Nonlinear optimization techniques often suffer from time-consuming computational load, which impedes them to be implemented as controller of fast plans, or when a fast action like trajectory tracking is required. In t...
详细信息
ISBN:
(纸本)9781728137872
Nonlinear optimization techniques often suffer from time-consuming computational load, which impedes them to be implemented as controller of fast plans, or when a fast action like trajectory tracking is required. In this paper, a Nonlinear Model Predictive Control (NMPC) approach is used to perform the trajectory tracking problem in a robot manipulator in the presence of input saturation and un-modeled dynamics, using the Quasi-Linear Parameter Varying (Quasi-LPV) representation. In this method, instead of the nonlinear state difference equations of the system, a sequence of linearized state equations about a nominal state-control history, over the prediction horizon, is used. By so doing, standard Quadratic programming (QP) optimization algorithms could be used for the online optimization problem, therefore, speed and efficiency of convergence to the optimal solution would be enhanced. Efficacy of this method is shown by simulation study of a 2-DOF robot manipulator.
Autonomous driving functions increasingly incorporate machine learning methods for perception, environment modeling and decision making. the ever-present danger of unintended behavior of neural networks has given caus...
详细信息
ISBN:
(纸本)9781728156255
Autonomous driving functions increasingly incorporate machine learning methods for perception, environment modeling and decision making. the ever-present danger of unintended behavior of neural networks has given cause for concern in safety-critical applications and has spurred research towards the establishment of certified properties. In our work we present a general approach for exploring guaranteed properties of neural networks through a specific use case. We first methodically specified several desired properties for an ideal traffic sign classifier. then we applied a mixed integer linear programming verification method to certify (or conversely, falsify) that our pre-trained rectified linear unit (ReLU) activation network will satisfy given properties under all conditions. We established through relaxations of our initial specification that our model does in fact happen to guarantee certain (but not all) properties at a different threshold. We thus showed that it is possible to establish the degree to which non-trivial and humanly meaningful properties are inherently guaranteed by an arbitrary pixel space ReLU network. We believe this approach can be a helpful addition in comprehensively evaluating the reliability of a network via quantifying its degree of compliance to an ideal specification.
the proceedings contain 10 papers. the special focus in this conference is on international Symposium on Unifying theories of programming. the topics include: A Testing Perspective on Algebraic, Denotational, and Oper...
ISBN:
(纸本)9783030310370
the proceedings contain 10 papers. the special focus in this conference is on international Symposium on Unifying theories of programming. the topics include: A Testing Perspective on Algebraic, Denotational, and Operational Semantics;whither Specifications as Programs;connecting Fixpoints of Computations with Strict Progress;probabilistic Semantics for RoboChart: A Weakest Completion Approach;Unified Graphical Co-modelling of Cyber-Physical Systems Using AADL and Simulink/Stateflow;Hybrid Relations in Isabelle/UTP;the Inner and Outer Algebras of Unified Concurrency;developing an Algebra for Rely/Guarantee Concurrency: Design Decisions and Challenges.
Microtrips are the key in driving cycle, and the base for constructing a driving cycle. For the construction of a modal driving cycle, the study firstly used principal component analysis to reduce the dimensions of th...
详细信息
Microtrips are the key in driving cycle, and the base for constructing a driving cycle. For the construction of a modal driving cycle, the study firstly used principal component analysis to reduce the dimensions of the index data of microtrips, then a multi-objective optimization model was established withthe goal of minimizing the deviation between the feature of the vehicle modal driving cycle and the actual vehicle operating feature. the non-dominated sorting genetic algorithm-II (NSGA-II) was designed to save the optimization model. Based on the correlation test of actual data, the designed method can obtain highly representative solutions.
the proceedings contain 164 papers. the topic discussed include: initial learning scenarios based on the computational thinking evaluation for the course programming fundamentals at INACAP;interpretation of computatio...
ISBN:
(纸本)9781450371919
the proceedings contain 164 papers. the topic discussed include: initial learning scenarios based on the computational thinking evaluation for the course programming fundamentals at INACAP;interpretation of computational thinking evaluation results for enrollment prediction;learning computational thinking and social skills development in young children through problem solving with educational robotics;ringing computational thinking to hospital classrooms;predicting student failure in an introductory programming course with multiple back-propagation;engineering education addressing professional challenges;engaging students in the context of software project management teaching;a chatbot assistant for writing good quality technical reports;understanding uncertainties in thermographic imaging;3D printed models-based lab activities to enhance learning-teaching processes in structural engineering courses;the teaching of metrology the genesis and the epilogue of a degree;and learning object for contextualization of matrix operations in digital image processing through programming.
the major concern in the field of power system is the voltage stability and transmission efficiency. Many studies have been going on in this topic and the optimal reactive power dispatch (ORPD) problem is one of those...
详细信息
ISBN:
(数字)9781728176123
ISBN:
(纸本)9781728176130
the major concern in the field of power system is the voltage stability and transmission efficiency. Many studies have been going on in this topic and the optimal reactive power dispatch (ORPD) problem is one of those problems which help us to peruse in the direction towards obtaining a more economic and stable system. Here, the ORPD problem is solved to reduce the real power losses and total voltage deviation (TVD) of few particular standard IEEE bus system. the two objectives are solved individually considering it as a single objective function. In this paper, the ORPD problem is integrated with a photovoltaic (PV) system where the power from the solar energy is added withthe power from the existing conventional sources of energy, thus reducing the dependency on fossil fuels to some extent. this study has been done interpret the study of the PV integrated ORPD problem in solving the objective functions. this is mainly intended towards improving the efficiency and enhancing the security of the system. the problem is solved using different algorithms that are developed in the recent past, along withthe JAYA algorithm and are tested on IEEE 30 and 57 bus systems to minimize the above mentioned objective functions. the results obtained from the optimization techniques have been compared along with many other techniques reported in the literature to observe the superiority among them.
this paper presents the programming of a Bioloid robot to engage elderly to do 15 minutes' exercise routines divided into 3 parts: warm-up, conditioning and relaxation. this social assistive robot system reproduce...
详细信息
this paper presents a study focused on the implementation of functional maintenance targets for flexible runway pavements. Airports besides performing its function specified by the international Civil Aviation Organiz...
详细信息
Understanding the relationship between emotion and learning helps to improve the learning experience and learning performance. In order to examine the dynamics of emotional states and their relationship with learning ...
详细信息
ISBN:
(纸本)9781450366397
Understanding the relationship between emotion and learning helps to improve the learning experience and learning performance. In order to examine the dynamics of emotional states and their relationship with learning outcomes during learning Python, this study adopts correlation analysis, linear regression analysis and lag sequence analysis. the results show that: (1) among the seven academic emotions, positive confusion and engagement/flow are positively related with learning, while boredom and neutral are negatively related with learning. (2) Compared with low-achievement group, high-achievement group experienced more negative to positive confusion sequences, more delight, less frustration and boredom. therefore, teachers could provide supports to regulate students' confusion or boredom when teaching Python. Meanwhile, reducing negative confusion and inducing more other emotions could also improve teaching results.
Energy hole problem is one of the most important hot spots of the academic research in Wireless Sensor Networks. the proposed strategies of clustering focus on heuristically determining the cluster size rather than ob...
详细信息
Energy hole problem is one of the most important hot spots of the academic research in Wireless Sensor Networks. the proposed strategies of clustering focus on heuristically determining the cluster size rather than obtaining the optimal cluster radius for Wireless Sensor Networks and fall short in the application requirement of time-sensitive. To overcome these limitations, in this paper, the strategy of resolving energy hole with unequal cluster radius is proposed on basis of time-sensitive in heterogeneous WSNs. Firstly, we formulate the optimal model of non linear programming problem accorded withthe requirements of network lifetime and latency-time in heterogeneous network model. then, NLP problem is simplified by Lagrange-Newton method in order to prove that there is a feasible solution for the optimal model. In succession, an effective algorithm to obtain the optimal solutions of cluster radius is proposed after analyzing the characteristics of this optimal model theoretically so that it can be good practice guidance for deployment of heterogeneous WSNs. Finally, the simulation results demonstrate the performance advantages of our strategy.
暂无评论