A central challenge in source-free domain adaptation (SFDA) is the lack of a theoretical framework for explicitly analyzing domain shifts, as the absence of source data prevents direct domain comparisons. In this paper, we introduce the Vicinal Gaussian Transform (VGT), an analytical operator that models source-informed latent vicinities as Gaussians and shows that vicinal prediction divergence is bounded by their covariance. By this formulation, SFDA can be reframed as shrinking covariance to reinforce label consistency. To operationalize this idea, we introduce the Energy-based VGT (EBVGT), a novel SDE that realizes the Gaussian transform by contracting covariance through a denoising mechanism. A recovery-likelihood with a Schrödinger-Bridge smoothness penalty denoises perturbed states, while a BYOL-derived energy function, directly obtained from model predictions, provides the score to guide label-consistent trajectories within the vicinity. This design not only yields noise-suppressed vicinal features for adaptation without source data, but also eliminates the need for additional learnable parameters for score estimation, in contrast to conventional deep SDEs. Our EBVGT is model- and modality-agnostic, efficient for classification, and improves state-of-the-art SFDA methods by 1.3-3.0% (2.0% on average) across both 2D image and 3D point cloud benchmarks.

Medical image registration is essential for integrating information from diverse imaging modalities for clinical diagnosis and treatment planning. Despite significant advancements, achieving efficient and precise deformable image registration remains a formidable challenge. In this study, we propose a novel medical image registration model, RWKVMatch, which employs global attention and cross-fusion mechanism based on the Vision-RWKV module to address complex deformations in medical images effectively. Additionally, the elastic transformation from data augmentation techniques is integrated into the model architecture to enhance its capability to handle multi-scale features and improve robustness to geometric variations in image registration. Experimental evaluations on two medical image registration datasets indicate the effectiveness of our approach, surpassing existing state-of-the-art methods in terms of registration accuracy and computational efficiency. These findings underscore the potential of RWKVMatch as a highly effective tool for medical image registration.

CAD drawing restoration is one of the most urgent needs in industrial manufacturing. The existing research focuses on the digitization of CAD drawings, However, there are actually many problems in digitized CAD drawings due to the upgrading of engineering drafting software, and it is difficult to repair reliably. In this paper, we use multi-modal large language models (MLLMs) to carry out digital CAD drawing restoration, and we use Retrieval-Augmented Generation (RAG) technology to inject engineering domain knowledge into MLLMs. In addition, a complete set of multiagent systems is constructed to realize restoration in accordance with the CAD drawing review process in the mechanical field. We collected 1,639 CAD drawings of bearing seats to evaluate our multi-agent system, verifying its reliability and robustness to various problematic drawings. Notably, ChatCAD also has a much simpler implementation than alternative methods trained on a huge dataset.

The visual steel surface inspection system is crucial to the steel quality assessment process. Existing methods based on the teacher-student paradigm need extra training overhead, while pure supervised methods suffer from low performance. In this study, we developed a novel training approach for steel surface defect segmentation, which has lower training overhead and better performance than the teacher-student paradigm. Firstly, we extended the Vicinal Risk Minimization principle and proposed a mixup approach named Pseudo Mixup to get more reliable augmented data with less distribution shift using pseudo label. Secondly, we proposed an encoder-decoder based Self Distillation approach with adaptive modifications, which has lower computational overhead compared to the teacher-student framework. We conducted experiments on three open-source steel surface defect segmentation datasets, and our experimental results show that our methods can steadily improve performance under different circumstances.

Existing imitation learning methods decouple perception and action, which overlooks the causal reciprocity between sensory representations and action execution that humans naturally leverage for adaptive behaviors. To bridge this gap, we introduce Action-Guided Diffusion Policy (DP-AG), a unified representation learning that explicitly models a dynamic interplay between perception and action through probabilistic latent dynamics. DP-AG encodes latent observations into a Gaussian posterior via variational inference and evolves them using an action-guided SDE, where the Vector–Jacobian Product (VJP) of the diffusion policy's noise predictions serves as a structured stochastic force driving latent updates. To promote bidirectional learning between perception and action, we introduce a cycle-consistent contrastive loss that organizes the gradient flow of the noise predictor into a coherent perception–action loop, enforcing mutually consistent transitions in both latent updates and action refinements. Theoretically, we derive a variational lower bound for the action-guided SDE, and prove that the contrastive objective enhances continuity in both latent and action trajectories. Empirically, DP-AG significantly outperforms state-of-the-art methods across simulation benchmarks and real-world UR5 manipulation tasks. As a result, our DP-AG offers a promising step toward bridging biological adaptability and artificial policy learning. Code is available on our project website: https://jingwang18.github.io/dp-ag.github.io/.

Wheeled climbing robots have great application prospects in the machining of large components with variable curvature. However, its accurate motion control on variable curvature surfaces faces two fatal challenges. The varied contact states between the robot’s wheels and the variable curvature surfaces make it difficult to establish an accurate kinematics model. Additionally, there exists a different degree of robot slippage when the robot moves in different attitudes due to the dragging effect of gravity. To overcome the above problems, we first present a kinematics modeling method with instantaneous plane constraints on a variable curvature surface. Subsequently, a linear extended state observer (LESO)-based nonlinear model predictive control (NMPC) scheme is designed, in which the NMPC is used to calculate the nominal control inputs and the LESO is used to estimate and compensate for lumped disturbance brought by the robot slippage and surface constraints. Experiments on a real wind turbine blade with variable curvature show that the proposed control scheme can well eliminate the influence of lumped disturbance, and the climbing robots can achieve unbiased (AVG < 0.1 mm) and high-precision (RMSE < 2 mm) trajectory tracking. Note to Practitioners—Wheeled climbing robots, capable of adhering to curved surfaces of workpieces while in motion, provide a new approach for machining large components when equipped with machining actuators. This paper is motivated by the tracking control problem of wheeled climbing robots on curved surfaces with variable curvature, which is crucial for ensuring effective machining. The varying contact states between the wheels and the surfaces during the robot’s motion, along with the robot slippage introduced by the dragging effect of gravity, result in discrepancies between the ideal and actual motion speeds. These discrepancies introduce model uncertainties and thus pose challenges for achieving high-precision trajectory tracking. Additionally, current research on climbing robots primarily focuses on prototype development, with practitioners predominantly utilizing open-loop controller or basic model-free control schemes. This often leads to non-robust trajectory tracking of the climbing robot. To address these problems, this paper offers an accurate kinematics modeling method considering instantaneous plane constraints of the curved surfaces and a LESO-based NMPC scheme which can effectively reduce the impact of external disturbances. This approach provides a solution for automatic and high-precision trajectory tracking for climbing robot with localization system in factories, offering the potential for high-quality machining of large components.

This paper presents a fast global collision detection method for robotic machining of large complex components, aiming to quickly determine whether there is a collision between the robot and the surrounding environment during the whole machining process. Geometric analysis shows that there are always some trajectory points on the motion path of the manipulator that are more likely to collide than the surrounding points during machining. These trajectory points with the highest collision probability within a certain range are defined as the feature points of global collision detection, and are used to replace all trajectory points to perform global collision detection, thus greatly improving the efficiency of related operations while ensuring accuracy. Compare to the traditional discrete collision detection method with computational complexity O($\text{n}^{2}$), the computational complexity of the proposed method is only O(n). Numerical analysis and application experiments verify the effectiveness of the proposed method. Note to Practitioners—Motion planning in robotic machining of large complex components usually needs to perform a lot of global collision detection. Existing methods generally have the problems of large calculation and low efficiency, which seriously affects the efficiency of motion planning. This is mainly because a single global collision detection usually includes no less than$n$times of static collision detection, where$n$is the number of trajectory points. In order to solve this problem, we present a new global collision detection method based on feature-point-set. It does not need to traverse all trajectory points for static collision detection, but only needs to detect a few feature points, that is, the trajectory points most likely to collide within a certain range. On the premise of ensuring the collision detection accuracy, the proposed method greatly reduces the execution times of static collision detection, and significantly improves the computational efficiency of global collision detection. Numerical analysis and experiments show that this method effectively improves the efficiency of motion planning in robotic machining of large complex components.

Localization in a large-scale three-dimensional scene is a key challenge faced by climbing robots on large workpieces. This article proposes a global localization method for climbing robots based on tether displacement sensor, visual-inertial odometry (VIO), and computer-aided design (CAD) model of workpieces. Tether displacement sensor measures the distance between robot and tether anchor with little drift, which enables robot to acquire global pose. Adsorption constraints on robot motion are extracted using CAD model to reduce the drift of VIO. The approach realizes global localization with high accuracy for the robots when climbing on large workpieces without other external locating equipment. The performance is verified with a prototype of climbing robot testing on real large workpieces. In all experiments, our method with adsorption constraints outperforms existing VIO. The largest drift of merged trajectory is as low as 0.51% in global localization on a wind turbine blade with length of 8 m.

In this article, we propose an RFID-based simultaneous localization and mapping (RF-SLAM) method that allows us, for the first time, to estimate the robot's position and the tags’ 3D position in the warehouse environment simultaneously without any reference tags and external sensors, using only COTS RFID device. RF-SLAM is designed to transform the RFID measurement into the relative tag position constraint and use a corresponding graph based model to solve the SLAM problem. Specifically, a multiantenna-based relative localization method using phase measurement and odometer data in a short time is proposed as the front end. The back end is a novel graph model based on the relative tags position constraint and odometer constraint. Experiments in different types of warehouses show the localization accuracy of robot and tags’ 3D position is about 5 cm and 10 cm, respectively. The experimental results in a more challenging and actual environment are still competitive.

A novel radio frequency identification (RFID)-based mobile robot global localization method combining two kinds of RFID signal information, i.e., phase difference and readability, is proposed. Specifically, a phase difference model and a classification logic strategy based on readability are built and integrated into a particle filter localization algorithm. Compared with existing RFID localization methods, the proposed localization method can achieve competitive localization performance in an environment with a relatively sparse reference tag distribution and without the need for offline phase drift calibration. A series of real experimental tests were performed, and the results show that the proposed method can localize a mobile robot with centimeter-level position accuracy and satisfactory attitude angle accuracy when the distance between adjacent reference tags is approximately 60 cm, even if all RFID devices are commercial off-the-shelf (COTS). The proposed method provides a promising option for mobile robot localization applications, such as path tracking of mobile robots.Note to Practitioners—Mobile robot localization is a key technology for its location-based services. Considering that radio frequency identification (RFID) is entirely unaffected by light interference and has a globally unique ID, RFID has been regarded as a localization sensor with broad application prospects. This article proposes an RFID-based mobile robot global localization method combining phase difference and readability, by which the mobile robot can be accurately localized in an environment with a relatively sparse reference tag distribution and without the need for offline phase drift calibration. The experimental results indicate that the proposed method can localize the mobile robot with good performance, including centimeter-level position accuracy and satisfactory attitude angle accuracy. The proposed method can effectively contribute to many practical applications, such as the path tracking of a mobile robot.

This article proposes a standalone radio frequency identification (RFID)-based mobile robot navigation method, in which a mobile robot equipped with reader antennas can be continuously guided to a static object marked with a single passive UHF RFID tag. An observation model based on the RFID phase difference is built and integrated into a particle filter, by which the instantaneous relative position between the mobile robot and the tagged object can be detected in real time. Based on the position information extracted from the RFID system, the mobile robot adjusts its pose to move toward the RFID-tagged object. Compared with the existing RFID-based mobile robot navigation methods, the proposed method requires no external sensors other than the RFID and requires only a single passive tag. Experiments using commercial off-the-shelf (COTS) RFID devices are performed, and the results indicate that the mobile robot can satisfactorily realize navigation task with a distance accuracy of 4.04 cm and a bearing accuracy of 2.23°. The proposed method is well applicable for the navigation scenes in which the absolute position of the tagged target object is not known beforehand.Note to Practitioners—UHF radio frequency identification (RFID) has been widely applied as an asset management ID sensor in many fields. RFID-based mobile robot navigation technology can further increase its application value as a location sensor. This article proposes a standalone RFID-based mobile robot navigation method, in which the reference tag and the external sensors other than RFID are both not required. In the proposed method, only a single passive tag is attached to the static target object. Experimental results indicate that the proposed method can enable navigation task with good performance in situations in which the absolute navigation goal position is not known in advance.

In order to improve the robustness and optimize trajectory of projective homography-based uncalibrated visual servoing (PHUVS) proposed in our previous work, an analytical expression of optimal trajectory for camera in projective homography space is proposed in this article, which is totally free of camera parameters and is corresponding to camera's shortest path in the 3-D space with straight path in translation and minimal geodesic in rotation. The projective homography is computed without scale ambiguity in both planning and tracking stages. The PHUVS controller is modified correspondingly to track the planned trajectory in projective homography space while maintaining superior characteristic of PHUVS under uncalibrated scenario. The simulations and experiments' results reveal the effectiveness and necessity of the proposed trajectory optimization method in the existence of large initial errors. Note to Practitioners-The state-of-the-art visual-guided robotic technology in industry usually requires system calibration, which is often costly, vulnerable, and challenging for ordinary workers. In our previous work, we offered an uncalibrated visual servo method based on projective homography named projective homography-based uncalibrated visual servoing (PHUVS), which is suitable for plug and play application for eye-in-hand robot visual servo tasks. However, PHUVS suffers from some defects, including undesirable 3-D space motion and local convergence. In this article, we proposed the trajectory planning method along with a modified PHUVS controller to improve the original one from the disadvantages mentioned earlier. This planning method is also calibration-free. With pure image information, a straight-line path in translational motion along with minimal geodesic in rotary motion can be achieved. This approach is capable of extending the range of applications for uncalibrated visual servo technology in robotic tasks, such as assembling, painting, and robotic machining.

A novel ultrahigh-frequency (UHF) radio frequency identification (RFID) localization method is proposed in this paper, by which the location of a static passive tag can be easily obtained using a mobile RFID antenna. An unwrapped phase-position model with three parameters is built, and the location of the tag can be pinpointed through an ordinary nonlinear least-squares algorithm. The main advantage of this method is that it is cheap in computation cost compared with the existing grid-based methods. The experimental tests confirm that the proposed method can localize the RFID tags with a competitive computational efficiency and accuracy performance, i.e., millisecond-level computing time and centimeter-level location accuracy. The proposed UHF RFID localization method is well suited to the pervasive location-aware applications, searching RFID-tagged item in the intelligent warehouse by the mobile robot with an onboard RFID system, for example.

An uncalibrated visual servo method based on projective homography, denoted as Projective Homography based Uncalibrated Visual Servoing (PHUVS), is proposed in this paper, in which a novel task function based on the element of projective homography is devised to realize visual servo without a prior knowledge of the camera intrinsic parameters and hand-eye relationships. The main advantage of this method is that it is not only suitable for totally uncalibrated scenarios but also cheap in computation costs when compared with classical image-based uncalibrated visual servoing methods. Numerical experiments are performed and the results confirm that the new approach is capable of both static positioning and dynamic tracking tasks, and presents competitive computational efficiency and accuracy performance.