This paper addresses the problem of three-dimensional (3-D) waypoint tracking for a biomimetic underwater vehicle (BUV) propelled by undulatory fins: RobCutt-II. Based on the specific mechanical design and control sys...
详细信息
This paper addresses the problem of three-dimensional (3-D) waypoint tracking for a biomimetic underwater vehicle (BUV) propelled by undulatory fins: RobCutt-II. Based on the specific mechanical design and control system configuration, the RobCutt-II can perform diversified locomotion patterns, especially submerging or surfacing vertically in the water. For practical underwater operating procedures, a selective switching control for 3-D waypoint tracking is proposed. This control scheme contains a depth controller, a waypoint tracking controller, and a selector. When tracking a series of given 3-D waypoints, the RobCutt-II can switch between two closed-loop locomotion patterns, i.e., the depth control pattern and the waypoint tracking pattern. Simulations and a comparative experimental study demonstrate the feasibility and effectiveness of the proposed switching control scheme.
In an environment where robots coexist with humans, mobile robots should be human-aware and comply with humans' behavioural norms so as to not disturb humans' personal space and activities. In this work, we pr...
详细信息
In an environment where robots coexist with humans, mobile robots should be human-aware and comply with humans' behavioural norms so as to not disturb humans' personal space and activities. In this work, we propose an inverse reinforcement learning-based time-dependent A* planner for human-aware robot navigation with local vision. In this method, the planning process of time-dependent A* is regarded as a Markov decision process and the cost function of the time-dependent A* is learned using the inverse reinforcement learning via capturing humans' demonstration trajectories. With this method, a robot can plan a path that complies with humans' behaviour patterns and the robot's kinematics. When constructing feature vectors of the cost function, considering the local vision characteristics, we propose a visual coverage feature for enabling robots to learn from how humans move in a limited visual field. The effectiveness of the proposed method has been validated by experiments in real-world scenarios: using this approach robots can effectively mimic human motion patterns when avoiding pedestrians;furthermore, in a limited visual field, robots can learn to choose a path that enables them to have the larger visual coverage which shows a better navigation performance.
Most conventional microscopes can only acquire two-dimensional (2D) images. However, there is increasing demand for microscopes capable of acquiring three-dimensional (3D) images for use in biological research. To imp...
详细信息
Most conventional microscopes can only acquire two-dimensional (2D) images. However, there is increasing demand for microscopes capable of acquiring three-dimensional (3D) images for use in biological research. To improve observations of in vivo specimens, we develop a novel one snap-shot 3D light field microscope with high spatial resolution. By adding a lenslet array and focusing optics into the optical train of a conventional microscope, we are able to simultaneously capture seven sub-aperture images from different perspectives in a single shot, and finish 3D surface reconstruction of the specimen. In this paper, we present a functioning prototype of a novel 3D light field microscope using different objectives, and describe its design and image quality. During 3D image reconstruction, we use an optical flow method and back-projection interpolation to improve the resolution of the subimages. The performance of the novel light field microscope is analyzed theoretically and experimentally. Multiple perspective images are obtained using an objective with 20 x /NA 0.4. These images are 1050 x 1050 pixels with a depth of view of 200 mu m. For our microscope, the highest resolvable group of USAF 1951 target is about group 7.5. 3D reconstructions of various specimens are successfully created using these images. This novel microscopy system is suitable for various applications in 3D imaging and optical metrology. (C) 2017 Elsevier B.V. All rights reserved.
A computational model of visual cortex has raised great interest in developing algorithms mimicking human visual systems. The max-operation is employed in the model to emulate the scale and position invariant response...
详细信息
A computational model of visual cortex has raised great interest in developing algorithms mimicking human visual systems. The max-operation is employed in the model to emulate the scale and position invariant responses of the visual cells. We further extend this idea to enhance the tolerance of visual classification against the general intra-class variability. A general architecture of the basic block constituting the model is first presented. The architecture adaptively chooses the best matching template from a set of competing templates to predict the label of the incoming sample. To optimize the non-convex and non-smooth objective function resulted, we develop an algorithm to train each template alternately. Experiments show that the proposed method significantly outperforms linear classifiers as a template matching method in several image classification tasks, and is much more computationally efficient than other commonly used non-linear classifiers. In the image classification task on the Caltech 101 database, the performance of the biologically inspired model is obviously boosted by incorporating the proposed method. (C) 2014 Elsevier B.V. All rights reserved.
In this paper, a multiple-object tracking approach in large-scale scene is proposed based on visual sensor network. Firstly, the object detection is carried out by extracting the HOG features. Then, object tracking is...
详细信息
In this paper, a multiple-object tracking approach in large-scale scene is proposed based on visual sensor network. Firstly, the object detection is carried out by extracting the HOG features. Then, object tracking is performed based on an improved particle filter method. On the one hand, a kind of temporal and spatial dynamic model is designed to improve the tracking precision. On the other hand, the cumulative error generated from evaluating particles is eliminated through an appearance model. In addition, losses of the tracking will be incurred for several reasons, such as occlusion, scene switching and leaving. When the object is in the scene under monitoring by visual sensor network again, object tracking will continue through object re-identification. Finally, continuous multiple-object tracking in large-scale scene is implemented. A database is established by collecting data through the visual sensor network. Then the performances of object tracking and object re-identification are tested. The effectiveness of the proposed multiple-object tracking approach is verified.
For a class of unstable discrete-time multi-variable switched systems with parametric uncertainty, an identification scheme is developed in this paper. Specifically, the identification algorithm is derived to identify...
详细信息
This paper proposes a probably approximately correct (PAC) algorithm that directly utilizes online data efficiently to solve the optimal control problem of continuous deterministic systems without system parameters fo...
详细信息
This paper proposes a probably approximately correct (PAC) algorithm that directly utilizes online data efficiently to solve the optimal control problem of continuous deterministic systems without system parameters for the first time. The dependence on some specific approximation structures is crucial to limit the wide application of online reinforcement learning (RL) algorithms. We utilize the online data directly with the kd-tree technique to remove this limitation. Moreover, we design the algorithm in the PAC principle. Complete theoretical proofs are presented, and three examples are simulated to verify its good performance. It draws the conclusion that the proposed RL algorithm specifies the maximum running time to reach a near-optimal control policy with only online data.
In Still-to-Video (S2V) face recognition, only a few high resolution images are registered for each subject, while the probe is video clips of complex variations. As faces present distinct characteristics under differ...
详细信息
In Still-to-Video (S2V) face recognition, only a few high resolution images are registered for each subject, while the probe is video clips of complex variations. As faces present distinct characteristics under different scenarios, recognition in the original space is obviously inefficient. Thus, in this paper, we propose a novel discriminant analysis method to learn separate mappings for different scenario patterns (still, video), and further pursue a common discriminant space based on these mappings. Concretely, by modeling each video as a manifold and each image as point data, we form the scenario-oriented mapping learning as a Point-Manifold Discriminant Analysis (PMDA) framework. The learning objective is formulated by incorporating the intra-class compactness and inter-class separability for good discrimination. Experiments on the COX-S2V dataset demonstrate the effectiveness of the proposed method.
An investigation and outline of Metacontrol and Decontrol in Metaverses for control intelligence and knowledge automation are *** control with prescriptive knowledge and parallel philosophy is proposed as the starting...
详细信息
An investigation and outline of Metacontrol and Decontrol in Metaverses for control intelligence and knowledge automation are *** control with prescriptive knowledge and parallel philosophy is proposed as the starting point for the new control philosophy and technology,especially for computational control of metasystems in cyberphysical-social *** argue that circular causality,the generalized feedback mechanism for complex and purposive systems,should be adapted as the fundamental principle for control and management of metasystems with metacomplexity in ***,an interdisciplinary approach is suggested for Metacontrol and Decontrol as a new form of intelligent control based on five control metaverses:MetaVerses,MultiVerses,InterVerses,TransVerse,and DeepVerses.
Social networks often serve as a critical medium for information dissemination, diffusion of epidemics, and spread of behavior, by shared activities or similarities be- tween individuals. Recently, we have witnessed a...
详细信息
Social networks often serve as a critical medium for information dissemination, diffusion of epidemics, and spread of behavior, by shared activities or similarities be- tween individuals. Recently, we have witnessed an explosion of interest in studying social influence and spread dynamics in social networks. To date, relatively little material has been provided on a comprehensive review in this field. This brief survey addresses this issue. We present the current significant empirical studies on real social systems, including network construction methods, measures of network, and newly em- pirical results. We then provide a concise description of some related social models from both macro- and micro-level per- spectives. Due to the difficulties in combining real data and simulation data for verifying and validating real social sys- tems, we further emphasize the current research results of computational experiments. We hope this paper can provide researchers significant insights into better understanding the characteristics of personal influence and spread patterns in large-scale social systems.
暂无评论