A fixture is an arrangement of fixturing modules that locate and hold a workpart during a manufacturing operation. In this work we address the fixturing problem in the plane. We consider fixtures with frictionless poi...
详细信息
This paper presents novel contributions on image-based control of a mobile robot using a general catadioptric camera model. A catadioptric camera is usually made up by a combination of a conventional camera and a curv...
详细信息
The problem of features, objects, gestures, and face detection has been tackled using a numerous vision-based algorithms available in literature. Each of these algorithms requires a set of hyper-parameters, which need...
详细信息
A sub-millimeter scale coil is investigated as an alternative means to power electronics for small-scale robots. The AC voltage is induced by time-varying magnetic field. FEM analysis of employing magnetic field conce...
详细信息
This paper presents an algorithm for multi-agent strategic modeling (MASM) applied in a robotic soccer domain. It transforms a multi-agent action sequence into a set of strategic action descriptions in a graphical and...
详细信息
ISBN:
(纸本)1595933034
This paper presents an algorithm for multi-agent strategic modeling (MASM) applied in a robotic soccer domain. It transforms a multi-agent action sequence into a set of strategic action descriptions in a graphical and symbolic form. By using hierarchically ordered domain knowledge, the algorithm is able to generate graphic and symbolic strategic action descriptions together with corresponding rules at different levels of abstraction. The method was evaluated on the RoboCup Soccer Server Internet League data. Copyright 2006 ACM.
The problem of computing volumetric shape from stereo is examined. It is argued that intermediate two-and-one-half-dimensional dense or wire-frame descriptions may not be always possible from stereo, especially when t...
详细信息
We propose a new interprocessor communication network, named the Segmented Bus, for multiprocessor message passing computer architectures executing groups of processes with localized communication patterns and time va...
详细信息
In automated feature-based motion analysis of multiple frames, correspondence data are usually noisy and fragmented. A technique that gradually refines the initial noisy correspondence data and links fragments of a si...
详细信息
Legged robots have better performance on discontinuous terrain than that of wheeled robots. However, the dynamic trotting and balance control of a quadruped robot is still a challenging problem, especially when the ro...
详细信息
Legged robots have better performance on discontinuous terrain than that of wheeled robots. However, the dynamic trotting and balance control of a quadruped robot is still a challenging problem, especially when the robot has multi-joint legs. This paper presents a three-dimensional model of a quadruped robot which has 6 Degrees of Freedom (DOF) on torso and 5 DOF on each leg. On the basis of the Spring-Loaded Inverted Pendulum (SLIP) model, body control algorithm is discussed in the first place to figure out how legs work in 3D trotting. Then, motivated by the principle of joint function separation and introducing certain biological characteristics, two joint coordination approaches are developed to produce the trot and provide balance. The robot reaches the highest speed of 2.0 m.s-1, and keeps balance under 250 Kg.m.s-1 lateral disturbance in the simulations. The effectiveness of these approaches is also verified on a prototype robot which runs to 0.83 m.s-1 on the treadmill, The simulations and experiments show that legged robots have good biological properties, such as the ground reaction force, and spring-like leg behavior.
The analysis of overcrowded areas is essential for flow monitoring,assembly control,and *** counting’s primary goal is to calculate the population in a given region,which requires real-time analysis of congested scen...
详细信息
The analysis of overcrowded areas is essential for flow monitoring,assembly control,and *** counting’s primary goal is to calculate the population in a given region,which requires real-time analysis of congested scenes for prompt reactionary *** crowd is always unexpected,and the benchmarked available datasets have a lot of variation,which limits the trained models’performance on unseen test *** this paper,we proposed an end-to-end deep neural network that takes an input image and generates a density map of a crowd *** proposed model consists of encoder and decoder networks comprising batch-free normalization layers known as evolving normalization(EvoNorm).This allows our network to be generalized for unseen data because EvoNorm is not using statistics from the training *** decoder network uses dilated 2D convolutional layers to provide large receptive fields and fewer parameters,which enables real-time processing and solves the density drift problem due to its large receptive *** benchmark datasets are used in this study to assess the proposed model,resulting in the conclusion that it outperforms conventional models.
暂无评论