As robots have become more pervasive in our daily life, natural human-robot interaction (HRI) has had a positive impact on the development of robotics. Thus, there has been growing interest in the development of vision-based hand gesture recognition for HRI to bridge human-robot barriers. The aim is for interaction with robots to be as natural as that between individuals. Accordingly, incorporating hand gestures in HRI is a significant research area. Hand gestures can provide natural, intuitive, and creative methods for communicating with robots. This paper provides an analysis of hand gesture recognition using both monocular cameras and RGB-D cameras for this purpose. Specifically, the main process of visual gesture recognition includes data acquisition, hand gesture detection and segmentation, feature extraction and gesture classification, which are discussed in this paper. Experimental evaluations are also reviewed. Furthermore, algorithms of hand gesture recognition for human-robot interaction are examined in this study. In addition, the advances required for improvement in the present hand gesture recognition systems, which can be applied for effective and efficient human-robot interaction, are discussed.

This paper investigates the global tracking control of underactuated aerial vehicles. In particular, the globally exponentially stable attitude tracking controller serving as the inner loop of the overall controller is investigated. It can avoid the common problems that may be accompanied by other attitude controllers, such as singularity and unwinding. In order to overcome the topological obstacles of global control on SO(3), rotational motion of a rigid body is expressed in the exponential coordinate restricted in a compact domain. We then construct a hybrid tracking error dynamics whose states are all represented in Euclidean space. The geometric properties of the state space are mathematically analyzed. The tracking controller of underactuated aerial vehicles is, thus, designed based on the hybrid tracking error dynamics. The global exponential stability of the closed-loop attitude subsystem, as well as the global asymptotical stability of the closed-loop overall system under assumptions, is analyzed using Lyapunov's method strictly. These properties are demonstrated by simulation results. The proposed controller is also implemented and tested on our self-developed quadrotor, showing the feasibility of the controller in realtime applications.

RGB-D Salient Object Detection (SOD) aims to segment the most prominent areas and objects in a given pair of RGB and depth images. Most current models adopt a dual-stream structure to extract information from both RGB and depth images. However, this leads to an exponential increase in the number of parameters and computations in the model. Moreover, the discrepancy between RGB pretrained and the 3D geometric relationships in depth maps present a challenge for the encoder in capturing spatial structural details. These issues impact the model's accuracy in locating salient objects and distinguishing edge details. To address these, we propose a novel early feature fusion network, named FasterSal, which enables more efficient RGB-D SOD. FasterSal uses a single stream structure to receive RGB images and depth maps, extracting features based on the 3D geometric relationships in the depth map while fully leveraging the pretrained RGB encoder. This approach effectively avoids the inconsistencies between depth modality and the RGB pretrained encoder. It also significantly reduces the number of network parameters while maintaining efficient feature encoding capabilities. To achieve finer edge learning, the detail-aware loss and texture enhancement module are introduced. These modules are designed to extract latent details in high-frequency component features and to enhance the edge learning capability of the model using distance information. Experimental results on several benchmark datasets confirm the effectiveness and superiority of our method over the state-of-the-art approaches, achieving a good balance between performance and speed with only 3.4 million parameters and a CPU operating speed of 63 FPS. Code and results available at: https://github.com/zhangjinCV/FasterSal .

A multipropeller multifunction aerial robot capable of flight and wall climbing is presented in this paper. This novel robot consists of four propellers and two leg-wheel mechanisms. The propellers providing thrust for the vehicle are devoted to the attitude control. Two leg-wheel mechanisms are used for the wall climbing. The dynamic modeling in flight mode is derived in terms of the coupling between the main body and the legs. The wall-climbing mode of the robot falls into wheel-wall-climbing mode and leg-wall-climbing mode, while the latter is the focus of this paper. The kinematic and dynamic modeling, as well as the constraints in leg-wall-climbing mode are investigated. Based on the model, the leg-wall-climbing motion planning is proposed in terms of the constraints. The paper also presents a stabilization control strategy to maintain the attitude stability when the aerial robot is in leg-wall-climbing mode. Simulations of the robot in leg-wall-climbing mode are accomplished to show the effectiveness of the designed stabilization controller at the presence of input disturbances, sensor noise, sensor delays, and parametric modeling errors. A quadrotor subsystem experimental platform is built, and the experimental results support the theoretical analysis.

This letter aims to solve the challenging problems in multi-modal active vision for object detection on unmanned aerial vehicles (UAVs) with a monocular camera and a limited Field of View (FoV) LiDAR. The point cloud acquired from the low-cost LiDAR is firstly converted into a 3-channel tensor via motion compensation, accumulation, projection, and up-sampling processes. The generated 3-channel point cloud tensor and RGB image are fused into a 6-channel tensor using an early fusion strategy for object detection based on a Gaussian YOLO network structure. To solve the low computational resource problem and improve the real-time performance, the velocity information of the UAV is further fused with the detection results based on an extended Kalman Filter (EKF). A perception-aware model predictive control (MPC) is designed to achieve active vision on our UAV. According to our performance evaluation, our pre-processing step improves other literature methods running time by a factor of 10 while maintaining acceptable detection performance. Furthermore, our fusion architecture reaches 94.6 mAP on the test set, outperforming the individual sensor networks by roughly 5%. We also described an implementation of the overall algorithm on a UAV platform and validated it in real-world experiments.