Inequality-based Manipulator-Obstacle Avoidance Using the LVI-based Primal-dual Neural Network

In reality, subnational governments suffer from moral hazard, creating uncertainty which, in turn, causes economic inefficiency. The behavior of subnational governments cannot be observed by the central government. An analysis which takes into account this phenomenon is therefore needed. Decentralization implies delegating authority from central government to subnational governments. In this study, the subnational government is represented by the local government. This study utilizes a model of principal-agent. The central government acts as a principal who delegates fiscal authority to subnational governments who act as agents. By applying principal-agent model, we can use the primal-dual approach to analyze both revenue and expenditure assignment associated with the tax effort of the subnational governments. The result from artificial neural network approach shows that asymmetric information between central and subnational governments exists in Indonesia.Keywords: Artificial Neural Network, Fiscal Decentralization, Local Tax Effort, Primal-Dual, Principal-Agent.

Download Full-text

Person classification leveraging Convolutional Neural Network for obstacle avoidance via Unmanned Aerial Vehicles

2017 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED-UAS) ◽

10.1109/red-uas.2017.8101662 ◽

2017 ◽

Author(s):

Shahmi Junoh ◽

Nabil Aouf

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Unmanned Aerial Vehicles ◽

Obstacle Avoidance ◽

Aerial Vehicles

Download Full-text

Bi-criteria velocity minimization of robot manipulators using LVI-based primal-dual neural network and illustrated via PUMA560 robot arm

Robotica ◽

10.1017/s0263574709005839 ◽

2009 ◽

Vol 28 (4) ◽

pp. 525-537 ◽

Cited By ~ 12

Author(s):

Yunong Zhang ◽

Kene Li

Keyword(s):

Neural Network ◽

Piecewise Linear ◽

Linear Structure ◽

Robot Arm ◽

Planning Scheme ◽

Primal Dual ◽

Joint Limits ◽

Joint Velocity ◽

High Computational Efficiency ◽

Minimization Scheme

SUMMARYIn this paper, to diminish discontinuity points arising in the infinity-norm velocity minimization scheme, a bi-criteria velocity minimization scheme is presented based on a new neural network solver, i.e., an LVI-based primal-dual neural network. Such a kinematic planning scheme of redundant manipulators can incorporate joint physical limits, such as, joint limits and joint velocity limits simultaneously. Moreover, the presented kinematic planning scheme can be reformulated as a quadratic programming (QP) problem. As a real-time QP solver, the LVI-based primal-dual neural network is developed with a simple piecewise linear structure and high computational efficiency. Computer simulations performed based on a PUMA560 manipulator model are presented to illustrate the validity and advantages of such a bi-criteria velocity minimization neural planning scheme for redundant robot arms.

Download Full-text