There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

생체의 모델링과 Simulation

Learning Deconvolution Network for Semantic Segmentation

Learning and then recognizing a route, whether travelled during the day or at night, in clear or inclement weather, and in summer or winter is a challenging task for state of the art algorithms in computer vision and robotics. In this paper, we present a new approach to visual navigation under changing conditions dubbed SeqSLAM. Instead of calculating the single location most likely given a current image, our approach calculates the best candidate matching location within every local navigation sequence. Localization is then achieved by recognizing coherent sequences of these “local best matches”. This approach removes the need for global matching performance by the vision front-end - instead it must only pick the best match within any short sequence of images. The approach is applicable over environment changes that render traditional feature-based techniques ineffective. Using two car-mounted camera datasets we demonstrate the effectiveness of the algorithm and compare it to one of the most successful feature-based SLAM algorithms, FAB-MAP. The perceptual change in the datasets is extreme; repeated traverses through environments during the day and then in the middle of the night, at times separated by months or years and in opposite seasons, and in clear weather and extremely heavy rain. While the feature-based method fails, the sequence-based algorithm is able to match trajectory segments at 100% precision with recall rates of up to 60%.

SeqSLAM : visual route-based navigation for sunny summer days and stormy winter nights

Short-term traffic forecast is one of the essential issues in intelligent transportation system. Accurate forecast result enables commuters make appropriate travel modes, travel routes, and departure time, which is meaningful in traffic management. To promote the forecast accuracy, a feasible way is to develop a more effective approach for traffic data analysis. The availability of abundant traffic data and computation power emerge in recent years, which motivates us to improve the accuracy of short-term traffic forecast via deep learning approaches. A novel traffic forecast model based on long short-term memory (LSTM) network is proposed. Different from conventional forecast models, the proposed LSTM network considers temporal-spatial correlation in traffic system via a two-dimensional network which is composed of many memory units. A comparison with other representative forecast models validates that the proposed LSTM network can achieve a better performance.

https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/iet-its.2016.0208

LSTM network: a deep learning approach for short-term traffic forecast

This paper presents a robust adaptive iterative learning control (ILC) algorithm for 3-DOF permanent magnet (PM) spherical actuators to improve their trajectory tracking performance. The dynamic model of a PM spherical actuator is a multivariable nonlinear system with interaxis coupling terms. Uncertainties such as modeling errors, loads, and external disturbances exist in the model unavoidably, which will affect the performance, including the precision of the control system. Hence, to compensate for these uncertainties, a new hybrid control scheme that consists of a proportional–derivative (PD) feedback control with varying gains, a PD-type ILC with adjustable gains, and a robust term is developed. The new control law combines the advantages of simplicity and easy design of the PD control, the effectiveness of the ILC to handle model uncertainties and repetitive disturbances, and the robustness of the robust term to random disturbances. In addition, to expedite the convergence rate, the gains in the PD feedback control and the PD-type ILC are adaptively adjusted according to the iteration times. It is shown that the system tracking error approaches zero as the number of iterations increases. To demonstrate the proposed algorithm and verify the established theoretical results, both simulations and experiments are conducted. The results have shown that the proposed control algorithm can effectively compensate for various uncertainties and can thus improve the trajectory tracking performance of spherical actuators.

A Robust Adaptive Iterative Learning Control for Trajectory Tracking of Permanent-Magnet Spherical Actuator

The design of a new six-degree-of-freedom (6-DOF) parallel-kinematics machine (PKM) has been proposed. Different from the conventional Stewart-Gough platform which has six extensible legs, the new PKM employs three identical RPRS legs to support the moving platform. Since all joint axes, excluding the three spherical joints at the leg ends, are parallel to each other and perpendicular to the base plane, this 6-DOF PKM presents a promising platform structure with decoupled-motion architecture (DMA) such that translation in a horizontal plane and rotation about a vertical axis are driven by the three active revolute joints, while translation in the vertical direction and rotation about horizontal axes are driven by the three active prismatic joints. As a result, this 6-DOF 3RPRS PKM with DMA has simple kinematics, large cylindrical reachable workspace, and high stiffness in the vertical direction. These features make it appropriate for light machining and heavy parts assembly tasks. Because of the DMA, a projection technique is employed for its kinematics analysis. By projecting the manipulator onto horizontal directions and vertical planes, the kinematics issues such as the displacement, singularity, and workspace analysis are significantly simplified.

Kinematic design of a six-DOF parallel-kinematics Machine with decoupled-motion architecture

This paper describes the design, modeling, and testing of a novel flexure-based microgripper for a large jaw displacement with high resolution. Such a microgripper is indispensable in micro/nano manipulation. In achieving a large jaw displacement, double amplification mechanisms, namely, Scott-Russell mechanism and leverage mechanism arranged in series, are utilized to overcome the limited output of microgrippers driven by piezoelectric actuators. The mechanical performance of the microgripper is analyzed using the pseudo rigid body model approach. Finite element analysis is conducted to evaluate the performance and validate the established models for further optimum design of the microgripper. The prototype of the developed microgripper is fabricated, with which experimental tests are carried out. The experimental results show that the developed microgripper is capable of handling various sized micro-objects with a maximum jaw displacement of 134 μm and a high amplification ratio of 15.5.

A novel flexure-based microgripper with double amplification mechanisms for micro/nano manipulation.

This paper focuses on the topic of smooth gait transition of a hexapod robot by a proposed central pattern generator (CPG) algorithm. Through analyzing the movement characteristics of the real insects, it is easy to generate kinds of gait patterns and achieve their smooth transition if we employ a series of oscillations with adjustable phase lag. Based on this concept, a CPG model is proposed, which is constructed by an isochronous oscillators and several first-order low-pass filters. As an application, a hexapod robot and its locomotion control are introduced by converting the CPG signal to robot’s joint space. Simulation and real world experiment are completed to demonstrate the validity of the proposed CPG model. Through measuring the position of the body center and the distance between footpoints and ground, the smooth gait transition can be achieved so that the effectiveness of the proposed method is verified.

Weihai Chen

Papers

LSTM network: a deep learning approach for short-term traffic forecast

A Robust Adaptive Iterative Learning Control for Trajectory Tracking of Permanent-Magnet Spherical Actuator

Kinematic design of a six-DOF parallel-kinematics Machine with decoupled-motion architecture

A novel flexure-based microgripper with double amplification mechanisms for micro/nano manipulation.

Smooth transition between different gaits of a hexapod robot via a central pattern generators algorithm