Educational robotics is used not only in competitions but also in the regular educational process in schools. Teachers in different countries around the world include it according to the possibilities and limitations ...
详细信息
ISBN:
(纸本)9783031670589;9783031670596
Educational robotics is used not only in competitions but also in the regular educational process in schools. Teachers in different countries around the world include it according to the possibilities and limitations of the educational system. In Slovakia, it is most often included in the subject of computer science and therefore it is necessary for learners to be assessed in this subject unit as well. The question remains whether teachers know how to assess ER. And if not, can we advise them on appropriate assessment methods? Therefore, our research focused on the analysis of the current situation in Slovakia, where we carried out a survey questionnaire, the results of which were published last year, and subsequently conducted face to face interviews with selected teachers. These interviews were qualitatively processed. The results point to the findings that teachers reflect a lack of standardized assessment criteria to help them assess the quality of the program and robot design. They perceive possible bias in the assessment and various technical problems in the execution of the activities. These and many other challenges affect the overall teaching and learning experience and therefore the extent to which the stated learning objectives are met.
One of the major challenges in the design and construction of soft-rigid hybrid systems is having robust bonding at soft-rigid interfaces. Soft robots tend to be compliant and adaptive but weak, while rigid robots ten...
详细信息
ISBN:
(纸本)9798350381818
One of the major challenges in the design and construction of soft-rigid hybrid systems is having robust bonding at soft-rigid interfaces. Soft robots tend to be compliant and adaptive but weak, while rigid robots tend to be strong and precise but uncompromising. Soft-rigid hybrid systems can provide a blend of both compliant interactions with environments as well as fast and precise body position controls. In this paper, we propose a fabrication strategy using flocking to achieve strong bonding between soft and rigid parts. Flocking is a fabrication method that bonds short fibers to fabrics or plastics. The fibers create a fuzzy surface texture on rigid components, which increases the surface area. In the context of soft robotic molding, flocked surface texture increases mechanical bonding between soft and rigid components and enables incorporation of rigid components with increased complexity or challenging placement that could be overmolded but not glued. In this paper, we investigate design parameters for flocking such as substrate materials, adhesives, and flocking materials;we recommend design and fabrication guidelines for the use of flocking to incorporate printed ABS and PLA components in silicone. To demonstrate the utility of flocking in a range of soft systems, we have fabricated several example soft systems with integrated components, including a pneumatic network (pneu-net) actuator, soft chambers connected to semi-rigid tubing, and a sensorized soft actuator. The performance of these demonstrations was comparable or exceeded that of silicone glues and allows for direct overmolding of complex structures, making flocking applicable and versatile in soft-rigid hybrid systems.
Interpolation of rigid body motions, or a general frame motion in Euclidean space, is a recurring topic in robotics. It boils down to generating trajectories in a Lie group, either SE (3) or SO (3) x R-3, with given i...
详细信息
ISBN:
(纸本)9798350377712;9798350377705
Interpolation of rigid body motions, or a general frame motion in Euclidean space, is a recurring topic in robotics. It boils down to generating trajectories in a Lie group, either SE (3) or SO (3) x R-3, with given initial and/or terminal values. To this end, spline interpolation schemes were developed where canonical coordinates are represented by cubic splines. They allow for prescribing initial velocity and acceleration only. In many robotic applications, terminal conditions are prescribed, however. In this paper, a novel interpolation scheme is presented that admits prescribing the terminal pose, velocity and acceleration, or the initial condition. As example, the scheme is applied to a rendezvous task of a UAV and describing the deformation of a Cosserat beam as relevant for soft robotics. The presented interpolation scheme can be directly applied to the motion parameterization in terms of (dual) quaternions.
Reinforcement Learning (RL) has become a critical tool for optimization challenges within automation, leading to significant advancements in several areas. This review article examines the present landscape of RL with...
详细信息
ISBN:
(纸本)9798350358513;9798350358520
Reinforcement Learning (RL) has become a critical tool for optimization challenges within automation, leading to significant advancements in several areas. This review article examines the present landscape of RL within automation, with a particular focus on its roles in manufacturing, energy systems, and robotics. It delves into state-of-the-art methods, major challenges, and upcoming avenues of research within each sector, highlighting RL's capacity to solve intricate optimization challenges. The paper reviews the advantages and constraints of RL-driven optimization methods in automation. It points out prevalent challenges encountered in RL optimization, including issues related to sample efficiency and scalability;safety and robustness;interpretability and trustworthiness;transfer learning and meta-learning;and real-world deployment and integration. It further explores prospective strategies and future research pathways to navigate these challenges. Additionally, the survey includes an comprehensive list of relevant research papers, making it an indispensable guide for scholars and practitioners keen on exploring this domain.
This study investigates the H-infinity performance analysis of sampled-data systems (SDSs) with polytopic uncertainty. To better exploit the information on the sampling pattern, a sawtooth-characteristic-based free-ma...
详细信息
ISBN:
(纸本)9798350350319;9798350350302
This study investigates the H-infinity performance analysis of sampled-data systems (SDSs) with polytopic uncertainty. To better exploit the information on the sampling pattern, a sawtooth-characteristic-based free-matrix integral inequality and a second-order looped-functional are used to enhance the precision. Besides, to address the complex computation caused by high-order terms, the product of input delay and system states are also introduced as system variables. Then, stability criterion and the bounded real lemma for the H-infinity performance with less conservatism for the SDSs with polytopic uncertainty are yielded. Ultimately, the efficacy and advancement of the method are proved via a series of examples.
In manufacturing, minimizing operational delays is crucial for efficiency and resilience. Therefore, efficiently handling contingencies is essential in human-robot teams working on assembly (i.e., collaborative assemb...
详细信息
ISBN:
(纸本)9798350384581;9798350384574
In manufacturing, minimizing operational delays is crucial for efficiency and resilience. Therefore, efficiently handling contingencies is essential in human-robot teams working on assembly (i.e., collaborative assembly) applications. This paper introduces a novel approach to generating contingency handling procedures by leveraging recent advances in Large Language Models (LLMs). Our approach uses LLMs to update the required tasks in hierarchical task networks (HTNs) to handle contingencies. The results demonstrate that our approach can handle various contingencies in assembly applications and minimize the impact on the assembly completion time.
This paper details a reliable control method for highly nonlinear dynamical systems such as soft robots. We call this method model evolutionary gain-based predictive control or MEGa-PC. The method uses an evolutionary...
详细信息
ISBN:
(纸本)9798350381818
This paper details a reliable control method for highly nonlinear dynamical systems such as soft robots. We call this method model evolutionary gain-based predictive control or MEGa-PC. The method uses an evolutionary algorithm to optimize a set of controller gains via model predictive control. We demonstrate the performance of MEGa-PC in simulation for a single-link inverted pendulum and a three-link inverted pendulum, and on physical hardware for a three-joint continuum soft robot arm with six degrees of freedom. MEGa-PC is compared to prior work that used Nonlinear Evolutionary Model Predictive Control or NEMPC. The new method performs similarly to NEMPC in terms of accumulated cost over the entire trajectory, however, MEGa-PC generalizes better to real-world applications where safety is paramount, the dynamic model is uncertain, the system has significant latency, and where the previous sampling-based method (NEMPC) resulted in significant steady-state error due to model inaccuracy.
We consider the problem of tracking a reference trajectory for dynamical systems subject to a priori unknown state-dependent disturbance behavior. We propose a formulation that embeds the uncertain system into a highe...
详细信息
ISBN:
(纸本)9798350384581;9798350384574
We consider the problem of tracking a reference trajectory for dynamical systems subject to a priori unknown state-dependent disturbance behavior. We propose a formulation that embeds the uncertain system into a higher dimensional deterministic system that accounts for worst case disturbances. Our main insight is that a single controlled trajectory of this embedding system corresponds to a controlled forward invariant interval tube around the reference trajectory. By taking observations of the system, we then propose to estimate the state-dependent uncertainty with Gaussian Process regression, which improves the accuracy of the forward invariant tube as data is collected. Given a safety objective, we also provide conditions on when an additional observation of the unknown disturbance behavior needs to be collected to maintain safety. We demonstrate our formulation on a case study of a planar multirotor attempting a safe landing in an unknown wind field.
The parallel energy-efficient stabilization robotic systems are well-suited for large-load vibration reduction and stabilization operations. However, challenges arise, including uncertainties in environmental paramete...
详细信息
ISBN:
(纸本)9798350344646;9798350344639
The parallel energy-efficient stabilization robotic systems are well-suited for large-load vibration reduction and stabilization operations. However, challenges arise, including uncertainties in environmental parameters, nonlinear disturbances in pneumatic structures, and limitations in dynamic vibration reduction performance during vibration control. We propose a reference trajectory compensation approach based on dynamic pneumatic cylinder stiffness compensation and environmental parameter estimation to tackle the tracking force error problem in vibration reduction control. Additionally, dynamic adjustments are made through an adaptive damping parameter adjuster to enhance the dynamic performance of vibration reduction. The results indicate that the proposed vibration reduction control strategy effectively resolves the tracking force problem and achieves superior outcomes compared to the basic impedance control strategy in vibration reduction control.
Nonlinear Model Predictive Control (NMPC) is a state-of-the-art approach for locomotion and manipulation which leverages trajectory optimization at each control step. While the performance of this approach is computat...
详细信息
ISBN:
(纸本)9798350384581;9798350384574
Nonlinear Model Predictive Control (NMPC) is a state-of-the-art approach for locomotion and manipulation which leverages trajectory optimization at each control step. While the performance of this approach is computationally bounded, implementations of direct trajectory optimization that use iterative methods to solve the underlying moderately-large and sparse linear systems, are a natural fit for parallel hardware acceleration. In this work, we introduce MPCGPU, a GPU-accelerated, real-time NMPC solver that leverages an accelerated preconditioned conjugate gradient (PCG) linear system solver at its core. We show that MPCGPU increases the scalability and real-time performance of NMPC, solving larger problems, at faster rates. In particular, for tracking tasks using the Kuka IIWA manipulator, MPCGPU is able to scale to kilohertz control rates with trajectories as long as 512 knot points. This is driven by a custom PCG solver which outperforms state-of-the-art, CPU-based, linear system solvers by at least 10x for a majority of solves and 3.6x on average.
暂无评论