In order to study to design a photoelectric intelligent platform based on multifunctional edge computing equipment by using photoelectric detection equipment TC505C, RK-Series Development Kits computing platform and N...
详细信息
The application of learning-based control methods in robotics presents significant challenges. One is that model-free reinforcement learning algorithms use observation data with low sample efficiency. To address this ...
详细信息
ISBN:
(纸本)9798350377712;9798350377705
The application of learning-based control methods in robotics presents significant challenges. One is that model-free reinforcement learning algorithms use observation data with low sample efficiency. To address this challenge, a prevalent approach is model-based reinforcement learning, which involves employing an environment dynamics model. We suggest approximating transition dynamics with symbolic expressions, which are generated via symbolic regression. Approximation of a mechanical system with a symbolic model has fewer parameters than approximation with neural networks, which can potentially lead to higher accuracy and quality of extrapolation. We use a symbolic dynamics model to generate trajectories in model-based policy optimization to improve the sample efficiency of the learning algorithm. We evaluate our approach across various tasks within simulated environments. Our method demonstrates superior sample efficiency in these tasks compared to model-free and model-based baseline methods.
This research drew upon 987 construction inspection data points spanning from 1993 to 2023, sourced from the Taiwanese Public Construction Management Information System, to unveil the correlation between construction ...
详细信息
ISBN:
(数字)9783031700187
ISBN:
(纸本)9783031700170;9783031700187
This research drew upon 987 construction inspection data points spanning from 1993 to 2023, sourced from the Taiwanese Public Construction Management Information System, to unveil the correlation between construction elements and quality outcomes. Initially, fuzzy logic was employed to compute the weights of 499 defects, resulting in the identification of 25 pivotal construction factors based on these weight allocations. Subsequently, a deep neural network was deployed to discern the interrelation between these significant construction factors (input variables) and the resultant construction quality (output variable). The evaluation of the prediction model's performance substantiated the influence of these key construction factors on project outcomes. In line with the contemporary trend of intelligent industrial informatics, this study harnessed the application of machine learning to enable these systems to adapt and learn from historical data. The developed hybrid soft computing approach, amalgamating fuzzy logic and artificial neural networks, demonstrated an impressive accuracy rate of 95.95%. The insights gleaned from this research offer project managers actionable intelligence to enhance project management efficacy and establish robust construction management protocols, thereby elevating the overall construction quality of projects.
Supernumerary robotic limbs (SRLs) provide additional wearable limbs to enhance the user's physical abilities. Most SRLs employ rigid structures, resulting in uncomfortable wearing experience and insufficient flex...
详细信息
ISBN:
(纸本)9798350377712;9798350377705
Supernumerary robotic limbs (SRLs) provide additional wearable limbs to enhance the user's physical abilities. Most SRLs employ rigid structures, resulting in uncomfortable wearing experience and insufficient flexible manipulation. As a new type of SRL, soft SRLs offer operational flexibility, lightweight structure, and wearing safety, compensating for the shortcomings of rigid SRLs. However, due to the complex actuation mechanisms, soft SRLs pose challenges in multiple deformations and accurate controlling. In this paper, a soft SRL actuated by fiber-reinforced actuators (FRAs) is proposed. A kinematic model is established to capture the posture of the SRL. A control system is proposed to adjust the SRL posture precisely by configuration of the FRAs. Finally, the accuracy of the proposed control strategy is verified through experiments, and the SRL prototype exhibits flexibility and adaptability to various scenarios, effectively assisting users in accomplishing complex tasks.
In human-robot interaction (HRI) research, ball games pose significant challenges that demand robotic solutions that are both cost-effective and user-friendly for non-experts. Air hockey, characterized by safe, non-di...
详细信息
ISBN:
(纸本)9798350377712;9798350377705
In human-robot interaction (HRI) research, ball games pose significant challenges that demand robotic solutions that are both cost-effective and user-friendly for non-experts. Air hockey, characterized by safe, non-direct-contact play and a simplified state-action space, emerges as an ideal platform for such research. Despite the availability of various air hockey robots, their high cost and complexity have limited widespread use among researchers requiring robotics expertise. Addressing this gap, we introduce a low-cost, accessible air hockey robot designed to facilitate HRI studies. Featuring a lightweight five-bar linkage mechanism powered by low-cost servomotors for position control, this robot combines efficiency with ease of use. The complete robot's cost is estimated at $346.8, with the arm weighing a mere 19 grams. The robot precisely returns the puck by intermittently adjusting its target joint positions, achieving a play with an average return error of 42.6 mm. These characteristics affirm the robot's potential as a valuable tool for advancing HRI research.
This paper deals with the design of a low level controller for acceleration tracking using the vehicle's pedals. Its architecture aims at mimicking the various elements which are involved when a human is driving. ...
详细信息
ISBN:
(纸本)9798350364309;9798350364293
This paper deals with the design of a low level controller for acceleration tracking using the vehicle's pedals. Its architecture aims at mimicking the various elements which are involved when a human is driving. The focus is on providing an efficient and easy to deploy solution. This is achieved by using data collected from non tailored driving sessions and requiring basic vehicle's knowledge. This topic takes all its relevance in the context of autonomous driving where the focus is usually on features which provide high level requests such as acceleration. Performances are claimed under the tacit requirements that requests will be accurately tracked by a (real) vehicle. This is however a strong assumption with respects to chassis control challenges, wide deployment concerns and calibration by non experts. From a calibration perspective, the focus is on how to process data collected in a relatively uncontrolled way to automatically generate appropriate parameters. From a feedback design perspective, the challenge is to retain a performing yet easy to interpret controller structure. To illustrate the controller's performances, tests results obtained from real life experiments are presented.
Robot swarms hold immense potential for performing complex tasks far beyond the capabilities of individual robots. However, the challenge in unleashing this potential is the robots' limited sensory capabilities, w...
详细信息
ISBN:
(纸本)9798350377712;9798350377705
Robot swarms hold immense potential for performing complex tasks far beyond the capabilities of individual robots. However, the challenge in unleashing this potential is the robots' limited sensory capabilities, which hinder their ability to detect and adapt to unknown obstacles in real-time. To overcome this limitation, we introduce a novel robot swarm control method with an indirect obstacle detector using a smoothed particle hydrodynamics (SPH) model. The indirect obstacle detector can predict the collision with an obstacle and its collision point solely from the robot's velocity information. This approach enables the swarm to effectively and accurately navigate environments without the need for explicit obstacle detection, significantly enhancing their operational robustness and efficiency. Our method's superiority is quantitatively validated through a comparative analysis, showcasing its significant navigation and pattern formation improvements under obstacle-unaware conditions.
Access control is an important component of information security system. It protects resources from unauthorized users or misuses by authorized users. Yet, the security of cipher-based access control may be compromise...
详细信息
ISBN:
(纸本)9789819756025;9789819756032
Access control is an important component of information security system. It protects resources from unauthorized users or misuses by authorized users. Yet, the security of cipher-based access control may be compromised due to its fixed and predefined features. As an intelligentcomputing technology that simulates human behavior, trust evaluation can be an effective method for capturing users' unpredictable actions. Trust-based access control is a better method for tracking dynamic user behavior. Researchers are becoming increasingly enthusiastic in integrating intelligentcomputing concepts with access control. However, there is no article that covers all aspects of trust-based access control. Therefore, a comprehensive survey in this area of study is desperately needed. In this paper, we will investigate a novel approach to access control with trust. Access control is thus becoming more secure by incorporating trust evaluation. Furthermore, we will demonstrate how trust can be used to enhance access control secure by combining it with other intelligentcomputing technology like game theory.
Many application domains, e.g., in medicine and manufacturing, can greatly benefit from pneumatic Soft Robots (SRs). However, the accurate control of SRs has remained a significant challenge to date, mainly due to the...
详细信息
ISBN:
(纸本)9798350377712;9798350377705
Many application domains, e.g., in medicine and manufacturing, can greatly benefit from pneumatic Soft Robots (SRs). However, the accurate control of SRs has remained a significant challenge to date, mainly due to their nonlinear dynamics and viscoelastic material properties. Conventional control design methods often rely on either complex system modeling or time-intensive manual tuning, both of which require significant amounts of human expertise and thus limit their practicality. In recent works, the data-driven method, Automatic Neural ODE control (ANODEC) has been successfully used to - fully automatically and utilizing only input-output data - design controllers for various nonlinear systems in silico, and without requiring prior model knowledge or extensive manual tuning. In this work, we successfully apply ANODEC to automatically learn to perform agile, non-repetitive reference tracking motion tasks in a real-world SR and within a finite time horizon. To the best of the authors' knowledge, ANODEC achieves, for the first time, performant control of a SR with hysteresis effects from only 30 s of input-output data and without any prior model knowledge. We show that for multiple, qualitatively different and even out-of-training-distribution reference signals, a single feedback controller designed by ANODEC outperforms a manually tuned PID baseline consistently. Overall, this contribution not only further strengthens the validity of ANODEC, but it marks an important step towards more practical, easy-to-use SRs that can automatically learn to perform agile motions from minimal experimental interaction time.
This research aims to explore and develop original approaches for improving the scalability and efficiency of distributed network computingsystems. The escalating demand for high-performance computing and the widespr...
详细信息
ISBN:
(纸本)9783031671944;9783031671951
This research aims to explore and develop original approaches for improving the scalability and efficiency of distributed network computingsystems. The escalating demand for high-performance computing and the widespread integration of interconnected devices present a critical challenge in optimizing resource allocation and load balancing within distributed networks. The study will investigate cutting-edge algorithms, employ machine learning techniques, and devise adaptive strategies to dynamically distribute computing tasks across network nodes. The primary objective is to enhance system scalability, minimize response times, and maximize resource utilization, contributing significantly to the progression of network technologies in distributed computing environments. The research findings are expected to have substantial implications for various applications, including cloud computing, edge computing, and Internet of Things (IoT) ecosystems.
暂无评论