The underwater swimming manipulator is a new type of underwater vehicle manipulator composed of an underwater snake robot and several thrusters. In this paper, trajectory tracking control is considered for the underwa...
The underwater swimming manipulator is a new type of underwater vehicle manipulator composed of an underwater snake robot and several thrusters. In this paper, trajectory tracking control is considered for the underwater swimming manipulator with system constraints and uncertainties. Firstly, a linear model predictive controller with control input constraints is designed via feedback linearization to realize the constraints on joint torque and thruster forces. Secondly, the system uncertainties are estimated in real time based on the off-line Gaussian process regression and an adaptive extended state observer, and the estimated results are applied to the closed-loop control system for compensation. Finally, the stability of the closed-loop system is proved, and the simulation shows that the proposed method can realize the high-precision trajectory tracking control of the underwater swimming manipulator and meet the actual constraints when considering the system uncertainties.
The Stewart Platform, a sophisticated robotic mechanism known for its precision positioning and orientation in six degrees of freedom (6-DOF), is utilized as a testbed for the proposed solution. The unique design of t...
详细信息
ISBN:
(数字)9798350365740
ISBN:
(纸本)9798350365757
The Stewart Platform, a sophisticated robotic mechanism known for its precision positioning and orientation in six degrees of freedom (6-DOF), is utilized as a testbed for the proposed solution. The unique design of the platform, combining translational and rotational movements, makes it suitable for applications that demand high accuracy and rapid position and orientation adjustments. It is widely used in sectors like flight simulators, animatronics, underwater research, and medical devices. This research presents an innovative solution for the inverse kinematics problem of the Stewart platform parallel robot by synergistically integrating mathematical modeling and deep learning techniques. The study introduces a fusion of fully connected neural networks and mathematical models, harnessing the computational prowess and adaptability of deep learning and the precision of established mathematical theories.
Foot amputation can happen due to several factors and cause severe changes in the individual's gait pattern, reduces mobility and generates injuries. Over the past two decades, researchers have dedicated efforts t...
详细信息
Biomass pyrolysis has garnered significant attention as a sustainable energy production method utilizing various biomass feedstocks. Pyrolysate is any product generated from the pyrolysis process, including solid, liq...
详细信息
Colonoscopy is a widely used method for diagnosing bowel cancers, requiring coordinated efforts from medical professionals due to its invasive nature. In contrast, miniature capsule robots, measuring just a few centim...
Predictive modeling of industrial rotating equipment is difficult due to a number of implementation challenges. Existing approaches are not well-equipped to adapt to the range of degradation trends that industrial equ...
详细信息
Plastic is one of the most serious environmental threats. Plastic is a non-biodegradable substance that releases various hazardous compounds that cause cancer and other serious illnesses, as well as endangering aquati...
详细信息
Deep reinforcement learning, when combined with demonstrations, can effectively formulate policies for manipulators. However, the practical collection of ample high-quality demonstrations is time-consuming, and demons...
Deep reinforcement learning, when combined with demonstrations, can effectively formulate policies for manipulators. However, the practical collection of ample high-quality demonstrations is time-consuming, and demonstrations generated by humans may not perfectly correspond with the operational demands of robots. These challenges are intensified by issues such as non-Markovian processes and excessive reliance on demonstrations. Our study indicates that in manipulation tasks, reinforcement learning (RL) agents are sensitive to the quality of demonstrations and struggle to adapt to those derived from humans. As a result, leveraging low-quality or scarce demonstrations to assist reinforcement learning in developing superior policies presents a significant challenge. In some cases, dependence on limited demonstrations may paradoxically impair performance. To address these challenges, we propose a novel algorithm, TD3fG (TD3 learning from a generator). This algorithm facilitates a seamless transition from learning from experts to learning from experience, enabling agents to assimilate prior knowledge while mitigating the negative impacts of the demonstrations. Our algorithm demonstrates notable improvement in the Adroit manipulator and MuJoCo tasks, even with limited demonstrations of mixed failure trajectory.
暂无评论