This study focuses on the steering optimization of the obstacle-surmounting platform of six-wheeled robots. After using the Ackermann steering twice, we calculated the parameters such as Ackermann steering angle and t...
This study focuses on the steering optimization of the obstacle-surmounting platform of six-wheeled robots. After using the Ackermann steering twice, we calculated the parameters such as Ackermann steering angle and turning radius, and then we simulated two situations of Ackermann steering and parallel steering. We simulated the relationship between horizontal friction force and analyzed the tire wear under two conditions using the Archard wear model. Through simulation analysis, we found that after adding the Ackermann steering, with other conditions unaffected, the horizontal friction of the tire was smaller, and the amount of tire wear was less under the same driving time. The results show that by adding Ackermann steering, the steering performance of the obstacle-surmounting platform is improved and the service life of tires is prolonged.
In this paper, the constraint function of the maximum turning angle is designed in the fitness function of the Beetle Antenna Search algorithm (BAS) according to the characteristic that unmanned surface vehicles (USV)...
In this paper, the constraint function of the maximum turning angle is designed in the fitness function of the Beetle Antenna Search algorithm (BAS) according to the characteristic that unmanned surface vehicles (USV) are not easy to turn sharply. To solve the problem of strong randomness and poor stability of the global path planning of BAS, the dynamic search step size that changes with the distance from the obstacle is used in the Improved Beetle Antenna Search algorithm (IBAS), instead of the fixed step size used in the original algorithm. Simulation results show that IBAS improves the stability and success rate of global path planning for USV. The planned path is smooth, continuous, safe, and effective. IBAS is more suitable for the path planning of USV than the original algorithm.
We present a new method to achieve accurate and real-time 3D scene reconstruction based on monocular cameras on a vision robotic manipulator platform. To realize this, we use the initialization part of SLAM and the la...
We present a new method to achieve accurate and real-time 3D scene reconstruction based on monocular cameras on a vision robotic manipulator platform. To realize this, we use the initialization part of SLAM and the latest advances in N eRF (Neural Radiance Field), Instant-NGP, and, most importantly, the information from the robotic manipulator to acquire real-time camera pose. This work uses keyframe images with camera real-time pose obtained from the visual robotic manipulator. Thus, the problem that instant-NGP needs images with pose are solved on the platform of the robotic manipulator, reducing the time of secondary processing of pure images and, consequently, realizing real-time 3D reconstruction.
Unmanned combat vehicle is one of the important development trends of the future battlefield, and the unmanned combat vehicle that can realize positioning navigation and autonomous obstacle avoidance in the complex an...
Unmanned combat vehicle is one of the important development trends of the future battlefield, and the unmanned combat vehicle that can realize positioning navigation and autonomous obstacle avoidance in the complex and changeable battlefield environment is an important research direction of unmanned combat vehicle. The path planning problem of unmanned combat vehicles is studied. Based on the classical potential field method, the inherent defects of the classical potential field method are emphatically analyzed. An improved model of repulsive potential field function based on the social force model is proposed. Aiming at the problem that unmanned combat vehicles are prone to fall into local minima, this solution of sub-target points is proposed. Through simulation verification, the inherent defects of the classical potential field method in the path process of unmanned combat vehicles are optimized, It shows that the model and simulation can provide an effective decision-making basis for the path planning of unmanned combat vehicles.
For the problem of poor safety and real-time tracking of the paths planned by UAVs with unknown map information, an improved JPS algorithm based on a heuristic angle search strategy is proposed on the basis of the tra...
For the problem of poor safety and real-time tracking of the paths planned by UAVs with unknown map information, an improved JPS algorithm based on a heuristic angle search strategy is proposed on the basis of the traditional JPS algorithm. This algorithm improves the jump point screening rules and introduces the visual camera's field of view angle as a heuristic factor to obtain obstacle information ahead of time, improving the real-time safety of path planning. The path is also smoothed by using a B-spline curve. Finally, the simulation and comparison experiments of the A* algorithm, the JPS algorithm, the hybrid A* algorithm, and this algorithm are conducted in a gazebo environment. The experimental results show that the path planned by this algorithm can effectively reduce the threat caused by unknown obstacles, and real flight experiments are being conducted on a UAV based on the ROS operating system to prove the feasibility and safety of this algorithm.
As an important metal material, zinc alloy is widely used in electroplating, spraying and other industries. In the production process of the original zinc alloy ingot, slagging is a very important process, and most do...
As an important metal material, zinc alloy is widely used in electroplating, spraying and other industries. In the production process of the original zinc alloy ingot, slagging is a very important process, and most domestic production enterprises still choose manual slagging. Due to the labor intensity, the working environment is harmful to artificial health, some companies began to turn their attention to automated machinery and equipment. The existing slag raking robots on the market are transformed into general-purpose industrial robots, the lack of specialization, and expensive, inconvenient maintenance. In this paper, based on the general-purpose zinc alloy production line of zinc alloy slag picking robot, using Adams and MATLAB joint control system traditional PID, PID control under fuzzy rules, and joint angular velocity control under improved nonlinear control PID, it is concluded that the improved nonlinear control PID has good control effect.
Aiming at problems of the limited accuracy of the model and poor control precision caused by the complex deformation of Cable-Driven Continuum Robot(CDCR), a shape sensing and feedback control approach for CDCR is pro...
Aiming at problems of the limited accuracy of the model and poor control precision caused by the complex deformation of Cable-Driven Continuum Robot(CDCR), a shape sensing and feedback control approach for CDCR is proposed based on the elastic magnetoelectric strain sensor. The kinematic model of CDCR was established based on the product of the exponential (POE) formula. Based on the sensor's physical characteristics, the robot's shape-sensing model was proposed and Qualisys Track System was used for calibration. A module prototype was built to verify the effect of the perceptual feedback control algorithm. The experiment proved that the flexible perception method used in this paper is universal and accurate, and provides a valuable framework for real-time sensing control.
The preparation of lunar soil samples is a complex task, and direct programming control of the robotic arm is too cumbersome and not safe enough under the existing conditions. Therefore, this paper proposes a six-degr...
The preparation of lunar soil samples is a complex task, and direct programming control of the robotic arm is too cumbersome and not safe enough under the existing conditions. Therefore, this paper proposes a six-degree-of-freedom robotic arm follow-up operation method based on human motion characteristics and deep reinforcement learning to improve the efficiency and safety of the preparation process. Firstly, the motion data of human arm under different tasks collected by Optitrack motion capture system are analyzed to get the motion law of joint angle, and the corresponding reward function is designed. Then, the robotic arm is trained in the simulation environment using Soft Actor-Critic (SAC) and Hindsight Experience Replay (HER) algorithms. According to the trained network model, the robot arm completes the task of tracking random target motion. Finally, the experiments in Pybullet simulation environment verify the feasibility, effectiveness and adaptability of the manipulator control method proposed in this paper. The method can be applied to other continuous motion control scenarios in continuous space.
Due to the dangerous working environment and high working intensity of electrolytic aluminum workshop, aluminum ingot transfer robot is used to assist workers to sample and transport aluminum ingot, among which, accur...
Due to the dangerous working environment and high working intensity of electrolytic aluminum workshop, aluminum ingot transfer robot is used to assist workers to sample and transport aluminum ingot, among which, accurate positioning of aluminum ingot is an important link. In the process of robot grasping aluminum ingot, there are some problems, such as uneven brightness, low contrast and small target to be detected, which affect the accuracy of identification and positioning. In order to solve the above problems, an optical correction method of aluminum ingot image based on adaptive gamma rays is proposed in this paper to improve the accuracy of target detection under extreme illumination conditions. After the YOLOX network detects the target, the space motion function is proposed to realize the conversion from two-dimensional(2D) plane coordinates to three-dimensional(3D) space coordinates. This algorithm can effectively solve the problem of low recognition accuracy caused by illumination. Through the calculation of space motion function, the positioning accuracy error of the manipulator is less than 5mm.
Deep reinforcement learning is a type of machine learning that enables an agent to learn from its interactions with the environment in order to maximize a reward signal. However, current research leaks of the combinat...
Deep reinforcement learning is a type of machine learning that enables an agent to learn from its interactions with the environment in order to maximize a reward signal. However, current research leaks of the combination with robotic control and the accuracy of robotic controlling illustrates low by utilizing the traditional detecting algorithms. In this research, the deep reinforcement learning algorithm is applied to control the characteristics of a robotic system, allowing it to adapt and improve its performance over time. The results of the research demonstrate that the deep reinforcement learning-based control mechanism is able to effectively navigate and manipulate objects in the robotic environment, achieving a high level of control and precision. Overall, this work shows the potential of deep reinforcement learning for creating advanced robotic control systems that can learn and adapt to changing conditions.
暂无评论