the main objective of a standard reinforcement learner is usually defined as maximization of a scalar reward function given externally from the environment. On the other hand, an intrinsically motivated reinforcement ...
详细信息
the main objective of a standard reinforcement learner is usually defined as maximization of a scalar reward function given externally from the environment. On the other hand, an intrinsically motivated reinforcement learner creates an intrinsic reward function from its own criteria such as curiosity, prediction error, and learning progress. this paper proposes a novel approach to deal with both intrinsic and extrinsic rewards for reinforcement learning from a viewpoint of constrained optimization problem. the extrinsic rewards construct inequality constraints to the stochastic policy while the intrinsic reward determines the current objective function for the learning agent. By integrating policy gradient reinforcement learning algorithms and techniques used in nonlinear programming, our proposed method, named the constrained policy gradient reinforcement learning (CPGRL), maximizes the long-term average intrinsic reward under the inequality constraints induced by the extrinsic rewards. the CPGRL is successfully applied to a simple MDP problem and a control task of a robot arm.
this paper investigates the application of Embodied Intelligence (EI) in assistive technologies for the visually impaired (BLV) population. the study examines the challenges faced by BLV individuals, including mobilit...
详细信息
ISBN:
(数字)9798331541699
ISBN:
(纸本)9798331541705
this paper investigates the application of Embodied Intelligence (EI) in assistive technologies for the visually impaired (BLV) population. the study examines the challenges faced by BLV individuals, including mobility, information access, and social interaction, while identifying the limitations of existing assistive devices. A theoretical framework is proposed, integrating EI's core components—perception, decision-making, and action execution—to deliver adaptive and personalized solutions. To validate the framework, an experimental study was conducted using an EI prototype. Participants, including those with complete and partial blindness, were observed over 60 days, with data collected both before and after using the prototype. Results, analyzed through the Visual Functioning Subscale (VFS), demonstrated significant improvements in navigation, safety, and social engagement. this research highlights the transformative potential of EI in enhancing the independence and quality of life of BLV individuals while addressing critical ethical and societal considerations for its implementation.
Reinforcement Learning (RL) has become a pivotal tool in robotic manipulation, especially for tasks requiring adaptability, such as object grasping. By allowing robots to learn optimal behaviors through trial and erro...
详细信息
ISBN:
(数字)9798331516208
ISBN:
(纸本)9798331516215
Reinforcement Learning (RL) has become a pivotal tool in robotic manipulation, especially for tasks requiring adaptability, such as object grasping. By allowing robots to learn optimal behaviors through trial and error, RL, when integrated with advanced vision systems, enhances the ability of robots to interact effectively withtheir environment. this paper reviews the fundamental aspects of RL in robotic grasping, including perception, decision-making, and execution, and explores practical applications in frameworks like “Laboratory automation Plug and Play (LAPP)”. While significant advancements have been made, challenges such as sim-to-real transfer, computational efficiency, and robustness remain critical issues. Additionally, the role of vision systems in object detection and grasp planning is examined, along withthe evaluation of performance in simulated and real-world settings. the paper concludes by discussing future directions, emphasizing the need for improved algorithms, better sim-to-real techniques, and multi-agent cooperation. Overall, RL continues to advance autonomous robotic systems, enhancing their precision and capability in complex tasks.
Most human interactions withthe environment depend on our ability to navigate freely and to use our hands and arms to manipulate objects. Developing natural means of controlling these abilities in humanoid robots can...
详细信息
Most human interactions withthe environment depend on our ability to navigate freely and to use our hands and arms to manipulate objects. Developing natural means of controlling these abilities in humanoid robots can significantly broaden the usability of such platforms. An ideal interface for humanoid robot teleoperation will be inexpensive, person-independent, require no wearable equipment, and will be easy to use, requiring little or no user training. this work presents a new humanoid robot control and interaction interface that uses depth images and skeletal tracking software to controlthe navigation, gaze and arm gestures of a humanoid robot. To controlthe robot, the user stands in front of a depth camera and assumes a specific pose to initiate skeletal tracking. the initial location of the user automatically becomes the origin of the control coordinate system. the user can then use leg and arm gestures to turn the robot's motors on and off, to switch operation modes and to controlthe behavior of the robot. We present two control modes. the body control mode enables the user to controlthe arms and navigation direction of the robot using the person's own arms and location, respectively. the gaze direction control mode enables the user to controlthe focus of attention of the robot by pointing with one hand, while giving commands through gestures of the other hand. We present a demonstration of this interface, in which a combination of these two control modes is used to successfully enable an Aldebaran Nao robot to carry an object from one location to another. Our work makes use of the Microsoft Kinect depth sensor.
A knowledge of the inertia tensors and centre of gravity locations of rigid bodies and rigid mechanical systems is required in precise control of motion and in many other applications whenever the dynamics of them is ...
详细信息
ISBN:
(纸本)9781479952922
A knowledge of the inertia tensors and centre of gravity locations of rigid bodies and rigid mechanical systems is required in precise control of motion and in many other applications whenever the dynamics of them is significantly determined by these inertia parameters. this paper presents a new method for identifying the inertia tensor and coordinates of the centre of mass of a rigid body or of a rigid mechanical system. the proposed method is based on the work-energy principle and provides high accuracy of identification even on devices with essential dissipation. the tensor and centre of gravity location are defined on a single spherical motion - symmetric precession. the paper gives a survey of existing inertia parameter identification methods, the theoretical fundamentals of the proposed identification method, the hybrid identification device and data processing procedure with error estimation on dissipative systems using proposed and classical methods.
the application range of communication robots could be widely expanded by the use of an automatic speech recognition (ASR) system with improved robustness for noise and for speakers of different ages. In this paper, w...
详细信息
ISBN:
(纸本)1424401992
the application range of communication robots could be widely expanded by the use of an automatic speech recognition (ASR) system with improved robustness for noise and for speakers of different ages. In this paper, we describe an ASR system which can robustly recognize speech by adults and children in noisy environments. We evaluate the ASR system in a communication robot placed in a real noisy environment. Speech is captured using a twelve-element microphone array arranged in the robot chest. To suppress interference and noise and to attenuate reverberation, we implemented a multi-channel system consisting of an outlier-robust generalized sidelobe canceller (RGSC) technique and a feature-space noise suppression using MMSE criteria. Speech activity periods are detected using GMM-based end-point detection (GMM-EPD). Our ASR system has two decoders for adults' and children's speech. the final hypothesis is selected based on posterior probability. We then assign a generalized word posterior probability (GWPP)-based confidence measure to this hypothesis, and if it is higher than a threshold, we transfer it to a subsequent dialog processing module. the performance of each step was evaluated for adults' and children's speech, by adding different levels of real environment noise recorded in a cafeteria. Experimental results indicated that our ASR system could achieve over 80 % word accuracy in 70 dBA noise. Further evaluation of adult speech recorded in a real noisy environment resulted in 73 % word accuracy
Kubernetes is a portable, extensible, open-source platform for managing containers. It comes with features such as automatic scaling, service discovery, load balancing, fault tolerance, etc. Being such a complex syste...
详细信息
ISBN:
(纸本)9781728176505
Kubernetes is a portable, extensible, open-source platform for managing containers. It comes with features such as automatic scaling, service discovery, load balancing, fault tolerance, etc. Being such a complex system, which has a lot of internal services and withthe ability to manage a lot more user services, Kubernetes comes with a monitoring system, which provides metrics and logs for every service in the cluster. However, most of the time, the monitoring system needs human intervention for detection and troubleshooting defects. Human intervention usually occurs when it is too late, when a defect appears. We think that detecting anomalies in metrics provided by the monitoring system will help to prevent defects. In this paper, we analyze current solutions for automatic anomaly detection and alerting, and also we propose a new solution that will help system administrators to catch and predict anomalies earlier, which may lead to defects. Our solution, which is a technical one, is developed around Prometheus, an open-source monitoring system for metrics.
this paper provides guidelines for designing bus transit simulations and justifies the need of a qualitatively and quantitatively correct model that is validated and can serve as a benchmark testing platform for the n...
详细信息
this paper provides guidelines for designing bus transit simulations and justifies the need of a qualitatively and quantitatively correct model that is validated and can serve as a benchmark testing platform for the numerous optimisation strategies that researchers *** describes and comments on some of the most important contributions regarding bus transportation control and optimisation from a modelling ***,a case study concerning a bus line in Singapore is conducted where smart card data is used to extract the parameters needed in order to construct the model,while discussing the methods and challenges of this ***,the simulation is calibrated and validated in order to ensure maximum accuracy of its outputs.
the purpose of this study is to analyze the health and power quality analysis of motors installed at different blocks of Johar Town Lahore installed by Water and Sanitation Authority (WASA) Lahore. Induction motors ar...
详细信息
the purpose of this study is to analyze the health and power quality analysis of motors installed at different blocks of Johar Town Lahore installed by Water and Sanitation Authority (WASA) Lahore. Induction motors are the most important components of industries due to their cost-effectiveness, robustness and high efficiency. However, these motors are prone to some mechanical and electrical faults with time. Most of the faults are due to mismanagement of power and load variations. Usually, health monitoring and quality analysis of induction motors is laborious work. this study was conducted by keeping in mind the most widely used standards of the international Electro-technical Commission (IEC) and the Institute of Electrical and Electronics Engineer (IEEE). To enhance the effectiveness of the electrical systems, a detailed inspection and knowledge are needed for every power system. this technique involves taking measurements from motors in different states i.e. rest, transient and steady. the comparison of the results on different parameters withthe help of graphical data is presented in this study for the safe and economical use of machines. the study covers only seven motors out of 596 installed motors at tube well sites in the city of Lahore covering almost 8 million people. there is no existing system to analyze the performance, efficiency and health of these motors. this study may be helpful in quality assurance and save from critical failure that tends to disturb the water supply system. It can also beneficial of saving the cost of repair and plant's down time. It may be recommended to analyze thoroughly the remaining tube well motors for the beneficial of WASA water supply system.
the evolution of the telecommunication networks towards their 6th generation has emerged new research directions in order to deal withthe challenges that are posed by the high-complexity of the new infrastructure. In...
the evolution of the telecommunication networks towards their 6th generation has emerged new research directions in order to deal withthe challenges that are posed by the high-complexity of the new infrastructure. In this new era, the structuring of the network management infrastructure is a complex endeavor that should efficiently control both communication and computational resources. In this paper, we present a set of strategies for managing the computational load in a cell-free-based, converged optical-wireless 6G network. the proposed approaches target to controlthe computational load of a cell-free network, by either compressing the load by considering load-thresholds, or offloading the load to the SDN controller of the fixed network. Both strategies are mathematically formulated by considering traffic-engineering formulas, while their performance is evaluated by comparing analytical results with corresponding results from a baseline scenario, where no load control strategies are applied. Moreover, the proposed analysis can be applied in order to determine the capacity of the network controllers that is required in order to guarantee pre-determined Quality of Service requirements.
暂无评论