Camera-to-robot calibration is crucial for visionbased robot control and requires effort to make it accurate. Recent advancements in markerless pose estimation methods have eliminated the need for time-consuming physical setups for camera-to-robot calibration. While the existing markerless pose estimation methods have demonstrated impressive accuracy without the need for cumbersome setups, they rely on the assumption that all the robot joints are visible within the camera's field of view. However, in practice, robots usually move in and out of view, and some portion of the robot may stay out-of-frame during the whole manipulation task due to real-world constraints, leading to a lack of sufficient visual features and subsequent failure of these approaches. To address this challenge and enhance the applicability to visionbased robot control, we propose a novel framework capable of estimating the robot pose with partially visible robot manipulators. Our approach leverages the Vision-Language Models for fine-grained robot components detection, and integrates it into a keypoint-based pose estimation network, which enables more robust performance in varied operational conditions. The framework is evaluated on both public robot datasets and self-collected partial-view datasets to demonstrate our robustness and generalizability. As a result, this method is effective for robot pose estimation in a wider range of realworld manipulation scenarios.

Robot pose estimation is a challenging and crucial task for vision-based surgical robotic automation. Typical robotic calibration approaches, however, are not applicable to surgical robots, such as the da Vinci Research Kit (dVRK) [1], due to joint angle measurement errors from cable-drives and the partially visible kinematic chain. Hence, previous works in surgical robotic automation used tracking algorithms to estimate the pose of the surgical tool in real-time and compensate for the joint angle errors. However, a big limitation of these previous tracking works is the initialization step which relied on only keypoints and SolvePnP. In this work, we fully explore the potential of geometric primitives beyond just keypoints with differentiable rendering, cylinders, and construct a versatile pose matching pipeline in a novel pose hypothesis space. We demonstrate the state-of-the-art performance of our single-shot calibration method with both calibration consistency and real surgical tasks. As a result, this marker-less calibration approach proves to be a robust and generalizable initialization step for surgical tool tracking.

Reconstruction of deformable scenes from endoscopic videos is important for many applications such as intraop-erative navigation, surgical visual perception, and robotic surgery. It is a foundational requirement for realizing autonomous robotic interventions for minimally invasive surgery. However, previous approaches in this domain have been limited by their modular nature and are confined to specific camera and scene settings. Our work adopts the Neural Radiance Fields (NeRF) approach to learning 3D implicit representations of scenes that are both dynamic and deformable over time, and furthermore with unknown cam-era poses. This work removes the constraints of known cam-era poses and overcomes the drawbacks of the state-of-the-art unstructured dynamic scene reconstruction technique, which relies on the static part of the scene for accurate re-construction. Through several experimental datasets, we demonstrate the versatility of our proposed model to adapt to diverse camera and scene settings, and show its promise for both current and future robotic surgical systems.

The rise of the metaverse concept has brought about widespread attention in wearable gesture recognition devices. Data gloves based on flexible strain sensors have been favoured by researchers owing to their low cost, light weight, direct and continuous monitoring of finger movements. In this review, we first compare the advantages and disadvantages of four different approaches based on the vision sensors, myoelectric sensors, inertial and magnetic sensors, and flexible strain sensors in designing data gloves, and demonstrate the superiority of the flexible strain sensor-based data glove used for metaverse applications. Next, some latest commercial data gloves are exampled and the function modules of the data gloves are presented based on the flexible strain sensors. Meanwhile, the potential applications of gesture recognition in the metaverse are summarized in diversified fields. Finally, the existing problems and development prospects of the current data gloves based on flexible strain sensors are concluded. We are optimistic that novel flexible strain sensor-based data gloves will make transformational impact to realize accurate, low-latency, and immersive gesture interaction in the metaverse.

One of the biggest advantages that a millimeter-wave (mmWave) system has is the tremendously available bandwidth. According to Shannon Theorem, an obvious improvement of the system capacity can be achieved. However, regarding an OFDM system, the number of subcarriers increases as well, although larger subcarrier spacing is considered in 5G. For the multiuser uplink transmission in an OFDM system, a baseband equalizer has to be computed on each subcarrier. Hence, an OFDM system with a great amount of subcarriers suffers from a high computation complexity while it benefits from the huge bandwidth. To reduce the system complexity, we introduce in this paper a simple subcarrier grouping scheme where only one equalizer is computed for a set of adjacent subcarriers. However, such scheme gives rise to a notable system degradation. Such a performance loss due to the subcarrier grouping can be further compensated by a time-domain linear filter.

Physical layer security in the presence of passive eavesdroppers (i.e., the eavesdroppers' channels are unknown to the transmitter) in correlated channels is addressed. The majority of the literature with passive eavesdroppers assumption focus on uncorrelated channels and random artificial noise (AN) generation in the null space of the legitimate channel. This paper targets joint optimization of the AN vector and the power fraction used for beamforming in correlated channels. These two variables are obtained by maximizing the minimum secure probability of attaining a pre-determined secrecy level for a certain number of the most dangerous potential Eves, which are obtained by the correlation map. The correlation map contains long-term channel correlation matrices for all the potential Eves' locations, which are captured by legitimate users passing through these areas in the past. We use a secure probability map to illustrate the secrecy levels for all the possible positions of the legitimate user. The results show the significant secrecy enhancement of our proposed algorithm when compared to the exiting AN generation methods.