In this paper, a new local trajectory planning algorithm for center-articulated vehicles (CAVs) is proposed to generate safe and collision-free trajectories in structured or semistructured scenarios. the method is bas...
详细信息
In this paper, a self-tuning parameters control method for multi-USV formation based on a dual-channel BPNN-PID controller is presented. the kinematic model of USV is analyzed, and the leader-follower formation model ...
详细信息
ISBN:
(纸本)9798350373141;9798350373158
In this paper, a self-tuning parameters control method for multi-USV formation based on a dual-channel BPNN-PID controller is presented. the kinematic model of USV is analyzed, and the leader-follower formation model is developed. To adapt the PID controller parameters to the changing formation of unmanned surface vehicles, the self-learning and adaptive abilities of the BP neural network are utilized, a BP neural network self-tuning PID parameters method combining BP neural network with traditional PID control for multi-USV formation is proposed. Simulation experiments are conducted to demonstrate the controller's ability to achieve and maintain the multi-USV formation. the BPNN-PID controller saves time in parameter tuning, avoids the need for selecting PID parameters, and achieves the expected effect compared to the traditional PID controller.
this paper proposes an approach and workflow for autonomous control of implements and vehicles in agriculture. We introduce a control and communication concept for this purpose. the integrated behavior-based control a...
详细信息
Managing diabetes effectively is vital to prevent complications such as heart disease, nerve damage, and kidney issues. this research shows that weight control and tailored interventions can improve blood sugar and me...
详细信息
robotics, representing a synthesis of scientific knowledge, engineering creativity, and programming, is becoming increasingly demanded in educational practice. the author analyzes the results of their own research, ba...
详细信息
In this study, we explore the intricate task of executing a docking operation between two quadrotors, utilizing a blend of offline and online reinforcement learning techniques. this multifaceted task is fraught with t...
详细信息
ISBN:
(纸本)9798350373141;9798350373158
In this study, we explore the intricate task of executing a docking operation between two quadrotors, utilizing a blend of offline and online reinforcement learning techniques. this multifaceted task is fraught withthe catastrophic forgetting problem due to its multiple objectives: it necessitates precise control over the trajectory of the quadrotors, ensures their stability during the docking process, and maintains stable control post-docking. the complexity of these objectives presents significant challenges when applying reinforcement learning directly, often leading to unsuccessful outcomes. To navigate these challenges, we initially developed a rule-based expert controller and amassed a substantial dataset. Subsequently, we employed offline reinforcement learning to train a guided policy, which was then fine-tuned using online reinforcement learning. this approach effectively addressed the out-of-distribution issues typically encountered in online reinforcement learning with guided policies. Notably, our methodology significantly enhanced the success rate of the expert strategy, boosting it from 40% to an impressive 95%(1).
To address the challenges posed by restricted waters, uncertain model parameters, and strong environmental disturbances such as wind and currents during the harbor navigation of underactuated ships, this paper introdu...
详细信息
this paper proposes a bio-inspired jaw exoskeleton to provide therapeutic exercise for people suffering from jaw motion disability. the inspiration comes from two sides: the mechanism of the device and the control sch...
详细信息
the development of Artificial Intelligence (AI) technology has revolutionized various industries. However, the vulnerability of deep learning models, which are the core technology of AI, has been gradually exposed, am...
详细信息
Withthe advancement of technology and the growing demand for intelligent and efficient services, the traditional hotel service model is increasingly unable to meet people's expectations for personalized and non-c...
详细信息
暂无评论