As the size of the modules in a self-reconfiguring modular robotic system shrinks and the number of modules increases, the flexibility of the system as a whole increases. In this paper, we describe the manufacturing m...
详细信息
Deep Neural Networks, particularly Convolutional Neural Networks (ConvNets), have achieved incredible success in many vision tasks, but they usually require millions of parameters for good accuracy performance. With i...
详细信息
ISBN:
(数字)9781665490627
ISBN:
(纸本)9781665490627
Deep Neural Networks, particularly Convolutional Neural Networks (ConvNets), have achieved incredible success in many vision tasks, but they usually require millions of parameters for good accuracy performance. With increasing applications that use ConvNets, updating hundreds of networks for multiple tasks on an embedded device can be costly in terms of memory, bandwidth, and energy. Approaches to reduce this cost include model compression and parameter-efficient models that adapt a subset of network layers for each new task. This work proposes a novel parameter-efficient kernel modulation (KM) method that adapts all parameters of a base network instead of a subset of layers. KM uses lightweight task-specialized kernel modulators that require only an additional 1.4% of the base network parameters. With multiple tasks, only the task-specialized KM weights are communicated and stored on the end-user device. We applied this method in training ConvNets for Transfer Learning and Meta-Learning scenarios. Our results show that KM delivers up to 9% higher accuracy compared to other parameter-efficient methods on the Transfer Learning benchmark.
This paper addresses the problem of ship trajectory planning in a collision situation. The objectives of this paper are twofold. The first objective is to propose the optimal safe ship trajectory in collision situatio...
详细信息
This paper addresses the problem of ship trajectory planning in a collision situation. The objectives of this paper are twofold. The first objective is to propose the optimal safe ship trajectory in collision situation is presented as multistage decision-making in a fuzzy environment. The second objective is to use method based on the neural network to determine a safe ship trajectory planning. The maneuverability parameters of the ship and the navigator's subjective assessment in making a decision are taken under consideration in the process model.
Nowadays, additive manufacturing is becoming increasingly popular, cheap and easily accessible. It got particularly useful in industry. While the engineering designs need to be verified as quickly as it is possible, i...
详细信息
ISBN:
(纸本)9783030132736;9783030132729
Nowadays, additive manufacturing is becoming increasingly popular, cheap and easily accessible. It got particularly useful in industry. While the engineering designs need to be verified as quickly as it is possible, it is hardly unmanageable due to their high costs and a long time of production. 3-D printing enables a totally different approach towards these problems. This technique lets the mechanic apply the changes in a design on spot and test it under the real conditions. Even though it gives the crucial advantage of the price and the save of time, it brings some major problems as well. The 3-D printers offer the accuracy and precision limited to much lower standards than traditional machining. Moreover, the filaments used for the additive manufacturing have usually much worse material parameters than the most common metals. This study assesses the capabilities of the additive manufacturing in the production of the small elements for the tests. It is based on the real-life case of rapid prototyping of the grippers' precision jaws used for assembling the cylindrical objects in the casings. The paper contains an overview of grippers, 3-D printers and filaments, finite element strength tests and the summary of the method's potential. Its result is a method of creating models and testing fragile elements so to guarantee their coherence and to verify their applicability for the particular intent.
The paper presents a new approach to derivation of a linear model representing an approximation of dynamic response determined for a model estimated within discrete time identification. The approximation is calculated...
详细信息
The paper presents a new approach to derivation of a linear model representing an approximation of dynamic response determined for a model estimated within discrete time identification. The approximation is calculated using with new algorithm, that minimize the approximation error with application a non-quadratic performance index. The used performance index is quite close to the absolute norm of error, but has better convergence features. The recursive formula for derivation of the approximation model coefficients is derived and tested on two different examples of two dynamic processes.
Increased reticulospinal (RS) function has been observed to cause both positive and negative outcomes in the recovery of motor function after corticospinal lesions such as stroke. Current knowledge of RS function is l...
详细信息
ISBN:
(纸本)9781728127552
Increased reticulospinal (RS) function has been observed to cause both positive and negative outcomes in the recovery of motor function after corticospinal lesions such as stroke. Current knowledge of RS function is limited by the lack of accurate, noninvasive methods for measuring RS function. Recent studies suggest that the RS tract may be involved in processing and generating Long Latency Responses (LLRs). As such, LLRs, elicited by applying precisely controlled perturbations, can thus act as a reliable stimulus to measure brainstem function using fMRI with high signal-to-noise ratio. In this paper, we present StretchfMRI, a novel technique that enables simultaneous recording of neural and muscular activity during motor responses conditioned by robotic perturbations, which allows direct investigation of the neural correlates of LLRs. Via preliminary validation experiments, we demonstrate that our technique can reliably elicit and identify LLRs in two wrist muscles Flexor Carpi Radialis and Extensor Carpi Ulnaris. Moreover, via a single-subject pilot experiment, we show that the occurrence of an LLR in a flexor and extensor muscles modulates neural activity in distinct regions of the brainstem. The observed somatotopic organization is in agreement with the double reciprocal model of RS function observed in animal models, in which the right medullary and left pontine reticular formation are responsible for control of the motor activity in flexors and extensors, respectively.
We have developed new methods for the automated assembly of prototype structures and we illustrate them with the construction of a simple one DOF 5mm surgical wrist employing polyester flexures instead of revolute joi...
详细信息
We have developed new methods for the automated assembly of prototype structures and we illustrate them with the construction of a simple one DOF 5mm surgical wrist employing polyester flexures instead of revolute joints. The first step in the structural assembly involves the construction of hollow stainless steel triangular beams that are used for the rigid elements of the structure. It includes the development of a folding fixture to bend stainless steel sheets and the determination of a folding angle sequence by static analysis using a compliant mechanism model. The semi-automatic process of using a millirobot (Orthotweezers) to manipulate and assemble the beams and attach the flexures is described in detail. The paper ends with a description of the procedure used to design the wrist.
This paper presents the tinySLAM algorithm, which enables a mobile robot to perform automatic localization and mapping, called SLAM. Indeed, it is one of the essential bricks to build an autonomous robot that can evol...
详细信息
In order to improve the design efficiency of dress, to shorten the production cycle, and to meet the rapid design needs of customers for customized garments, a design method of dress for Mass Customization (MC) was pr...
详细信息
Time delay and delay jitter are the critical issues in system design of networked control systems (NCS). Aiming at the particularity of control network, the conceptions of loop-delay and network-delay are proposed in ...
详细信息
暂无评论