Explore the vast range of titles available.

The resolution of traffic congestion and personal safety issues holds paramount importance for human’s life. The ability of an autonomous driving system to navigate complex road conditions is crucial. Deep learning has greatly facilitated machine vision perception in autonomous driving. Aiming at the problem of small target detection in traditional YOLOv5s, this paper proposes an optimized target detection algorithm. The C3 module on the algorithm’s backbone is upgraded to the CBAMC3 module, introducing a novel GELU activation function and EfficiCIoU loss function, which accelerate convergence on position loss l box , confidence loss l obj , and classification loss l cls , enhance image learning capabilities and address the issue of inaccurate detection of small targets by improving the algorithm. Testing with a vehicle-mounted camera on a predefined route effectively identifies road vehicles and analyzes depth position information. The avoidance model, combined with Pure Pursuit and MPC control algorithms, exhibits more stable variations in vehicle speed, front-wheel steering angle, lateral acceleration, etc., compared to the non-optimized version. The robustness of the driving system's visual avoidance functionality is enhanced, further ameliorating congestion issues and ensuring personal safety.

The logistics industry has made significant progress in recent years. However, there are still issues with low operational efficiency and high costs. Unmanned logistics vehicles have gained attention as an efficient and intelligent mode of transportation with the rapid development of the industry. The study utilizes an advanced path tracking control algorithm, in combination with model predictive control technology, to monitor and adjust the path, speed, and direction of unmanned logistics vehicles in real-time. The aim is to enhance the stability, safety, and efficiency of travel. The experiments revealed that the average accuracy of path deviation prediction of the proposed model on two different datasets is 88.33% and 82.1%, which is 3.96% and 4.72% higher than that of the control model, respectively. The control accuracy of the proposed model reached 94.19% on the KITTI Vision Benchmark Suite dataset and 95.61% on the CARLA Simulator dataset, which are both higher than the other control models. In addition, the study also tested the proposed model for energy consumption, controller switching frequency, lateral error and other indexes, and the findings revealed that the proposed model of the study exhibits high stability and efficiency. This research not only provides new ideas for the control of unmanned logistics vehicles, but also verifies the effectiveness of the control strategy through experiments.

In order to improve the driving performance of four-wheel drive electric vehicles and realize precise control of their speed, a Chaotic Random Grey Wolf Optimization-based PID in-wheel motor control algorithm is proposed in this paper. Based on an analysis of the structural principles of electric vehicles, mathematical and simulation models for the whole vehicle are established. In order to improve the control performance of the hub motor, the traditional Grey Wolf Optimization algorithm is improved. In particular, an enhanced population initialization strategy integrating sine and cosine random distribution factors into a Kent chaotic map is proposed, the weight factor of the algorithm is improved using a sine-based non-linear decreasing strategy, and the population position is improved using the random proportional movement strategy. These strategies effectively enhance the global optimization ability, convergence speed, and optimization accuracy of the traditional Grey Wolf Optimization algorithm. On this basis, the CR-GWO-PID control algorithm is established. Then, the software and hardware of an in-wheel motor controller are designed and an in-wheel motor bench test system is built. The simulation and bench test results demonstrate the significantly improved response speed and control accuracy of the proposed in-wheel motor control system.

This study proposes an enhanced multi-agent swarm control algorithm (EN-MASCA) to solve the problem of efficient patrolling of drone swarms in complex durian orchard environments. It introduces a virtual navigator model to dynamically adjust the patrol path of the drone swarm and perform obstacle avoidance and path optimization in real time according to environmental changes. Different from traditional algorithms that only rely on fixed path planning, the virtual navigator model significantly improves the flexibility and stability of the drone swarm in complex environments. It also applies deep reinforcement learning algorithms to path planning and obstacle avoidance of drone swarms for the first time, improving the algorithm’s adaptability and optimization capabilities by learning dynamic information in complex environments. This innovation significantly improves the applicability of existing methods in complex terrain and dynamic obstacle environments. Finally, it incorporates the simulation characteristics of biological swarm behavior, and on this basis, comprehensively optimizes the flight path, obstacle avoidance and swarm stability of the drone swarm. By improving control strategies and parameter design, it improves the trajectory consistency and mission completion efficiency of the UAV swarm during flight. In the experimental part, this study verified in detail the advantages of the EN-MASCA algorithm in terms of flight trajectory, flight stability, cluster consistency and task completion efficiency by constructing a six-degree-of-freedom UAV motion simulation model and real environment simulation. It provides an efficient and intelligent solution for collaborative patrol operations of drones in durian orchards, which has important practical application value and promotion prospects.

This paper presents a simulation model environment for the popular and low-cost remotely operated vehicle (ROV) BlueROV2 implemented in Simulink™ which has been designed and experimentally validated for benchmark control algorithms for underwater vehicles. The BlueROV2 model is based on Fossen’s equations and includes a kinematic model of the vehicle, the hydrodynamics of vehicle and water interaction, a dynamic model of the thrusters, and, lastly, the gravitational/buoyant forces. The hydrodynamic parameters and thruster model have been validated in a test facility. The benchmark model also includes the ocean current, modeled as constant velocity. The tether connecting the ROV to the top-site facility has been modeled using the lumped mass method and is implemented as a force input to the ROV model. At last, to show the usefulness of the benchmark model, a case study is presented where a BlueROV2 is deployed to inspect an offshore monopile structure. The case study uses a sliding mode controller designed for the BlueROV2. The controller fulfills the design criteria defined for the case study by following the provided trajectory with a low error. It is concluded that the simulator establishes a benchmark for future control schemes for position control and trajectory tracking under the influence of environmental disturbances.

With the continuous progress of contemporary science and technology and the increasing requirements for marine vehicles in various fields, the intelligence and automation of ships have become a general trend. The autonomous control of surface Unmanned Surface Vessel (USV) generally covers the USV path planning, path tracking control, and autonomous collision avoidance control. But in the whole navigation process of USV, autonomous berthing is also a crucial part. And the research on the algorithm of the automatic berthing process of the USV is less. Mature USV autonomous berthing technology can effectively reduce the cost of human and material resources and financial resources while reducing the accident rate reasonably and safely. Therefore, it is of great importance to comprehensively promote the development of USV autonomous berthing technology.

In this paper, a finite-time controller is proposed for the quadrotor aircraft to achieve hovering control in a finite time. The design of controller is mainly divided into two steps. Firstly, a saturated finite-time position controller is designed such that the position of quadrotor aircraft can reach any desired position in a finite time. Secondly, a finite-time attitude tracking controller is designed, which can guarantee that the attitude of quadrotor aircraft converges to the desired attitude in a finite time. By homogenous system theory and Lyapunov theory, the finite-time stability of the closed-loop systems is given through rigorous mathematical proofs. Finally, numerical simulations are given to show that the proposed algorithm has a faster convergence performance and a stronger disturbance rejection performance by comparing to the PD control algorithm.

This article presents a tuned control algorithm for the speed and course of a four-wheeled automobile-type robot as a single nonlinear object, developed by the analytical approach of compensation for the object’s dynamics and additive effects. The method is based on assessment of external effects and as a result new, advanced feedback features may appear in the control system. This approach ensures automatic movement of the object with accuracy up to a given reference filter, which is important for stable and accurate control under various conditions. In the process of the synthesis control algorithm, an inverse mathematical model of the robot was built, and reference filters were developed for a closed-loop control system through external effect channels, providing the possibility of physical implementation of the control algorithm and compensation of external effects through feedback. This combined approach allows us to take into account various effects on the robot and ensure its stable control. The developed algorithm provides control of the robot both when moving forward and backward, which expands the capabilities of maneuvering and planning motion trajectories and is especially important for robots working in confined spaces or requiring precise movement into various directions. The efficiency of the algorithm is demonstrated using a computer simulation of a closed-loop control system under various external effects. It is planned to further develop a digital algorithm for implementation on an onboard microcontroller, in order to use the new algorithm in the overall motion control system of a four-wheeled mobile robot.

High demands for precision laser soldering technologies arise as digital devices move towards volume downsizing. Laser soldering is a very complicated thermodynamic chemical process, and controlling the temperature also becomes challenging. Based on experimental data, a thermodynamic model for the soldering process is developed in this study, taking into account variables like laser power, spot size, and heating duration, among others. A novel feedforward-PI control algorithm is proposed using the model which includes a target temperature curve-based feedforward algorithm to help the PI feedback control to achieve precise temperature control during the laser soldering process. Experiments and comparisons are used to demonstrate the efficacy of the suggested model and control approach. The outcomes show that the suggested model is capable of effectively describing the dynamics of laser soldering. The temperature standard deviation of the proposed control technique is shown to be lower than 55%-60% of the classic PID control approach, while the former has higher precision.

To address several challenges, including low efficiency, significant damage, and high costs, associated with the manual harvesting of Agaricus bisporus, in this study, a machine vision-based intelligent harvesting device was designed according to its agronomic characteristics and morphological features. This device mainly comprised a frame, camera, truss-type robotic arm, flexible manipulator, and control system. The FES-YOLOv5s deep learning target detection model was used to accurately identify and locate Agaricus bisporus. The harvesting control system, using a Jetson Orin Nano as the main controller, adopted an S-curve acceleration and deceleration motor control algorithm. This algorithm controlled the robotic arm and the flexible manipulator to harvest Agaricus bisporus based on the identification and positioning results. To confirm the impact of vibration on the harvesting process, a stepper motor drive test was conducted using both trapezoidal and S-curve acceleration and deceleration motor control algorithms. The test results showed that the S-curve acceleration and deceleration motor control algorithm exhibited excellent performance in vibration reduction and repeat positioning accuracy. The recognition efficiency and harvesting effectiveness of the intelligent harvesting device were tested using recognition accuracy, harvesting success rate, and damage rate as evaluation metrics. The results showed that the Agaricus bisporus recognition algorithm achieved an average recognition accuracy of 96.72%, with an average missed detection rate of 2.13% and a false detection rate of 1.72%. The harvesting success rate of the intelligent harvesting device was 94.95%, with an average damage rate of 2.67% and an average harvesting yield rate of 87.38%. These results meet the requirements for the intelligent harvesting of Agaricus bisporus and provide insight into the development of intelligent harvesting robots in the industrial production of Agaricus bisporus.