107 accepted papers
Expressive generative models have recently shown promise in offline reinforcement learning (RL) by capturing the complex, multimodal structure of dataset behavior. However, directly integrating these models into policy optimization introduces substantial computational and stability challenges due to
Iterative generative policies, such as diffusion models and flow matching, offer superior expressivity for continuous control but complicate Maximum Entropy Reinforcement Learning because their action log-densities are not directly accessible. To address this, we propose \textbf{Field Least-Energy A…
Diffusion policies are powerful visuomotor models for robotic manipulation, yet they often fail to generalize to manipulators or end-effectors unseen during training and struggle to accommodate new task requirements at inference time. Addressing this typically requires costly data recollection and p…
Standard on-policy reinforcement learning relies on heuristic clipping to enforce trust regions, but this mechanism imposes a severe cost by indiscriminately truncating high-return yet high-divergence updates. We demonstrate that explicitly constraining the *policy ratio **variance*** provides a pri…
We introduce SceneTransporter, an end-to-end framework for structured 3D scene generation from a single image. While existing methods generate part-level 3D objects, they often fail to organize these parts into distinct instances in open-world scenes. Through a debiased clustering probe, we reveal a…
Vision-Language-Action models (VLAs) achieve remarkable performance in sequential decision-making but remain fragile to subtle environmental shifts, such as small changes in object pose. We attribute this brittleness to trajectory overfitting, where VLAs over-attend to the spurious correlation betwe
This paper presents a novel multi-mode bionic robotic hand. Its bionic finger (BIF) ingeniously combines a magnetic-silica-gel skin with a rigid skeletal framework and integrates a vacuum suction cup at the fingertip. This design enables the bionic manipulator to execute multiple grasping modes, nam
Humans exhibit diverse and expressive whole-body movements. However, attaining human-like whole-body coordination in humanoid robots remains challenging, as conventional approaches that mimic whole-body motions often neglect the distinct roles of upper and lower body. This oversight leads to computa…
Mobile manipulation typically entails the base for mobility, the arm for accurate manipulation, and the camera for perception. The principle of Distant Mobility, Close Grasping(DMCG) is essential for holistic control. We propose Embod-ied Holistic Control for Mobile Manipulation(EHC-MM) with the emb
Small-scale autonomous aerial vehicles (AAVs) are widely used in various fields. However, their underactuated design limits their ability to perform complex tasks that require physical interaction with environments. The fully-actuated Integrated Aerial Platforms (IAPs), where multiple AAVs are conne
Reinforcement learning (RL) has shown promising performance in tackling robotic manipulation tasks (RMTs), which require learning a prolonged sequence of manipulation actions to control robots efficiently. However, most RL algorithms often suffer from two problems when solving RMTs: inefficient expl…
We present $\textbf{FlowRL}$, a novel framework for online reinforcement learning that integrates flow-based policy representation with Wasserstein-2-regularized optimization. We argue that in addition to training signals, enhancing the expressiveness of the policy class is crucial for the performan…
Soft robots, compared to regular rigid robots, as their multiple segments with soft materials bring flexibility and compliance, have the advantages of safe interaction and dexterous operation in the environment. However, due to its characteristics of high dimensional, nonlinearity, time-varying natu
Temporal sequences, even after stationarization, often exhibit leptokurtic distributions with fat tails and persistent distribution shifts. These properties destabilize feature dynamics, amplify model variance, and hinder model convergence in time series forecasting. To address this, we propose Morp…
In low-light, unstructured, and confined environments, performing Simultaneous Localization and Mapping (SLAM) with conventional methods presents significant challenges. Soft growing robots, characterized by their compliance and extensibility, interact safely with the environment, making them well-s
Multi-Modal Learning (MML) aims to learn effective representations across modalities for accurate predictions. Existing methods typically focus on modality consistency and specificity to learn effective representations. However, from a causal perspective, they may lead to representations that contai…
The varying significance of distinct primitive behaviors during the policy learning process has been overlooked by prior model-free RL algorithms. Leveraging this insight, we explore the causal relationship between different action dimensions and rewards to evaluate the significance of various primi…
As a novel and effective fine-tuning paradigm based on large-scale pre-trained language models (PLMs), prompt-tuning aims to reduce the gap between downstream tasks and pre-training objectives. While prompt-tuning has yielded continuous advancements in various tasks, such an approach still remains a…
This paper presents a novel Bionic Soft Finger (BSF) that aims to overcome the limitations of conventional rigid manipulators in terms of adaptability and safety, as well as the challenges faced by soft hands regarding carrying capacity and stability. The BSF design uses a hybrid variable stiffness…
Graph contrastive learning (GCL) aims to align the positive features while differentiating the negative features in the latent space by minimizing a pair-wise contrastive loss. As the embodiment of an outstanding discriminative unsupervised graph representation learning approach, GCL achieves impres…
This paper presents a 6-DOF hybrid robot for percutaneous needle intervention procedures. The new robot combines the advantages of both serial robots and parallel robots, featuring compactness, high accuracy, and small footprint while overcoming the problems of the high cost of serial robots and the…
Recent research has made significant progress in designing fusion modules for audio-visual speech separation. However, they predominantly focus on multi-modal fusion at a single temporal scale of auditory and visual features without employing selective attention mechanisms, which is in sharp contras…
Visual odometry is one of the key technologies for unmanned ground vehicles. To improve the robustness of the systems and enable intelligent tasks, researchers introduced learning-based recognition modules into visual odometry systems, but didn't realize tight coupling between visual odometry system
In this paper, we introduce PADUAV, a novel 5-DOF aerial platform designed to overcome the limitations of traditional tiltrotor vehicles. PADUAV features a unique mechanical design that incorporates two off-the-shelf quadrotors passively articulated to a rigid frame. This innovation enables free pit…
Training reinforcement learning policies using environment interaction data collected from varying policies or dynamics presents a fundamental challenge. Existing works often overlook the distribution discrepancies induced by policy or dynamics shifts, or rely on specialized algorithms with task pri…
Off-policy reinforcement learning (RL) has achieved notable success in tackling many complex real-world tasks, by leveraging previously collected data for policy learning. However, most existing off-policy RL algorithms fail to maximally exploit the information in the replay buffer, limiting sample…
Marine radar is employed across multiple fields, notably in navigation, meteorology, defense, and security. Marine radar images are highly sensitive to sea clutter, highlighting the crucial importance of sea clutter suppression in radar image processing. However, existing algorithms for sea clutter…
We present RobotGPT, an innovative decision framework for robotic manipulation that prioritizes stability and safety. The execution code generated by ChatGPT cannot guarantee the stability and safety of the system. ChatGPT may provide different answers for the same task, leading to unpredictability.
Learning high-quality $Q$-value functions plays a key role in the success of many modern off-policy deep reinforcement learning (RL) algorithms. Previous works primarily focus on addressing the value overestimation issue, an outcome of adopting function approximators and off-policy learning. Deviati…
Data-free knowledge distillation is able to utilize the knowledge learned by a large teacher network to augment the training of a smaller student network without accessing the original training data avoiding privacy security and proprietary risks in real applications. In this line of research existi…
Model Predictive Control (MPC) has exhibited remarkable capabilities in optimizing objectives and meeting constraints. However, the substantial computational burden associated with solving the Optimal Control Problem (OCP) at each triggering instant introduces significant delays between state sampli…
Drawing inspiration from human fine tactile and proprioceptive kinaesthetic sensing pathways, we propose a soft magnetic skin (m-skin) with multimodal sensing functions integrated into the anthropomorphic robotic finger. This paper mainly explores the magnetic tactile sensor's structural design, per
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 glob…
Integrated aerial Platforms (IAPs), comprising multiple aircrafts, are typically fully actuated and hold significant potential for aerial manipulation tasks. Differing from a multiple aerial swarm, the aircrafts within the IAP are interconnected, presenting promising opportunities for enhancing loca…
Video generative models are receiving particular attention given their ability to generate realistic and imaginative frames. Besides, these models are also observed to exhibit strong 3D consistency, significantly enhancing their potential to act as world simulators. In this work, we present Vidu4D,…
Obtaining high-density tactile field information is a critical aspect of research in the field of robotic haptics, as it plays a decisive role in determining the precision of robot manipulations. Vision-based tactile sensors have unique high-resolution features, which make them promising for related…
Binocular depth estimation is a fundamental problem in computer vision. Learning-based models have achieved significant performance improvements on public datasets in recent years. Our study finds that the performance of the current state-of-the-art deep learning-based models deteriorates significan…
Binary Neural Network (BNN) represents convolution weights with 1-bit values, which enhances the efficiency of storage and computation. This paper is motivated by a previously revealed phenomenon that the binary kernels in successful BNNs are nearly power-law distributed: their values are mostly clu…
Few-shot learning models learn representations with limited human annotations, and such a learning paradigm demonstrates practicability in various tasks, e.g., image classification, object detection, etc. However, few-shot object detection methods suffer from an intrinsic defect that the limited tra…
Embodied agents are expected to perform more complicated tasks in an interactive environment, with the progress of Embodied AI in recent years. Existing embodied tasks including Embodied Referring Expression (ERE) and other QA-form tasks mainly focuses on interaction in term of linguistic instructio…
Robust and efficient grasping of different objects is still an open problem due to the difficulty of integrating multidisciplinary knowledge such as gripper ontology design, perception, control, and learning. In recent years, learning-based methods have achieved excellent results in grasping various…
As humans, we hear sound every second of our life. The sound we hear is often affected by the acoustics of the environment surrounding us. For example, a spacious hall leads to more reverberation. Room Impulse Responses (RIR) are commonly used to characterize environment acoustics as a function of t…
The prevailing graph neural network models have achieved significant progress in graph representation learning. However, in this paper, we uncover an ever-overlooked phenomenon: the pre-trained graph representation learning model tested with full graphs underperforms the model tested with well-prune…
This work focuses on the 3D reconstruction of non-rigid objects based on monocular RGB video sequences. Concretely, we aim at building high-fidelity models for generic object categories and casually captured scenes. To this end, we do not assume known root poses of objects, and do not utilize catego…
Diffusion model, as a new generative model which is very popular in image generation and audio synthesis, is rarely used in speech enhancement. In this paper, we use the diffusion model as a module for stochastic refinement. We propose SRTNet, a novel method for speech enhancement via Stochastic Ref…
Learning a shared policy that guides the locomotion of different agents is of core interest in Reinforcement Learning (RL), which leads to the study of morphology-agnostic RL. However, existing benchmarks are highly restrictive in the choice of starting point and target point, constraining the movem…
This letter proposes a vision-based tactile sensor named TIRgel, leveraging visual integration to simplify the sensing system. First, the sensor achieves conversion of visual and tactile modality via focus adjustment. Under far-focus imaging, the camera can observe external environments; Under near-
Simulation is widely applied in robotics research to save time and resources. There have been several works to simulate optical tactile sensors that leverage either a smoothing method or Finite Element Method (FEM). However, elastomer deformation physics is not considered in the former method, where
Video action segmentation under timestamp supervision has recently received much attention due to lower annotation costs. Most existing methods generate pseudo-labels for all frames in each video to train the segmentation model. However, these methods suffer from incorrect pseudo-labels, especially…
A compliant control model based on reinforcement learning (RL) is proposed to allow robots to interact with the environment more effectively and autonomously execute force control tasks. The admittance model learns an optimal adjustment policy for interactions with the external environment using RL…
Nowadays, cameras equipped with AI systems can capture and analyze images to detect people automatically. However, the AI system can make mistakes when receiving deliberately designed patterns in the real world, i.e., physical adversarial examples. Prior works have shown that it is possible to print…
Referring expressions are commonly used when referring to a specific target in people's daily dialogue. In this paper, we develop a novel task of audio-visual grounding referring expression for robotic manipulation. The robot leverages both the audio and visual information to understand the referrin…
Recent works explore learning graph representations in a self-supervised manner. In graph contrastive learning, benchmark methods apply various graph augmentation approaches. However, most of the augmentation methods are non-learnable, which causes the issue of generating unbeneficial augmented grap…
3D object detection is a crucial research topic in computer vision, which usually uses 3D point clouds as input in conventional setups. Recently, there is a trend of leveraging multiple sources of input data, such as complementing the 3D point cloud with 2D images that often have richer color and fe…
In this letter, we propose a C-shaped bidirectional stiffness joint for an anthropomorphic hand. The spring steel piece is used to connect the knuckles with inner concave C-shape as a rotational joint. The finger is bent by the tendon driven with low stiffness and reset by its own elasticity. The re
Vision-and-language navigation (VLN) has been an important task in the field of Robotics and Computer Vision. However, most existing vision-and-language navigation models only use features extracted from RGB observation as input, while robots can utilize depth sensors in the real world. Existing res…
In human-robots collaboration scenarios, a human would give robots an instruction that is intuitive for the human himself to accomplish. However, the instruction given to robots is likely ambiguous for them to understand as some information is implicit in the instruction. Therefore, it is necessary…
Learning to reason about relations and dynamics over multiple interacting objects is a challenging topic in machine learning. The challenges mainly stem from that the interacting systems are exponentially-compositional, symmetrical, and commonly geometrically-constrained. Current methods, particular…
Currently, task-oriented grasp detection approaches are mostly based on pixel-level affordance detection and semantic segmentation. These pixel-level approaches heavily rely on the accuracy of a 2D affordance mask, and the generated grasp candidates are restricted to a small workspace. To mitigate t…
In visual semantic navigation, the robot navigates to a target object with egocentric visual observations and the class label of the target is given. It is a meaningful task inspiring a surge of relevant research. However, most of the existing models are only effective for single-agent navigation, a
In this work, we tackle the challenging problem of grasping novel objects using a high-DoF anthropomorphic hand-arm system. Combining fingertip tactile sensing, joint torques and proprioception, a multimodal agent is trained in simulation to learn the finger motions and to determine when to lift an
Many adaptations of transformers have emerged to address the single-modal vision tasks, where self-attention modules are stacked to handle input sources like images. Intuitively, feeding multiple modalities of data to vision transformers could improve the performance, yet the inner-modal attentive w…
During postharvest storage, fruit firmness usually decreases due to respiration and bruise, the former of which indicates the fruit ripeness while the latter negatively influence consumers' taste preference. This paper presents a portable and low-cost device using vision-based tactile information to…
Ithas always been a great challenge for the robot to navigate in the visual world following natural language instructions. Recently, several tasks such as the Vision-and-Language Navigation (VLN) and Remote Embodied Visual Referring Expression in Real Indoor Environments (REVERIE) are proposed tryin
Detecting 3D keypoints from point clouds is important for shape reconstruction, while this work investigates the dual question: can shape reconstruction benefit 3D keypoint detection? Existing methods either seek salient features according to statistics of different orders or learn to predict keypoi…
Keypoint detection and description play a central role in computer vision. Most existing methods are in the form of scene-level prediction, without returning the object classes of different keypoints. In this paper, we propose the object-centric formulation, which, beyond the conventional setting, r…
Audio-visual navigation task requires an agent to find a sound source in a realistic, unmapped 3D environment by utilizing egocentric audio-visual observations. Existing audio-visual navigation works assume a clean environment that solely contains the target sound, which, however, would not be suita…
Designing and analyzing model-based RL (MBRL) algorithms with guaranteed monotonic improvement has been challenging, mainly due to the interdependence between policy optimization and model learning. Existing discrepancy bounds generally ignore the impacts of model shifts, and their corresponding alg…
It has been a challenge to learning skills for an agent from long-horizon unannotated demonstrations. Existing approaches like Hierarchical Imitation Learning(HIL) are prone to compounding errors or suboptimal solutions. In this paper, we propose Option-GAIL, a novel method to learn skills at long h…
Deep reinforcement learning has made significant progress in robotic manipulation tasks and it works well in the ideal disturbance-free environment. However, in a real-world environment, both internal and external disturbances are inevitable, thus the performance of the trained policy will dramatica…
Semantic scene graph provides an effective way for intelligent agents to better understand the environment and it has been extensively used in many robotic applications. Existing work mainly focuses on generating the scene graph from the sensory information collected from a pre-defined path, while t…
Overcoming catastrophic forgetting is of great importance for deep learning and robotics. Recent lifelong learning research has great advances in supervised learning. However, little work focuses on reinforcement learning(RL). We focus on evaluating the performances of state-of-the-art lifelong lear…
This paper proposes a method of fabric structure defect detection based on tactile information. Different from traditional visual-based detection methods, the proposed method uses a tactile sensor to attain the information of fabric. The advantage of using tactile information is to avoid different i…
Robots are usually equipped with cameras to explore the indoor scene and it is expected that the robot can well describe the scene with natural language. Although some great success has been achieved in image and video captioning technology, especially on many public datasets, the caption generated…
In the low-bit quantization field, training Binarized Neural Networks (BNNs) is the extreme solution to ease the deployment of deep models on resource-constrained devices, having the lowest storage cost and significantly cheaper bit-wise operations compared to 32-bit floating-point counterparts. In…
Generalized Zero-Shot Learning (GZSL) is a challenging topic that has promising prospects in many realistic scenarios. Using a gating mechanism that discriminates the unseen samples from the seen samples can decompose the GZSL problem to a conventional Zero-Shot Learning (ZSL) problem and a supervis…
In this paper, we present a multimodal mobile teleoperation system that consists of a novel vision-based hand pose regression network (Transteleop) and an IMU (inertial measurement units)-based arm tracking method. Transteleop observes the human hand through a low-cost depth camera and generates not…
Deep multimodal fusion by using multiple sources of data for classification or regression has exhibited a clear advantage over the unimodal counterpart on various applications. Yet, current methods including aggregation-based and alignment-based fusion are still inadequate in balancing the trade-off…
We investigate a new AI task --- Multi-Agent Interactive Question Answering --- where several agents explore the scene jointly in interactive environments to answer a question. To cooperate efficiently and answer accurately, agents must be well-organized to have balanced work division and share know…
We propose a general method to train a single convolutional neural network which is capable of switching image resolutions at inference. Thus the running speed can be selected to meet various computational resource limits. Networks trained with the proposed method are named Resolution Switchable Net…
Unsupervised image-to-image translation is a central task in computer vision. Current translation frameworks will abandon the discriminator once the training process is completed. This paper contends a novel role of the discriminator by reusing it for encoding the images of the target domain. The pr…
Robust and accurate estimation of liquid height lies as an essential part of pouring tasks for service robots. However, vision-based methods often fail in occluded conditions while audio-based methods cannot work well in a noisy environment. We instead propose a multimodal pouring network (MP-Net) t…
The sound source separation problem has many useful applications in the field of robotics, such as human-robot interaction, scene understanding, etc. However, it remains a very challenging problem. In this paper, we utilize both visual and audio information of videos to perform the sound source sepa…
Embodiment is an important characteristic for all intelligent agents (creatures and robots), while existing scene description tasks mainly focus on analyzing images passively and the semantic understanding of the scenario is separated from the interaction between the agent and the environment. In th…
Different functional areas of the human brain play different roles in brain activity, which has not been paid sufficient research attention in the brain-computer interface (BCI) field. This paper presents a new approach for electroencephalography (EEG) classification that applies attention-based tra…
In this paper, a novel robotic grasping system is established to automatically pick up objects in cluttered scenes. A composite robotic hand composed of a suction cup and a gripper is designed for grasping the object stably. The suction cup is used for lifting the object from the clutter first and t…
This paper studies Learning from Observations (LfO) for imitation learning with access to state-only demonstrations. In contrast to Learning from Demonstration (LfD) that involves both action and state supervisions, LfO is more practical in leveraging previously inapplicable resources (e.g., videos)…
In this work, we investigate the lifelong learning problem from the viewpoint of heterogeneous multi-modal fusion. The main challenges come from the fact that the common representation between heterogeneous modalities should be persistently learned and the learned classifier for each multi-modal tas…
In this paper, we focus on the challenging perception problem in robotic pouring. Most of the existing approaches either leverage visual or haptic information. However, these techniques may suffer from poor generalization performances on opaque containers or concerning measuring precision. To tackle…
In this paper, we propose an end-to-end grasp evaluation model to address the challenging problem of localizing robot grasp configurations directly from the point cloud. Compared to recent grasp evaluation metrics that are based on handcrafted depth features and a convolutional neural network (CNN),…
Robots are usually equipped with microphones and cameras to perceive and understand the physical world. Though visual object detection technology has achieved great success, the detection in other modalities remains unsolved. In this paper, we establish a novel robotic sound-indicated visual object…
In this paper, we present TeachNet, a novel neural network architecture for intuitive and markerless vision-based teleoperation of dexterous robotic hands. Robot joint angles are directly generated from depth images of the human hand that produce visually similar robot hand poses in an end-to-end fa…
Humans' fingertips can perceive not only the magnitude and the direction of force but also the texture of object. When we grasp an object, the surface texture sensing of the fingertip helps us recognize the object and the force feeling that is parallel to the skin helps us grasp stably. Focusing on…
State-of-the-art object detectors usually learn multi-scale representations to get better results by employing feature pyramids. However, the current designs for feature pyramids are still inefficient to integrate the semantic information over different scales. In this paper, we begin by investigati…
The electroencephalography classifier is the most important component of brain-computer interface based systems. There are two major problems hindering the improvement of it. First, traditional methods do not fully exploit multimodal information. Second, large-scale annotated EEG datasets are almost…
The robotic grasp detection is a great challenge in the area of robotics. Previous work mainly employs the visual approaches to solve this problem. In this paper, a hybrid deep architecture combining the visual and tactile sensing for robotic grasp detection is proposed. We have demonstrated that th…
Linear Dynamical Systems (LDSs) are fundamental tools for modeling spatio-temporal data in various disciplines. Though rich in modeling, analyzing LDSs is not free of difficulty, mainly because LDSs do not comply with Euclidean geometry and hence conventional learning techniques can not be applied d…
In this paper, we exploit the intrinsic relation between different adjective labels and develop a novel multilabel dictionary learning and sparse coding method which is improved by introducing the structured output association information. Such a method makes use of the label correlation information…
We present RON, an efficient and effective framework for generic object detection. Our motivation is to smartly associate the best of the region-based (e.g., Faster R-CNN) and region-free (e.g., SSD) methodologies. Under fully convolutional architecture, RON mainly focuses on two fundamental problem…
Almost all of the current top-performing object detection networks employ region proposals to guide the search for object instances. State-of-the-art region proposal methods usually need several thousand proposals to get high recall, thus hurting the detection efficiency. Although the latest Region…
Human-powered lower exoskeletons have gained considerable interests from both academia and industry over the past few decades, and thus have seen increasing applications in areas of human locomotion assistance and strength augmentation. One of the most important aspects in those applications is to a…
Grasp an object from a stack of objects in real-time is still a challenge in robotics. This requires the robot to have the ability of both fast object discovery and grasp detection: a target object should be picked out from the stack first and then a proper grasp configuration is applied to grasp th
Linear Dynamical Systems (LDSs) are the fundamental tools for encoding spatio-temporal data in various disciplines. To enhance the performance of LDSs, in this paper, we address the challenging issue of performing sparse coding on the space of LDSs, where both data and dictionary atoms are LDSs. Rat…
Automatic discovery of topical objects from a set of image collections provides more strong cognitive capability of robot to understand the unstructured environment. In this paper, we propose a novel framework based on dictionary learning for such a task. Different from existing work which utilizes…
We present an effective method of identifying the graspable components of a variety of complex objects for grasp planning based on human experience. Instead of focusing on individual objects, our method identifies graspable components on the category level under the assumption that geometrically ali…
Robotic grasping has been hindered by the inability of robots to perceive unstructured environments. Because these environments can be complex or dynamic, it is important to obtain additional and precise sensing information just before grasping. This paper expands upon the pretouch modality by intro…