonical benchmark for underactuated and nonholonomic control, which are characterized by a reality gap in co…
Robotic grippers aim to replicate the remarkable functionalities of the human hand by providing advanced perception, adaptability, stability, and dexterity for complex tasks. Achieving these capabilities demands a sophisticated design hierarchy and robust perception mechanisms that ensure accurate m
One important task of multimodal models is to translate referred image regions to human preferred language descriptions. Existing methods, however, ignore the resolution adaptability needs of different tasks, which hinders them to find out precise language descriptions. In this study, we propose a D…
Deep learning has become essential in the biological species recognition task. However, a significant challenge is the ability to continuously learn new or mutated species with limited annotated samples. Since species within the same family typically share similar traits, distinguishing between new…
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 models by caching and reusing model outputs at uniformly selected timesteps.However, such a strategy neglects the fact that d…
Despite the substantial progress in deep learning, its adoption in industrial robotics projects remains limited, primarily due to challenges in data acquisition and labeling. Previous sim2real approaches using domain randomization require extensive scene and model optimization. To address these issu…
Comprehensive and constructive evaluation protocols play an important role when developing sophisticated text-to-video (T2V) generation models. Existing evaluation protocols primarily focus on temporal consistency and content continuity, yet largely ignore dynamics of video content. Such dynamics is…
"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 detections. Our paper presents Ray Denoising, an innovative method that enhances detection accuracy by strategically sa…
Pointly supervised instance segmentation (PSIS) learns to segment objects using a single point within the object extent as supervision. Challenged by the non-negligible semantic variance between object parts, however, the single supervision point causes semantic bias and false segmentation. In this…
Weakly supervised object localization (WSOL) remains challenging when learning object localization models from image category labels. Conventional methods that discriminatively train activation models ignore representative yet less discriminative object parts. In this study, we propose a generative…
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 detector head and the feature pyramid network (FPN) remain trained from scratch, which hinders the generalization capaci…
"Conventional methods for weakly supervised object detection (WSOD) typically enumerate dense proposals and select the discriminative proposals as objects. However, these two-stage “enumerate-and-select” methods suffer object feature ambiguity brought by dense proposals and low detection efficiency…
In active learning, the ignorance of aligning unlabeled samples' distribution with that of labeled samples hinders the model trained upon labeled samples from selecting informative unlabeled samples. In this paper, we propose an agreement-discrepancy-selection (ADS) approach, and target at unifying…
Planar mechanisms dominate modern designs of legged robots with remote actuator placement for robust agility in ground mobility. This paper presents a novel design of robotic leg modules using the Bennett linkage, driven by two coaxially arranged quasi-direct actuators capable of omnidirectional gro…
This letter presents a novel design of a soft tactile finger with omni-directional adaptation using multi-channel optical fibers for rigid-soft interactive grasping. Machine learning methods are used to train a model for real-time prediction of force, torque, and contact using the tactile data colle
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, we propose Multiple Instance Active Object Detection (MI-AOD), to select the most informative images for detector train…
Deep neural networks (DNNs) have been widely applied to active learning. Despite of its effectiveness, the generalization ability of the discriminative classifier (the softmax classifier) is questionable when there is a significant distribution bias between the labeled set and the unlabeled set. In…
Weakly supervised object localization (WSOL) aims at learning to localize objects of interest by only using the image-level labels as the supervision. While numerous efforts have been made in this field, recent approaches still suffer from two challenges: one is the part domination issue while the o…
Weakly supervised object localization (WSOL) is a challenging problem when given image category labels but requires to learn object localization models. Optimizing a convolutional neural network (CNN) for classification tends to activate local discriminative regions while ignoring complete object ex…
This paper explores the feasibility of learning robot force control and interaction using soft metamaterial and machine vision. We start by investigating the differential stiffness of a hollow, cone-shaped, 3D metamaterial made from soft rubber, achieving a large stiffness ratio between the axial an…
Soft robots often show a superior power-to-weight ratio using highly compliant, light-weight material, which leverages various bio-inspired body designs to generate desirable deformations for life-like motions. In this letter, given that most material used for soft robots is light-weight in general,
For high-level human-robot interaction tasks, 3D scene understanding is important and non-trivial for autonomous robots. However, parsing and utilizing effective environment information of the 3D scene is not trivial due to the complexity of the 3D environment and the limited ability for reasoning a…
The engineering design of robotic grippers presents an ample design space for optimization towards robust grasping. In this letter, we investigate how learning method can be used to support the design reconfiguration of robotic grippers for grasping using a novel soft structure with omni-directional
Robot learning is widely accepted by academia and industry with its potentials to transform autonomous robot control through machine learning. 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
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 Multiple Instance Learning (MIL) framework, where a bag (video) contains multiple instances (action segments). Since only the b…
Weakly supervised object detection (WSOD) that only needs image-level annotations has obtained much attention recently. By combining convolutional neural network with multiple instance learning method, Multiple Instance Detection Network (MIDN) has become the most popular method to address the WSOD…
Weakly supervised object detection (WSOD) is a challenging task when provided with image category supervision but required to simultaneously learn object locations and object detectors. Many WSOD approaches adopt multiple instance learning (MIL) and have non-convex loss functions which are prone to…
Weakly supervised object localization remains a challenge when learning object localization models from image category labels. Optimizing image classification tends to activate object parts and ignore the full object extent, while expanding object parts into full object extent could deteriorate the…
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-to-match approach to break IoU restriction, allowing objects to match anchors in a flexible manner. Our approach, referr…
The weight sharing scheme and spatial pooling operations in Convolutional Neural Networks (CNNs) introduce semantic correlation to neighboring pixels on feature maps and therefore deteriorate their pixel-wise classification performance. In this paper, we implement an Orthogonal Decomposition Unit (O…
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 1,059,231 X-ray images, in which 6 classes of 8,929 prohibited items are manually annotated. It raises a brand new challe…
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 detectors. The inconsistency between the weak supervision and learning objectives introduces randomness to object locations and…
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 soft components for actuation. Inspired by the bending abdomen of lobsters, hybrid actuators are built with serially jointe…
Classical rigid-bodied robotic systems are presented with proven success in theoretical development and industrial applications, are recently challenged by the emergence of soft robotics due to a growing need in physical human-robot interactions (pHRI), such as wearable devices, medical robots, pers…