Ning Tan

Wensheng Wang, Chuanjun Guo, Wei Wei et al.

Generalizable grasping with high-degree-of-freedom (DoF) dexterous hands remains challenging in tiered workspaces, where occlusion, narrow clearances, and height-dependent constraints are substantially stronger than in open tabletop scenes. Most existing methods are evaluated in relatively unoccluded settings and typically do not explicitly model the distinct control requirements of arm navigation and hand articulation under spatial constraints. We present SpaceDex, a hierarchical framework for dexterous manipulation in constrained 3D environments. At the high level, a Vision-Language Model (VLM) planner parses user intent, reasons about occlusion and height relations across multiple camera views, and generates target bounding boxes for zero-shot segmentation and mask tracking. This stage provides structured spatial guidance for downstream control instead of relying on single-view target selection. At the low level, we introduce an arm-hand Feature Separation Network that decouples global trajectory control for the arm from geometry-aware grasp mode selection for the hand, reducing feature interference between reaching and grasping objectives. The controller further integrates multi-view perception, fingertip tactile sensing, and a small set of recovery demonstrations to improve robustness to partial observability and off-nominal contacts. In 100 real-world trials involving over 30 unseen objects across four categories, SpaceDex achieves a 63.0\% success rate, compared with 39.0\% for a strong tabletop baseline. These results indicate that combining hierarchical spatial planning with arm-hand representation decoupling improves dexterous grasping performance in spatially constrained environments.

Peng Yu, Xin Wang, Ning Tan

Continuum robots possess high flexibility and redundancy, making them well suited for safe interaction in complex environments, yet their continuous deformation and nonlinear dynamics pose fundamental challenges to perception, modeling, and control. Existing vision-based control approaches often rely on end-to-end learning, achieving shape regulation without explicit awareness of robot geometry or its interaction with the environment. Here, we introduce a shape-interpretable visual self-modeling framework for continuum robots that enables geometry-aware control. Robot shapes are encoded from multi-view planar images using a Bezier-curve representation, transforming visual observations into a compact and physically meaningful shape space that uniquely characterizes the robot's three-dimensional configuration. Based on this representation, neural ordinary differential equations are employed to self-model both shape and end-effector dynamics directly from data, enabling hybrid shape-position control without analytical models or dense body markers. The explicit geometric structure of the learned shape space allows the robot to reason about its body and surroundings, supporting environment-aware behaviors such as obstacle avoidance and self-motion while maintaining end-effector objectives. Experiments on a cable-driven continuum robot demonstrate accurate shape-position regulation and tracking, with shape errors within 1.56% of image resolution and end-effector errors within 2% of robot length, as well as robust performance in constrained environments. By elevating visual shape representations from two-dimensional observations to an interpretable three-dimensional self-model, this work establishes a principled alternative to vision-based end-to-end control and advances autonomous, geometry-aware manipulation for continuum robots.

Wensheng Wang, Ning Tan

The acquisition of large-scale and diverse demonstration data are essential for improving robotic imitation learning generalization. However, generating such data for complex manipulations is challenging in real-world settings. We introduce HybridGen, an automated framework that integrates Vision-Language Model (VLM) and hybrid planning. HybridGen uses a two-stage pipeline: first, VLM to parse expert demonstrations, decomposing tasks into expert-dependent (object-centric pose transformations for precise control) and plannable segments (synthesizing diverse trajectories via path planning); second, pose transformations substantially expand the first-stage data. Crucially, HybridGen generates a large volume of training data without requiring specific data formats, making it broadly applicable to a wide range of imitation learning algorithms, a characteristic which we also demonstrate empirically across multiple algorithms. Evaluations across seven tasks and their variants demonstrate that agents trained with HybridGen achieve substantial performance and generalization gains, averaging a 5% improvement over state-of-the-art methods. Notably, in the most challenging task variants, HybridGen achieves significant improvement, reaching a 59.7% average success rate, significantly outperforming Mimicgen's 49.5%. These results demonstrating its effectiveness and practicality.

Xulang Liu, Ning Tan

3D Gaussian Splatting (3DGS) has recently emerged as a powerful representation of geometry and appearance for dense Simultaneous Localization and Mapping (SLAM). Through rapid, differentiable rasterization of 3D Gaussians, many 3DGS SLAM methods achieve near real-time rendering and accelerated training. However, these methods largely overlook inertial data, witch is a critical piece of information collected from the inertial measurement unit (IMU). In this paper, we present GI-SLAM, a novel gaussian-inertial SLAM system which consists of an IMU-enhanced camera tracking module and a realistic 3D Gaussian-based scene representation for mapping. Our method introduces an IMU loss that seamlessly integrates into the deep learning framework underpinning 3D Gaussian Splatting SLAM, effectively enhancing the accuracy, robustness and efficiency of camera tracking. Moreover, our SLAM system supports a wide range of sensor configurations, including monocular, stereo, and RGBD cameras, both with and without IMU integration. Our method achieves competitive performance compared with existing state-of-the-art real-time methods on the EuRoC and TUM-RGBD datasets.

Kejun Hu, Peng Yu, Ning Tan

Self-modeling enables robots to build task-agnostic models of their morphology and kinematics based on data that can be automatically collected, with minimal human intervention and prior information, thereby enhancing machine intelligence. Recent research has highlighted the potential of data-driven technology in modeling the morphology and kinematics of robots. However, existing self-modeling methods suffer from either low modeling quality or excessive data acquisition costs. Beyond morphology and kinematics, texture is also a crucial component of robots, which is challenging to model and remains unexplored. In this work, a high-quality, texture-aware, and link-level method is proposed for robot self-modeling. We utilize three-dimensional (3D) Gaussians to represent the static morphology and texture of robots, and cluster the 3D Gaussians to construct neural ellipsoid bones, whose deformations are controlled by the transformation matrices generated by a kinematic neural network. The 3D Gaussians and kinematic neural network are trained using data pairs composed of joint angles, camera parameters and multi-view images without depth information. By feeding the kinematic neural network with joint angles, we can utilize the well-trained model to describe the corresponding morphology, kinematics and texture of robots at the link level, and render robot images from different perspectives with the aid of 3D Gaussian splatting. Furthermore, we demonstrate that the established model can be exploited to perform downstream tasks such as motion planning and inverse kinematics.

Yun Jiang, Ning Tan, Tingting Peng et al.

Accurate segmentation of retinal vessels is a basic step in Diabetic retinopathy(DR) detection. Most methods based on deep convolutional neural network (DCNN) have small receptive fields, and hence they are unable to capture global context information of larger regions, with difficult to identify lesions. The final segmented retina vessels contain more noise with low classification accuracy. Therefore, in this paper, we propose a DCNN structure named as D-Net. In the proposed D-Net, the dilation convolution is used in the backbone network to obtain a larger receptive field without losing spatial resolution, so as to reduce the loss of feature information and to reduce the difficulty of tiny thin vessels segmentation. The large receptive field can better distinguished between the lesion area and the blood vessel area. In the proposed Multi-Scale Information Fusion module (MSIF), parallel convolution layers with different dilation rates are used, so that the model can obtain more dense feature information and better capture retinal vessel information of different sizes. In the decoding module, the skip layer connection is used to propagate context information to higher resolution layers, so as to prevent low-level information from passing the entire network structure. Finally, our method was verified on DRIVE, STARE and CHASE dataset. The experimental results show that our network structure outperforms some state-of-art method, such as N4-fields, U-Net, and DRIU in terms of accuracy, sensitivity, specificity, and AUCROC. Particularly, D-Net outperforms U-Net by 1.04%, 1.23% and 2.79% in DRIVE, STARE, and CHASE three dataset, respectively.

Yun Jiang, Ning Tan

The segmentation of retinal vessels is of significance for doctors to diagnose the fundus diseases. However, existing methods have various problems in the segmentation of the retinal vessels, such as insufficient segmentation of retinal vessels, weak anti-noise interference ability, and sensitivity to lesions, etc. Aiming to the shortcomings of existed methods, this paper proposes the use of conditional deep convolutional generative adversarial networks to segment the retinal vessels. We mainly improve the network structure of the generator. The introduction of the residual module at the convolutional layer for residual learning makes the network structure sensitive to changes in the output, as to better adjust the weight of the generator. In order to reduce the number of parameters and calculations, using a small convolution to halve the number of channels in the input signature before using a large convolution kernel. By used skip connection to connect the output of the convolutional layer with the output of the deconvolution layer to avoid low-level information sharing. By verifying the method on the DRIVE and STARE datasets, the segmentation accuracy rate is 96.08% and 97.71%, the sensitivity reaches 82.74% and 85.34% respectively, and the F-measure reaches 82.08% and 85.02% respectively. The sensitivity is 4.82% and 2.4% higher than that of R2U-Net.