Recently, robotics has widely utilized in tremendous applications including traffic transportation, medical treatments, power system and virtual environment. These applications are almost based on the vision system, w...
详细信息
The proceedings contain 52 papers. The topics discussed include: design of a soft robot using pneumatic muscles for elbow rehabilitation;remote sensing images recognition by deep convolutional neural networks;challeng...
ISBN:
(纸本)9781538695944
The proceedings contain 52 papers. The topics discussed include: design of a soft robot using pneumatic muscles for elbow rehabilitation;remote sensing images recognition by deep convolutional neural networks;challenges of dynamic environment for visual-inertial odometry;sensor fault tolerant algorithm for 7.2nm class SPMSM applied electro-hydraulic power steering system for medium and heavy commercial vehicle;an improved method of 3D scene reconstruction based on SfM;menu control and functionalities of 3D digital oscilloscope;multi-view clustering: a brief review;remote control and tracking dual mode smart suitcas;and a novel hybrid path planning algorithm at macroscopic level for autonomous climbing robot.
Three-dimensional (3D) point cloud understanding is important for autonomous robots. However, point clouds are normally irregular and discrete. It is challenging to obtain semantic information from them. In this paper...
详细信息
Three-dimensional (3D) point cloud understanding is important for autonomous robots. However, point clouds are normally irregular and discrete. It is challenging to obtain semantic information from them. In this paper, we present a method to build a dense semantic map, which utilizes both two-dimensional (2D) image labels and 3D geometric information. The dense point cloud is built by using a state-of-the-art RGB-D SLAM system. It is further segmented into meaningful clusters using a graph-based method. Then, image keyframes during the SLAM process are used to extract semantic image labels by a convolution neural network (CNN). Finally, these semantic labels are projected to the point cloud clusters to achieve a 3D dense semantic map. The effectiveness of our method is validated on a popular public dataset.
With development of medical image processing, more and more cancers are diagnosed and treated with assistance of computer, especially lung cancer. Extracting lung from CT image series is usually the first step. Hundre...
详细信息
ISBN:
(纸本)9781538604854
With development of medical image processing, more and more cancers are diagnosed and treated with assistance of computer, especially lung cancer. Extracting lung from CT image series is usually the first step. Hundreds of CT images slow down the processing. As to clinical applications, the accuracy and efficiency is crucial. We proposed and realized an auto-segmentation of lung in CT image series based on level set method with prior knowledge. Firstly, we autosegmented one CT image with LBF method. Secondly, we extracted the lung contour from the segmentation with region grow and feature selection. In the end, we extracted the lung contour of the next CT image with DRLSE method. The previous lung contour was set to be the initial contour to ensure the accuracy and efficiency. The experiment results proved that our approach is more stable and faster. It spent only about 67% of the time that LBF and DRLSE did.
With the intensification of aging population, medical and social insurance system is facing up with the unprecedented pressure. Most of old people need nursing and care. On the one hand, it needs expensive expenditure...
详细信息
With the intensification of aging population, medical and social insurance system is facing up with the unprecedented pressure. Most of old people need nursing and care. On the one hand, it needs expensive expenditure and manpower. On the other hand, living quality of old people in degree of freedom is greatly reduced. The problem of helping old people to walk has become a great social problem. The self-adaption coordination control of robot is an important indicator of walking assistant robot for the elderly and also the precondition to support and protect old people and the disabled. In order to realize the control of direction for walking assistant robot and get the smaller turning radius and more flexible movement, this paper studied a dual-motor differential control method to realize forward, backward, and cornering of robot. Finally, the experimental results show that the control system of the friendly walking assistant robot for the elderly is rational and feasible, and the designed control system is stable and reliable.
Coordinated operation is a common task for the dual-Arm robot system in nuclear industry, and the trajectory tracking performance and inner torque are both important indications for the coordinated operation. However,...
详细信息
Based on the fifth generation of mobile communication (5G), 5G open grid computing environment (5G OGCE), in order to adapt to "civil-military integration strategy" in region from deep sea to space, at the s...
详细信息
ISBN:
(纸本)9781538695944
Based on the fifth generation of mobile communication (5G), 5G open grid computing environment (5G OGCE), in order to adapt to "civil-military integration strategy" in region from deep sea to space, at the same time to meet the needs of ocean engineering development, a joint (connecting or docking-and-berthing) robot and aircraft carriers combinatorial systems are presented in this paper, the aim of which is to, (1) achieve aircraft carrier combinatorial systems jointed dynamically by double aircraft carriers, or more ships and aircraft carriers, providing the new runway of 600 meters long taking off and landing aircraft in the sea;(2) integrate unmanned aircraft carriers (and manned aircraft carriers) to take off and land the sixth generation strike fighter or unmanned stealth fighter;(3) combine the aircraft carrier and new production systems of ocean engineering, including polar icebreaker, underwater rare earth mining, combustible ice mining, underwater power generation and so on;(4) support the development of sea wave energy, offshore power generation plant and weather radar forecasting platform, and the launch and recovery of offshore rockets. By using distributed control cloud architecture in 5G OGCE, large passenger aircraft taking off and landing at 600 meters runway in aircraft carriers combinatorial systems can be realized.
In this paper, aiming at the problems of 2-DOF horizontal motion control with high precision for autonomous underwater vehicle(AUV) trajectory tracking tasks, deep reinforcement learning controllers are applied to the...
详细信息
In this paper, aiming at the problems of 2-DOF horizontal motion control with high precision for autonomous underwater vehicle(AUV) trajectory tracking tasks, deep reinforcement learning controllers are applied to these conditions. These control problems are considered as a POMDP (Partially Observable Markov Decision Process). Model-free reinforcement learning(RL) algorithms for continuous control mission based on Deterministic Policy Gradient(DPG) allows robots learn from received delayed rewards when interacting with environments. Recurrent neural networks LSTM (Long Short-Term Memory) are involved into the reinforcement learning algorithm. Through this deep reinforcement learning algorithm, AUVs learn from sequences of dynamic information. The horizontal trajectory tracking tasks are described by LOS method and the motion control are idealized as a SISO model. Tanh-estimators are presented as data normalization. Moreover, AUV horizontal trajectory tracking and motion control simulation results demonstrate this algorithm gets better accuracy compared with the PID method and other non-recurrent methods. Efforts show the efficiency and effectiveness of the improved deep reinforcement learning algorithm.
The flapping wing robot (FWR), inspired by avian aerodynamics, is a distinct category of unmanned aerial vehicles (UAVs). Different to general UAVs, such as quadcopters, FWRs are featured by their superior aerodynamic...
详细信息
Determining the accurate count of leukocytes commonly known as WBC (white blood cells) in a blood test is critical in evaluating and diagnosing an individual39;s health particularly on a wide range of diseases which...
详细信息
暂无评论