Serwis Infona wykorzystuje pliki cookies (ciasteczka). Są to wartości tekstowe, zapamiętywane przez przeglądarkę na urządzeniu użytkownika. Nasz serwis ma dostęp do tych wartości oraz wykorzystuje je do zapamiętania danych dotyczących użytkownika, takich jak np. ustawienia (typu widok ekranu, wybór języka interfejsu), zapamiętanie zalogowania. Korzystanie z serwisu Infona oznacza zgodę na zapis informacji i ich wykorzystanie dla celów korzytania z serwisu. Więcej informacji można znaleźć w Polityce prywatności oraz Regulaminie serwisu. Zamknięcie tego okienka potwierdza zapoznanie się z informacją o plikach cookies, akceptację polityki prywatności i regulaminu oraz sposobu wykorzystywania plików cookies w serwisie. Możesz zmienić ustawienia obsługi cookies w swojej przeglądarce.
In order to accurately control the portable AUV, a dynamic modeling method based on computational fluid dynamics (CFD) and a improved Generalized Predictive Control (GPC) method were presented. First, the whole modeling process was described from two aspects: dynamic model derivation and model parameter identification. Second, the validity of the model and modeling method were tested by comparing...
During an oil spill, an accurate assessment of the trajectory of oil is important for a quick and effective remediation response. In the remote Arctic, oil fate and transport models are critical; especially during winter months when darkness and ice presence hamper visual detection of oil. A set of equations to describe the transport of oil in ice-covered waters and an environmental database were...
A software tool has been developed to simulate the entanglement of leatherback sea turtles (Dermochelys coriacea) in fishing and aquaculture gear. Entanglements are well documented and are increasing in frequency due to greater fishing effort and with the use of synthetic materials in marine applications. However relatively little is known about how entanglements occur and how they might be prevented...
Self-organized flocking behavior is often seen in nature in the form of flocks of sheep, herds of cow, fish schools, and swarms of insects. The shepherding problem is concerned with the control of such a group by a small number of guides and has useful applications. The present paper focuses on two unrelated control methods and the similarities between them. Based on these two control methods, we...
Most of the available robot programming by demonstration (PbD) approaches focus on learning a single task, in a given environmental situation. In this paper, we propose to learn multiple tasks together, within a common environment, using one of the available PbD approaches. Task-parameterized Gaussian mixture model (TP-GMM) is used at the core of the proposed approach. A database of TP-GMMs will be...
In this paper, we propose a CNN-based framework for online MOT. This framework utilizes the merits of single object trackers in adapting appearance models and searching for target in the next frame. Simply applying single object tracker for MOT will encounter the problem in computational efficiency and drifted results caused by occlusion. Our framework achieves computational efficiency by sharing...
In this paper, we introduce a cognitive model inspired in a rough description of the human cognition process to provide a more efficient parallel architecture for autonomous reactions in real systems. The model is a non-hierarchical structure composed of three main parallel blocks-mind, reason, action-in a nested double closed-loop configuration for control and supervision; the mind is a practical...
The paper treats a class of human walking robots, the athlete robot (AR). The dynamic equations of this model are generated by Euler Lagrange method as a multi-input-multi-output under-actuated model. The balancing control on one leg in the stance phase is studied. The hierarchical sliding mode control algorithm is proposed. Numerical simulations show the method efficiency.
This paper presents a solution with reduced computational complexity for path planning of a team of robots that should satisfy a mission expressed as a Boolean formula. It is assumed that the robots move in a partitioned environment containing some regions of interest. The robots should reach some final regions such that a Boolean formula expressed using the regions of interest is satisfied. Moreover,...
We introduce a general framework for visual forecasting, which directly imitates visual sequences without additional supervision. As a result, our model can be applied at several semantic levels and does not require any domain knowledge or handcrafted features. We achieve this by formulating visual forecasting as an inverse reinforcement learning (IRL) problem, and directly imitate the dynamics in...
In order to describe the inherent hysteresis nonlinearity of the piezo-actuated stages, a Krasnosel'skii-Pokrovskii (KP) model is presented in the paper. The parameters of the KP model are identified by a modified bat optimization algorithm based on Levy fights trajectory. The modified bat optimization algorithm uses the Levy fights trajectory to improve the global searching ability and break away...
The majority of existing solutions to the Multi-Target Tracking (MTT) problem do not combine cues over a long period of time in a coherent fashion. In this paper, we present an online method that encodes long-term temporal dependencies across multiple cues. One key challenge of tracking methods is to accurately track occluded targets or those which share similar appearance properties with surrounding...
Electric vehicles (EVs) are one of the key technolgies for a sustainable mobility, reducing fuel consumption and traffic related emissions. Until today the energy density of the traction battery is low compared to fossil fuels, resulting in a limited range of EVs. Therefore, an optimization of the overall energy consumption of an electric vehicle is crucial. This paper proposes an optimized velocity...
Given 2D discrete vector-geometric trajectories generated by a controllable, quarter-plane causal system, we identify an unfalsified Roesser model for it. We first compute state trajectories from the factorization of constant matrices directly constructed from the data; the A, B, C and D matrices of the Roesser model are then determined solving a system of linear equations involving the data and the...
Trajectory planning using Mixed Integer Linear Programming (MILP) is a powerful approach because vehicle dynamics and other constraints can be taken into account. However, it is currently severely limited by poor scalability. This paper presents a new approach which improves the scalability regarding the amount of obstacles and the distance between the start and goal positions. While previous approaches...
This work addresses a technique for robot motion planning and navigation in dynamic environments. First, a model to represent the future evolution of the moving obstacles in the environment is defined in a robocentric reference, which maps the obstacle motion on the control space, the velocity-time space, of the robot. Second, a planning technique working on that model for navigation and maneuvering...
The multi-agent monitoring (surveillance) problem over graphs is to find trajectories of multiple agents that travel each node as evenly as possible. This problem has several applications such as city safety management and disaster rescue. in our previously proposed method, the finite-time optimal surveillance problem was formulated, and was reduced to a mixed integer linear programming (MILP) problem...
In this paper, we consider parameter estimation in latent, spatiotemporal Gaussian processes using particle Markov chain Monte Carlo methods. In particular, we use spectral decomposition of the covariance function to obtain a high-dimensional state-space representation of the Gaussian processes, which is assumed to be observed through a nonlinear non-Gaussian likelihood. We develop a Rao-Blackwellized...
In this work we propose a framework for data-driven crowd simulation starting from a small set of trajectories. To model the macroscopic behavior, our method extracts pedestrian trajectories from real videos, clusters all trajectories of pedestrians who intend to reach the same goal, and computes the velocity field associated with each exit region in the scene to guide virtual agents toward their...
Appearance based multi-object tracking (MOT) is a challenging task, specially in complex scenes where objects have similar appearance or are occluded by background or other objects. Such factors motivate researchers to propose effective trackers which should satisfy real-time processing and object trajectory recovery criteria. In order to handle both mentioned requirements, we propose a robust online...
Podaj zakres dat dla filtrowania wyświetlonych wyników. Możesz podać datę początkową, końcową lub obie daty. Daty możesz wpisać ręcznie lub wybrać za pomocą kalendarza.