In this paper, we present a P300 model for control of Cerebot - a mind-controlled humanoid robot, including a procedure of acquiring P300 signals, topographical distribution analysis of P300 signals, and a classificat...
详细信息
Why is pedestrian detection still very challenging in realistic scenes? How much would a successful solution to monocular depth inference aid pedestrian detection? In order to answer these questions we trained a state...
详细信息
ISBN:
(纸本)9781479969357
Why is pedestrian detection still very challenging in realistic scenes? How much would a successful solution to monocular depth inference aid pedestrian detection? In order to answer these questions we trained a state-of-the-art deformable parts detector using different configurations of optical images and their associated 3D point clouds, in conjunction and independently, leveraging upon the recently released KITTI dataset. We propose novel strategies for depth upsampling and contextual fusion that together lead to detection performance which exceeds that of the RGB-only systems. Our results suggest depth cues as a very promising mid-level target for future pedestrian detection approaches.
This paper introduces a novel single DOF plane transition mechanism, designed to enable wheel based climbing robots to transit between perpendicular planes. The developed mechanism is composed of an arm with two revol...
详细信息
ISBN:
(纸本)9781479969357
This paper introduces a novel single DOF plane transition mechanism, designed to enable wheel based climbing robots to transit between perpendicular planes. The developed mechanism is composed of an arm with two revolute joints derived by a single motor. An innovative transmission mechanism is designed based on the required trajectory and relative position for each arm link, enabling individual or simultaneous rotation of the two joints during the transition movement. An electromagnetic unit which adapts to both flat and curved structures is also designed and integrated in the arm. This solution was installed on the omnidirectional climbing robot, OmniClimber. The mechanism was successfully tested on a curved structure with a diameter of 220mm.
isr-Softhand is a novel under-actuated self contained anthropomorphic robotic hand which takes advantage of elastic joints and soft pads. The integrated compliance in the hand's joint allows for a very good adapta...
详细信息
ISBN:
(纸本)9781479969357
isr-Softhand is a novel under-actuated self contained anthropomorphic robotic hand which takes advantage of elastic joints and soft pads. The integrated compliance in the hand's joint allows for a very good adaptability to a wide range of objects. It can achieve the top ten grasps with highest frequency of usage by humans, with only three actuators.
This paper presents a localization solution for the study of tagged marine animals (sources) based on direction and Doppler measurements. The source localization, in 3-D, is supported by a Portable Underwater Robotic ...
详细信息
This paper presents a localization solution for the study of tagged marine animals (sources) based on direction and Doppler measurements. The source localization, in 3-D, is supported by a Portable Underwater Robotic Tool (PURT), comprising a Ultra-Short Baseline (USBL) aided INS navigation system, carried by a diver (agent). Furthermore, a Surface Robotic Tool (SRT) provides the agent with its absolute position expressed in inertial coordinates. The observability of the system is studied and realistic simulation results are presented, in the presence of measurement noise.
This paper proposes a high-efficiency synchronous reluctance motor drive for the traction system of an electric vehicle. A vector control system, along with a maximum torque per ampere strategy was implemented taking ...
详细信息
This paper proposes a high-efficiency synchronous reluctance motor drive for the traction system of an electric vehicle. A vector control system, along with a maximum torque per ampere strategy was implemented taking into account the cross-magnetic saturation in the motor, to achieve a high- efficiency drive with a good dynamic behavior. Experimental results obtained in the laboratory, both in steady-state and transient regimes, demonstrate the feasibility and applicability of the developed control system for the target application.
This paper addresses the problem of keeping an autonomous marine vehicle in a moving triangular formation by regulating its position with respect to two leader vehicles. The follower vehicle has no prior knowledge of ...
详细信息
This paper studies the problem of identifying the minimum number of entities (agents), referred to as information gatherers, that are able to infer all the states in a dynamical social network. The information gathere...
详细信息
ISBN:
(纸本)9781479970896
This paper studies the problem of identifying the minimum number of entities (agents), referred to as information gatherers, that are able to infer all the states in a dynamical social network. The information gatherers can be, for instance, service providers and the remaining agents the clients, each comprising several dynamic states associated with the services and personal information. The problem of identifying the minimum number of information gatherers can constitute a way to create coalitions to oversee the entire state of the system, and consequently the behavior of the agents in the social network. The dynamical social network is assumed to be modelled as a linear time-invariant system, and we will make use of the structural systems concept, i.e., by considering only the sparsity pattern (location of zeroes/non-zeroes) of the system coupling matrix. As a consequence, the design guarantees derived hold for almost all numerical parametric realizations of the system. In this paper, we show that this problem is NP-hard: in addition, we provide a reduction of the coalition problem to a minimum set covering problem that, in practice, leads to efficient (polynomial complexity) approximation schemes for solving the coalition problem with guaranteed optimality gaps. Finally, an example is provided which illustrates the analytical findings.
This paper studies the problem of sensor placement design for efficient dynamic real-time state estimation in electric power networks. Given a (linearized) dynamic physical model of the power system, efficient sensor ...
详细信息
ISBN:
(纸本)9781479982981
This paper studies the problem of sensor placement design for efficient dynamic real-time state estimation in electric power networks. Given a (linearized) dynamic physical model of the power system, efficient sensor placement strategies are proposed that minimize the observability index of the system. The observability index plays a key role in determining the minimum window length of filters that guarantee stable estimation error and minimizing this index allows the design of memory and computationally efficient filtering schemes with performance guarantees. Specifically, given the system dynamics, the paper addresses the following two sensor placement design problems: (1) determining the minimal number and placement of sensors that achieves a certain desired system observability index, and (2) given the number of sensors to be deployed, obtaining the placement achieving minimal system observability index. These problems are addressed in a structural systems framework, i.e., the placement strategies are obtained on the basis of the sparsity pattern (location of zeroes/non-zeroes) of the system coupling matrix, and the design guarantees hold for almost all numerical parametric realizations of the system. Finally, an example is provided which illustrates the analytical findings.
The present paper describes exploratory work in which a Sparse Distributed Memory (SDM) was applied as a text classifier. The SDM is a type of associative memory based on the properties of high-dimensional spaces, whe...
详细信息
ISBN:
(纸本)9789881925282
The present paper describes exploratory work in which a Sparse Distributed Memory (SDM) was applied as a text classifier. The SDM is a type of associative memory based on the properties of high-dimensional spaces, where data are stored based on pattern similarity. The results obtained with the SDM are surprisingly good, for they can be achieved with little or none pre-processing. They are far superior to the performance of a "dumb classifier," though still inferior to the results obtained with other modern methods.
暂无评论