An intermittent controller for robotic manipulator in task space was developed in this paper.In task space,for given a desired time-varying trajectory,the robot end-effector can track the desired target under the desi...An intermittent controller for robotic manipulator in task space was developed in this paper.In task space,for given a desired time-varying trajectory,the robot end-effector can track the desired target under the designed intermittent controller.Different from most of the existing works on control of robotic manipulator,the intermittent control for robotic manipulator is discussed in task space instead of joint space.Besides,the desired trajectory can be time-varying and not limited to constant.As a direct application,the authors implemented the proposed controller on tracking of a two-link robotic manipulator in task space.Numerical simulations demonstrate the effectiveness and feasibility of the proposed intermittent control strategy.展开更多
空天地融合车载网场景下,无人机设备由于电池容量和能源有限,无法为任务卸载提供长期有效支持;低轨卫星受资源成本以及通信延迟、时延抖动的影响难以为大规模车联网任务提供稳定的高带宽通信服务。针对空天地融合车载网络场景下无人机...空天地融合车载网场景下,无人机设备由于电池容量和能源有限,无法为任务卸载提供长期有效支持;低轨卫星受资源成本以及通信延迟、时延抖动的影响难以为大规模车联网任务提供稳定的高带宽通信服务。针对空天地融合车载网络场景下无人机和低轨卫星的资源优化问题,提出了一种基于多任务深度强化辅助学习(Multi-Task Deep Reinforcement and Auxiliary Learning,MTDRAL)的任务卸载以及功率调整、缓存决策的方案。首先构建了任务切分与传输模型、时延模型、能耗模型、服务器计算与缓存模型和问题模型;然后,基于对任务处理时延、服务器能耗以及缓存命中率的综合考虑,给出了基于MTDRAL的任务卸载及资源调度方案;最后将所提方案与随机卸载策略方案、成功率贪婪决策方案、基于柔性动作-评价算法的多网络深度强化学习的卸载方案、基于深度确定性策略梯度算法的多网络深度强化学习的卸载方案进行了对比实验。实验结果表明:所提方案在服务器数量为14、车载终端数量为10时,综合得分相较于4种对比方案,分别领先约134.41%,31.32%,38.93%,29.49%;所提方案具有较好的性能,能更好地满足空天地融合车载网场景下的任务卸载需求。展开更多
基金the National Natural Science Foundation of China under Grant No.61603174the Natural Science Foundation of Fujian under Grant No.2020J01793。
文摘An intermittent controller for robotic manipulator in task space was developed in this paper.In task space,for given a desired time-varying trajectory,the robot end-effector can track the desired target under the designed intermittent controller.Different from most of the existing works on control of robotic manipulator,the intermittent control for robotic manipulator is discussed in task space instead of joint space.Besides,the desired trajectory can be time-varying and not limited to constant.As a direct application,the authors implemented the proposed controller on tracking of a two-link robotic manipulator in task space.Numerical simulations demonstrate the effectiveness and feasibility of the proposed intermittent control strategy.
文摘空天地融合车载网场景下,无人机设备由于电池容量和能源有限,无法为任务卸载提供长期有效支持;低轨卫星受资源成本以及通信延迟、时延抖动的影响难以为大规模车联网任务提供稳定的高带宽通信服务。针对空天地融合车载网络场景下无人机和低轨卫星的资源优化问题,提出了一种基于多任务深度强化辅助学习(Multi-Task Deep Reinforcement and Auxiliary Learning,MTDRAL)的任务卸载以及功率调整、缓存决策的方案。首先构建了任务切分与传输模型、时延模型、能耗模型、服务器计算与缓存模型和问题模型;然后,基于对任务处理时延、服务器能耗以及缓存命中率的综合考虑,给出了基于MTDRAL的任务卸载及资源调度方案;最后将所提方案与随机卸载策略方案、成功率贪婪决策方案、基于柔性动作-评价算法的多网络深度强化学习的卸载方案、基于深度确定性策略梯度算法的多网络深度强化学习的卸载方案进行了对比实验。实验结果表明:所提方案在服务器数量为14、车载终端数量为10时,综合得分相较于4种对比方案,分别领先约134.41%,31.32%,38.93%,29.49%;所提方案具有较好的性能,能更好地满足空天地融合车载网场景下的任务卸载需求。
