关键词： 协作机器人   动力学模型   模型误差补偿   循环神经网络   长短期记忆模型  

摘要： 由于协作机器人的结构比普通工业机器人更为轻巧,一般动力学模型所忽略的复杂特性占比较大,导致协作机器人的计算预测力矩误差较大.据此提出在考虑重力、科里奥利力、惯性力和摩擦力等的基础上,采用深度循环神经网络中的长短期记忆模型对自主研发的六自由度协作机器人动力学模型进行误差补偿.在实验中采用优化后的基于傅里叶级数的激励轨迹驱动机器人运动,以电机电流估算关节力矩,获取的原始数据用来训练长短期记忆模型(LSTM)补偿网络.网络的训练结果和评价指标为预测力矩相比实际力矩的均方根误差.计算与实验结果表明,补偿后的协作机器人动力学模型对实际力矩具有更好的预测效果,各轴预测力矩与实际力矩的均方根误差相比于未补偿的传统模型降低了61.8%至78.9%不等,表明了文中所提出补偿方法的有效性.

关键词： Group of rigid motions   Compactification   Robotics  

摘要： We introduce a compactification of the group of rigid motions in 3-space derived from the Study model for this group. We use this compactification in robot kinematics, by considering the boundary of the configuration space of a robot. We study in particular the degeneration of the direct kinematic problem for some parallel robots with three degrees of freedom. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Task analysis   Service robots   Collaboration   Resource management   Decision making   Symbiosis   Collaborative robots   fog computing   Industry 4   0   Internet of Things   robotic symbiotic network   task distribution  

摘要： Collaborative robots are an emerging area where robots share resources among each other for mutual benefit. They are particularly becoming popular in a modern industrial environment, primarily to improve production efficiency. This often involves some sort of decision making at the robots. Traditionally, the robots are connected to the cloud infrastructure and edge locations to offload compute-intensive tasks. But due to the dynamic workload generated and additional network delay, cloud, and edge locations are deemed unsuitable computing paradigms for use in industrial robots. In this article, we propose a symbiotic robotics framework where robots share their onboard computing capabilities for effective task offloading and its execution. Furthermore, the underlying symbiotic paradigm incorporates the concept of repute based on every successful task offloading and execution. The experimental results demonstrate a significant performance gain in terms of offloading time, task completion time, and overall efficiency when compared to two classical task offloading schemes.

关键词： Navigation   Robot kinematics   Shape control   Shape   Convergence   Robot sensing systems   Autonomous system   fault tolerance   obstacle avoidance   shape control   swarm robotics  

摘要： This article presents a geometrical region-based shape control methodology for navigating a cohesive swarm-robotic structure toward the goal even in a field occluded by unknown obstacles. In this control approach, initially, the robotic swarm is conceived to lie within a well-defined virtual circular region thus preserving a strict interagent cohesiveness among them. However, during the progression, for evading severely constricted obstacles, the virtual circle has been allowed to change its shape and in the process, varied elliptical shapes are made to evolve. In essence, for a collision-free solution, this shrinking aspect (from circle to ellipse) depends entirely on the number of agents in the swarm and at the same time also reliance on the sensed distance between two nearest obstacles through which the shrunken circle or the virtual ellipse will be able to pass. Consequently, shape switching is a dynamic as well as a stochastic process throughout the journey of the swarm. For achieving these objectives, a two-level hierarchical control strategy has been employed. Moreover, during aggregating toward the target, the actuation failure of any agent or agents may occur. In this perspective, the proposed control law has been updated adaptively throughout the route such that agent failure does not encumber the mission. Finally, the extensive simulation results along with the hardware experimentation are provided to demonstrate the efficacy of the proposed scheme.

关键词： Evolutionary robotics   Estimation-exploration algorithm   Neural network   Physics-based simulation   Information loss  

摘要： Theory of mind (ToM) is the ability to understand others' mental states (e.g., intentions). Studies on human ToM show that the way we understand others' mental states is very efficient, in the sense that observing only some portion of others' behaviors can lead to successful performance. Recently, ToM has gained interest in robotics to build robots that can engage in complex social interactions. Although it has been shown that robots can infer others' internal states, there has been limited focus on the data utilization of ToM mechanisms in robots. Here we show that robots can infer others' intentions based on limited information by selectively and flexibly using behavioral cues similar to humans. To test such data utilization, we impaired certain parts of an actor robot's behavioral information given to the observer, and compared the observer's performance under each impairment condition. We found that although the observer's performance was not perfect compared to when all information was available, it could infer the actor's mind to a degree if the goal-relevant information was intact. These results demonstrate that, similar to humans, robots can learn to infer others' mental states with limited information.

关键词： Control   Robotics   Mechatronics  

关键词： Chronic stroke   Dual-site transcranial direct current stimulation   Gait recovery   Robot-aided gait training  

摘要： Background Stroke is one of the main causes of impairment affecting daily activities and quality of life. There is a growing effort to potentiate the recovery of functional gait and to enable stroke patients to walk independently. Aim To estimate the effects of dual-site transcranial direct current stimulation (dstDCS) on gait recovery in chronic stroke patients provided with robot-aided gait training (RAGT). Methods Thirty-seven patients were included in this retrospective clinical study. Nine patients were provided with dstDCS during the first 10 min of RAGT by using Lokomat (R) Pro (on-RAGT), 15 patients immediately after RAGT (post-RAGT), and 13 patients immediately before RAGT (pre-RAGT). Results Each group improved over time concerning disability burden and lower limb strength. on-RAGT and post-RAGT experienced better improvement in balance (p < 0.001) and, moderately, gait endurance (p = 0.04) as compared to pre-RAGT. Furthermore, all treatments decreased the facilitation of the unaffected hemisphere (p < 0.001) and the inhibition of the affected hemisphere (p < 0.001). The duration of such aftereffects was found to be greater for post-RAGT. Discussion and conclusion This is the first trial with dstDCS coupled with RAGT in chronic stroke patients with gait impairment. When timely coupled with RAGT, dstDCS may be considered an effective tool for the recovery of lower limb function in patients with first unilateral stroke in the chronic phase. Moreover, our data suggest the ductility of dstDCS concerning RAGT timing, thus making this intervention suitable in a neurorehabilitation setting and well adaptable to patients' needs.

关键词： mobile robots   artificial potential fields   field lines of force   trajectory control  

摘要： In the well-known works devoted to the method of potential fields in mobile robotics, the key importance is attached to the mechanism of force influence on the movement of the robot;it determines the law of change in the velocity of its movement. In this article, a new methodology for using virtual fields is proposed: the force aspect is excluded and the lines of intensity of the created field set only the desired trajectories of the robot's movement, and following a given trajectory is carried out by a two-contour control system for the direction and velocity of the robot's movement. The question of constructing the attracting and repulsive potentials is discussed. The results of simulating the trajectory control of the two-wheeled robot are presented.

关键词： Dynamic task allocation   Communication topology   Swarm robotics  

摘要： Cooperation is a central idea to the usage of swarm robotics. It enables the solution of complex problems with a coordinated execution of simple tasks by a large group of small robot, which together lead to the achievement of the swarm common goal. This coordination is only possible with an efficient task allocation. Inspired by the strategy of the particle swarm optimization algorithm, we propose a novel algorithm called the Clustered Dynamic Task Allocation. This algorithm performs task allocation in a swarm robotic system in a fully distributed manner. It performs a guided search of the allocation space using the concept of adaptive speed. This search process requires information exchange between robots. This robot communication process must be planned carefully so as to achieve two conflicting objectives: the knowledge acquired by a given robot must flow throughout the swarm so that the optimization process may converge yet this communication must be limited so it does not hinder the efficiency of the task allocation process regarding large swarms. This paper proposes the use of a clustered communication topology between the swarm robots, aiming to optimize the underlying communication process, and thus enabling efficient task allocation for large robotic swarms. The results obtained with the cluster-based topology are compared to those obtained with the full mesh-based topology. On average, the results show a clear improvement in terms of execution time and battery charge requirements. Moreover, the performance of the proposed algorithm and the stability of the produced allocation are compared to other well-known models, demonstrating its better applicability to real-world swarm robotics based systems. (C) 2021 Elsevier B.V. All rights reserved.

关键词： Self-healing materials  

摘要： The intrinsic compliance of soft robots provides safety, a natural adaptation to its environment, allows to absorb shocks, and protects them against mechanical impacts. However, a literature study shows that the soft polymers used for their construction are susceptible to various types of damage, including fatigue, overloads, interfacial debonding, and cuts, tears and perforations by sharp objects. An economic and ecological solution is to construct future soft robotic systems out of self-healing polymers, incorporating the ability to heal damage. This review paper proposes criteria to evaluate the potential of a self-healing polymer to be used in soft robotic applications. Based on these soft robotics requirements and on defined performance parameters of the materials, linked to the mechanical and healing properties, the different types of self-healing polymers already available in literature are critically assessed and compared. In addition to a description of the state of the art on self-healing soft robotics, the paper discusses the driving forces and limitations to spur the interdisciplinary combination between self-healing polymer science and soft robotics.