Search results

Unsupervised domain adaptation object detection not only mitigates model terrible performance resulting from domain gap, but also has the ability to apply knowledge trained on a definite domain to a distinct domain. However, aligning the whole feature may confuse the object and background information, making it challenging to extract discriminative features. This paper aims to propose an improved approach which is called intrinsic feature extraction domain adaptation (IFEDA) to extract discriminative features effectively.

IFEDA consists of the intrinsic feature extraction (IFE) module and object consistency constraint (OCC). The IFE module, designed on the instance level, mainly solves the issue of the difficult extraction of discriminative object features. Specifically, the discriminative region of the objects can be paid more attention to. Meanwhile, the OCC is deployed to determine whether category prediction in the target domain brings into correspondence with it in the source domain.

Experimental results demonstrate the validity of our approach and achieve good outcomes on challenging data sets.

Limitations to this research are that only one target domain is applied, and it may change the ability of model generalization when the problem of insufficient data sets or unseen domain appeared.

This paper solves the issue of critical information defects by tackling the difficulty of extracting discriminative features. And the categories in both domains are compelled to be consistent for better object detection.

Autonomous obstacle avoidance is important in unmanned surface vehicle (USV) navigation. Although the result of obstacle detection is often inaccurate because of the inherent errors of LIDAR, conventional methods typically emphasize on a single obstacle-avoidance algorithm and neglect the limitation of sensors and safety in a local region. Conventional methods also fail in seamlessly integrating local and global obstacle avoidance algorithms. This paper aims to present a cooperative manoeuvring approach including both local and global obstacle avoidance.

The global algorithm used in our USV is the Artificial Potential Field-Ant Colony Optimization (APF-ACO) obstacle-avoidance algorithm, which plans a relative optimal path on the specified electronic map before the cruise of USV. The local algorithm is a multi-layer obstacle-avoidance framework based on a single LIDAR to present an efficient solution to USV path planning in the case of sensor errors and collision risks. When obstacles are within a layer, the USV uses a corresponding obstacle-avoidance algorithm. Then the USV moves towards the global direction according to fuzzy rules in the fuzzy layer.

The presented method offers a solution for obstacle avoidance in a complex environment. The USV follows the global trajectory planed by the APF-ACO algorithm. While, the USV can bypass current obstacle in the local region based on the multi-layer method effectively. This fact was validated by simulations and field trials.

The method presented in this paper takes advantage of algorithm integration that remedies errors of obstacle detection. Simulation and experiments were also conducted for performance evaluation.

This paper aims to improve the adaptability and control performance of the controller, a proposed seeker optimization algorithm (SOA) is introduced to optimize the controller parameters of a robot manipulator.

In this paper, a traditional proportional integral derivative (PID) controller and a fuzzy logic controller are integrated to form a fuzzy PID (FPID) controller. The SOA, as a novel algorithm, is used for optimizing the controller parameters offline. There is a performance comparison in terms of FPID optimization about the SOA, the genetic algorithm (GA), particle swarm optimization (PSO) and ant colony optimization (ACO). The DC motor model and the experimental platform are used to test the performance of the optimized controller.

Compared with GA, PSO and ACO, this novel optimization algorithm can enhance the control accuracy of the system. The optimized parameters ensure a system with faster response speed and better robustness.

A simplified FPID controller structure is constructed and a novel SOA method for FPID controller is presented. In this paper, the SOA is applied on the controller of 5-DOF manipulator, and the validation of controllers is tested by experiments.

In order to replace the conventional human maintenance of cable‐stayed bridges, a robot is designed and constructed for tasks such as cleaning, painting and rust‐detecting.

Adopting a modular approach, two kinds of climbing mechanisms, plus a painting mechanism and a rust‐detecting method are designed.

A robot that can climb and maintain the cables of cable‐stayed bridges has been designed and constructed. It has been proved by experiment that the robot can overcome many disadvantages of conventional human bridge‐maintenance, and drastically improve efficiency, cost, and safety.

The robot is of industrial size, but a new mechanism requiring less installing time will be designed for the future.

The robot has been applied to cables of the Nanpu Bridge and Xupu Bridge in Shanghai. More than 80 cable‐stayed bridges and six suspension bridges have been built or are being constructed across large rivers in China alone. This gives an enormous potential market.

The cable maintenance robot developed in this paper is the world's first special robot for the cables of cable‐stayed bridges.

This paper aims to propose a new method for combining global path planning with local path planning, to provide an efficient solution for unmanned surface vehicle (USV) path planning despite the changeable environment. Path planning is the key issue of USV navigation. A lot of research works were done on the global and local path planning. However, little attention was given to combining global path planning with local path planning.

A search of shortcut Dijkstra algorithm was used to control the USV in the global path planning. When the USV encounters unknown obstacles, it switches to our modified artificial potential field (APF) algorithm for local path planning. The combinatorial method improves the approach of USV path planning in complex environment.

The method in this paper offers a solution to the issue of path planning in changeable or unchangeable environment, and was confirmed by simulations and experiments. The USV follows the global path based on the search of shortcut Dijkstra algorithm. Both USV achieves obstacle avoidances in the local region based on the modified APF algorithm after obstacle detection. Both the simulation and experimental results demonstrate that the combinatorial path planning method is more efficient in the complex environment.

This paper proposes a new path planning method for USV in changeable environment. The proposed method is capable of efficient navigation in changeable and unchangeable environment.

The purpose of this paper was to solve the shortage of carrying energy in probing robot and make full use of wind resources in the Antarctic expedition by designing a four-wheel land-yacht. Land-yacht is a new kind of mobile robot powered by the wind using a sail. The mathematical model and trajectory of the land-yacht are presented in this paper.

The mechanism analysis method and experimental modeling method are used to establish a dual-input and dual-output mathematical model for the motion of land-yacht. First, the land-yacht’s model structure is obtained by using mechanism analysis. Then, the models of steering gear, servomotors and force of wing sail are analyzed and validated. Finally, the motion of land-yacht is simulated according to the mathematical model.

The mathematical model is used to analyze linear motion and steering motion. Compared with the simulation results and the actual experimental tests, the feasibility and reliability of the proposed land-yacht modeling are verified. It can travel according to the given signal.

This land-yacht can be used in the Antarctic, outer planet or for harsh environment exploration.

A land-yacht is designed, and the contribution of this research is the development of a mathematical model for land-yacht robot. It provides a theoretical basis for analysis of the land-yacht’s motion.

After almost 10 years, people wonder if green finance has been able to attain its objectives in terms of controlling climate change. Persistent global warming and climate deregulation manifested by melting glaciers, droughts and floods, are all of these determinants that have called into question the efficiency of green finance.

Green finance is a way to support climate action through investments. It has proven that this is a viable financial instrument and that it can be used by governments and private companies to plan for the future of our planet.

Based on an analysis of articles published in top international journals from 2016 to 2022, about the relationship between green technology and financial services in China, this paper aims to present an overview of green finance, its importance for the planet, its objectives and its instruments.

This study’s contribution is to shed light on the aspects that may have limited its effectiveness, such as the absence of incentives, the absence of climate costs and above all the absence of finance green standards.

The results have shown that there is still a significant gap in green finance before inclusive green growth can be achieved. Inclusive green growth. All stakeholders need to increase the level of investment in green finance. The green investment financing gap is the result of inconsistencies in sustainability and policies. Therefore, governments must intervene to impose appropriate policies and regulations to compel the financial sector to engage in sustainable development. All of these factors make the concept of green finance just an illusion.