Thunniform swimmers(tuna)have a swinging narrow sequence stalk and a moon-shaped tail fin,which performs poorly at slow speed,higher acceleration and turning maneuverability.In most cases,faster speed and higher maneu...Thunniform swimmers(tuna)have a swinging narrow sequence stalk and a moon-shaped tail fin,which performs poorly at slow speed,higher acceleration and turning maneuverability.In most cases,faster speed and higher maneuverability are mutually rejection for most marine creatures and their robotic opponents.This paper presents a novel hybrid tuna-like swimming robot for aquaculture water quality monitoring,which interleaves faster speed and higher maneuverability.The robotic prototype emphasizes on streamlining and enhanced maneuverability mechanism designs in conjunction with a narrow caudal propeller to the tail.The innovative design endows the robot to easily execute the multi-mode swimming gait,including forward swimming,turning,diving/surfacing.The capabilities of our robot are validated through a series of indoor swimming pool and field breeding ponds.The robotic fish can achieve a maximum speed up to about 1.16 m/s and a minimum turning radius less than 0.46 Body Lengths(BL)and its maximum turning speed can reach 78.6∘/s.Due to its high speed,maneuverability and relatively small size,the robotic fish shed light on intelligent monitoring in complex aquatic environments.展开更多
基金the National Key R&D Program of China(2022YFE0107100)the National Key R&D Programs of China(Grant No.2019YFD0901000)the National Natural Science Foundation of China(Grant No.61903007).
文摘Thunniform swimmers(tuna)have a swinging narrow sequence stalk and a moon-shaped tail fin,which performs poorly at slow speed,higher acceleration and turning maneuverability.In most cases,faster speed and higher maneuverability are mutually rejection for most marine creatures and their robotic opponents.This paper presents a novel hybrid tuna-like swimming robot for aquaculture water quality monitoring,which interleaves faster speed and higher maneuverability.The robotic prototype emphasizes on streamlining and enhanced maneuverability mechanism designs in conjunction with a narrow caudal propeller to the tail.The innovative design endows the robot to easily execute the multi-mode swimming gait,including forward swimming,turning,diving/surfacing.The capabilities of our robot are validated through a series of indoor swimming pool and field breeding ponds.The robotic fish can achieve a maximum speed up to about 1.16 m/s and a minimum turning radius less than 0.46 Body Lengths(BL)and its maximum turning speed can reach 78.6∘/s.Due to its high speed,maneuverability and relatively small size,the robotic fish shed light on intelligent monitoring in complex aquatic environments.
文摘粒子群优化(particle swarm optimization,PSO)算法是一种在机器人运动规划、信号处理等领域有广泛应用的优化算法。然而该算法易陷入局部最优解,从而导致早熟问题。出现早熟问题的原因之一是粒子群仅依靠适应度值选择学习范例。为了克服上述问题,提出了一种基于适应度值、改进率和新颖性混合驱动的PSO算法(particle swarm optimization algorithm based on hybrid driven by fitness values,improvement rate,and novelty,FINPSO)。在该算法中,引入的新指标和遗传算法会平衡种群的探索与开发,降低粒子群早熟的可能性。适应度值、改进率和新颖性会作为粒子的评价指标。各指标独立地选择学习范例并保存到不同的档案中。粒子每一次速度更新都要确定各个指标的权重,并从每个档案中选择一个范例学习。该算法采用了遗传算法进行粒子间的信息交流。遗传算法中的交叉互换和突变会给种群带来更多的随机性,提升种群的全局搜索能力。以八个PSO算法变体作为对比算法,两个CEC测试套件作为基准函数进行实验。实验结果表明,FINPSO算法优于已有的PSO算法变体达到最先进水平。