Search

Dexterous manipulation of the robot is an important part of realizing intelligence, but manipulators can only perform simple tasks such as sorting and packing in a structured environment. In view of the existing problem, this paper presents a state-of-the-art survey on an intelligent robot with the capability of autonomous deciding and learning. The paper first reviews the main achievements and research of the robot, which were mainly based on the breakthrough of automatic control and hardware in mechanics. With the evolution of artificial intelligence, many pieces of research have made further progresses in adaptive and robust control. The survey reveals that the latest research in deep learning and reinforcement learning has paved the way for highly complex tasks to be performed by robots. Furthermore, deep reinforcement learning, imitation learning, and transfer learning in robot control are discussed in detail. Finally, major achievements based on these methods are summarized and analyzed thoroughly, and future research challenges are proposed.

Feature point detection is the basis of computer vision, and the detection methods with geometric invariance and illumination invariance are the key and difficult problem in the field of feature detection. This paper proposes an illumination-invariant feature point detection method based on neighborhood information. The method can be summarized into two steps. Firstly, the feature points are divided into eight types according to the number of connected neighbors. Secondly, each type of feature points is classified again according to the position distribution of neighboring pixels. The theoretical deduction proves that the proposed method has lower computational complexity than other methods. The experimental results indicate that, when the photometric variation of the two images is very large, the feature-based detection methods are usually inferior, while the learning-based detection methods performs better. However, our method performs better than the learning-based detection method in terms of the number of feature points, the number of matching points, and the repeatability rate stability. The experimental results demonstrate that the proposed method has the best illumination robustness among state-of-the-art feature detection methods.

Existing moving target detection methods mainly include inter-frame differences, background differences, optical flow and so on. For the recognition of human motions in the process of human-computer collaboration, existing algorithms are usually difficult to meet the requirements of real-time processing and easily interfered by lighting or image noises. In this paper, a method for establishing a static background model based on pixel histogram is proposed. The effect of moving targets and noises on the background model is excluded due to the selectivity of the new algorithm to the gray values, so it can detect the real background more reliably. Compared with other moving target detection methods, this method has the characteristics of fast speed, strong anti-interference ability, and the ability to identify human body movement quickly and accurately.

Flow separation is ubiquitous in turbomachinery. Compared with the more mature turbomachinery flow separation control method where the medium is gas, the turbomachinery flow separation method where the medium is liquid cannot be controlled well. In this study, according to the flow separation control principle of the aircraft fowler flap, taking the stator blade of the hydraulic torque converter as the basic research object, the stator blade shape is fitted with Joukowsky transformation, and then it is slotted. Computational fluid dynamics is used to perform flow analysis on original blades and slotted blades. It is found that compared with that of the original blade, the slotted blade’s flow separation phenomenon is effectively suppressed, turbulent kinetic energy is reduced, flow is more stable, and energy loss is reduced. In addition, using slotted blades for torque converter simulation, the torque ratio is increased by up to 0.245, and the efficiency is increased by up to 5%, which shows that slotted blades can improve the mechanical performance of the pump wheel and are not limited to the torque converter.