No description available.

This research investigates the ability of genetic programming to build profitable trad- ing strategies for the Foreign Exchange Market (FX) of one major currency pair (EURUSD) using one hour prices from July 1, 2009 to November 30, 2012. We rec- ognize that such environments are likely to be non-stationary and we do not expect that a single training partition, used to train a trading agent, represents all likely future behaviours. The proposed adaptive retraining algorithm – hereafter FXGP – detects poor trading behaviours and trains a new trading agent. This represents a significant departure from current practice which assumes some form of continuous evolution. Extensive benchmarking is performed against the widely used EURUSD currency pair. The non-stationary nature of the task is shown to result in a prefer- ence for exploration over exploitation. Moreover, adopting a behavioural approach to detecting retraining events is more effective than assuming incremental adaptation on a continuous basis. From the application perspective, we demonstrate that use of a validation partition and Stop-Loss (S/L) orders significantly improves the perfor- mance of a trading agent. In addition the task of co-evolving of technical indicators (TI) and the decision trees (DT) for deploying trading agent is explicitly addressed. The results of 27 experiments of 100 simulations each demonstrate that FXGP sig- nificantly outperforms existing approaches and generates profitable solutions with a high probability.

Yes / Purpose- Research on entrepreneurial orientation (EO) has concluded a positive link between EO and firm performance and that relationship depends on several contingencies. The paper derives insights from the absorptive capacity and contingency perspectives to introduce extraorganizational advice as a moderator of the relationship between EO and firm performance in a dynamic environment. Design/methodology/approach-Using survey data from 340 small and medium-sized enterprises (SMEs) in Ghana, the study examines the moderating influence of extraorganizational advice on the EO-firm performance relationship in dynamic environments. Findings-The study’s empirical findings suggest that extra-organizational advice amplifies the EO-performance relationship in dynamic environments. Research limitations/implications-The cross-sectional design of the study does not permit causal inferences to be made regarding the variables examined. Future studies may use longitudinal design to examine the causal links of the variables. Limitations aside, the study helps to answer how extra-organizational advice translates EO into improved performance in an environment characterised by constant flux. Practical implications- The results of this paper can assist entrepreneurs and policy-makers in understanding the dynamics and processes involved in implementing a strategic orientation to achieve higher performance. For SME managers, firm performance is determined by high levels of EO and extra-organizational advice in dynamic environments. The understanding of this issue can promote the development and maintenance of entrepreneurial ventures. Originality/value-The paper examines an important, but under-researched issue-the moderating effect of extra-organizational advice on the EO-performance relationship in dynamic environments. To the best of the authors’ knowledge, the present study pioneers research in this area.

Developing unsupervised vision systems in Dynamic Environments is one of the next challenges in Computer Vision. In Dynamic Environments, we usually lack the complete domain knowledge of the applied environments before deployment, and computation is also limited due to the need for prompt reaction and on-board computational capacity. This thesis studies a series of key Computer Vision problems in Dynamic Environments. <div><br></div><div>First, we propose a stream clustering algorithm and a number of variants for unsupervised feature learning and object discovery, which possess several crucial characteristics required by applications in Dynamic Environments, e.g. fully progressive, arbitrary similarity measure, matching object while the feature space is increasing, etc. We give strong provable guarantees of the clustering accuracy in statistic view. Based on the above the approaches, we tackle the problem of discovering aerial objects on-the-fly, where we assume all of the objects are unknown at the beginning of the deployment. The vision system is required to discover from the low-level features to salient objects on-the-fly without any supervision. We propose a number of approaches with respect to object proposal, tracking, recognition, and localization to achieve real-time performance. Extensive experiments on prevalent aerial video datasets showed that the approaches efficiently and accurately discover salient ground objects. </div><div><br></div><div>To explore complex and deep architectures in Dynamic Environments, we propose Unsupervised Deep Encoding which unifies traditional Visual Encoding and Convolutional Neural Networks. We found strong relationships between single-layer Neural Networks and Clustering and thus performed unsupervised feature learning at each layer from the feature maps of the previous layer. We replaced the dot product inside each neuron with a similarity measure, which is also used in unsupervised feature learning. The weight vectors of our network are initialized by cluster centers. Therefore, one feature map is a visual encoding of its previous feature map. We applied this mechanism to pre-training Convolutional Neural Networks for image classification. It has been found by extensive experiments that pre-training benefits the network more reliable learning dynamics (e.g.fast convergence without Batch Normalization) and better classification accuracy.</div>

The objectives of this research are to extend cooperative control methods based on potential games to dynamic environments and to develop an experimental test bed to illustrate theoretical results. Cooperative control concerns coordinating a collective performance of multiple autonomous agents. Possible applications include mobile sensor networks, distributed computation, and unmanned vehicle teams. Prior work has explored game theory, specifically the framework of potential games, as an approach to cooperative control, but has been restricted to static environments. This research shows that potential game based cooperative control also can be applied to dynamic environment problems. The approach is illustrated on three example problems. The first one is a moving target tracking problem using a modified form of the learning algorithm, restrictive log-linear learning. The second example is mobile sensor coverage for an unknown dynamic environment. The last example is multi-agent path optimization using payoff based learning. The performances of the developed systems are studied by simulation. The last part of this thesis develops an experimental moving target tracking system using multiple mobile robots. Finally, the thesis concludes with suggestions for future research directions.

Dynamic optimisation problems are problems where the search space does not remain constant over time. Evolutionary algorithms aimed at static optimisation problems often fail to effectively optimise dynamic problems. The main reason for this is that the algorithms converge to a single optimum in the search space, and then lack the necessary diversity to locate new optima once the environment changes. Many approaches to adapting traditional evolutionary algorithms to dynamic environments are available in the literature, but differential evolution (DE) has been investigated as a base algorithm by only a few researchers. This thesis reports on adaptations of existing DE-based optimisation algorithms for dynamic environments. A novel approach, which evolves DE sub-populations based on performance in order to discover optima in an dynamic environment earlier, is proposed. It is shown that this approach reduces the average error in a wide range of benchmark instances. A second approach, which is shown to improve the location of individual optima in the search space, is combined with the first approach to form a new DE-based algorithm for dynamic optimisation problems. The algorithm is further adapted to dynamically spawn and remove sub-populations, which is shown to be an effective strategy on benchmark problems where the number of optima is unknown or fluctuates over time. Finally, approaches to self-adapting DE control parameters are incorporated into the newly created algorithms. Experimental evidence is presented to show that, apart from reducing the number of parameters to fine-tune, a benefit in terms of lower error values is found when employing self-adaptive control parameters. / Thesis (PhD)--University of Pretoria, 2012. / Computer Science / unrestricted

[pt] Robôs moveis se tornaram populares nos últimos anos devido a sua capacidade de operar de forma autônoma e performar tarefas que são perigosas, repetitivas ou tediosas para seres humanos. O robô necessita ter um mapa de seus arredores e uma estimativa de sua localização dentro desse mapa para alcançar navegação autônoma. O problema de Localização e Mapeamento Simultâneos (SLAM) está relacionado com a determinação simultânea do mapa e da localização usando medidas de sensores. SLAM visual diz respeito a estimar a localização e o mapa de um robô móvel usando apenas informações visuais capturadas por câmeras. O uso de câmeras para o sensoriamento proporciona uma vantagem significativa, pois permite resolver tarefas de visão computacional que fornecem informações de alto nível sobre a cena, incluindo detecção, segmentação e reconhecimento de objetos. A maioria dos sistemas de SLAM visuais não são robustos a ambientes dinâmicos. Os sistemas que lidam com conteúdo dinâmico normalmente contem com métodos de aprendizado profundo para detectar e filtrar objetos dinâmicos. Existem vários sistemas de SLAM visual na literatura com alta acurácia e desempenho, porem a maioria desses métodos não englobam objetos desconhecidos. Este trabalho apresenta um novo sistema de SLAM visual robusto a ambientes dinâmicos, mesmo na presença de objetos desconhecidos. Este método utiliza segmentação panóptica para filtrar objetos dinâmicos de uma cena durante o processo de estimação de estado. A metodologia proposta é baseada em ORB-SLAM3, um sistema de SLAM estado-da-arte em ambientes estáticos. A implementação foi testada usando dados reais e comparado com diversos sistemas da literatura, incluindo DynaSLAM, DS-SLAM e SaD-SLAM. Além disso, o sistema proposto supera os resultados do ORB-SLAM3 em um conjunto de dados personalizado composto por ambientes dinâmicos e objetos desconhecidos em movimento. / [en] Mobile robots have become popular in recent years due to their ability to operate autonomously and accomplish tasks that would otherwise be too dangerous, repetitive, or tedious for humans. The robot must have a map of its surroundings and an estimate of its location within this map to achieve full autonomy in navigation. The Simultaneous Localization and Mapping (SLAM) problem is concerned with determining both the map and localization concurrently using sensor measurements. Visual SLAM involves estimating the location and map of a mobile robot using only visual information captured by cameras. Utilizing cameras for sensing provides a significant advantage, as they enable solving computer vision tasks that offer high-level information about the scene, including object detection, segmentation, and recognition. There are several visual SLAM systems in the literature with high accuracy and performance, but the majority of them are not robust in dynamic scenarios. The ones that deal with dynamic content in the scenes usually rely on deep learning-based methods to detect and filter dynamic objects. However, these methods cannot deal with unknown objects. This work presents a new visual SLAM system robust to dynamic environments, even in the presence of unknown moving objects. It uses Panoptic Segmentation to filter dynamic objects from the scene during the state estimation process. The proposed methodology is based on ORB-SLAM3, a state-of-the-art SLAM system for static environments. The implementation was tested using real-world datasets and compared with several systems from the literature, including DynaSLAM, DS-SLAM and SaD-SLAM. Also, the proposed system surpasses ORB-SLAM3 results in a custom dataset composed of dynamic environments with unknown moving objects.

The implementation of deep reinforcement learning in mobile robotics offers a great solution for the development of autonomous mobile robots to efficiently complete tasks and transport objects. Reinforcement learning continues to show impressive potential in robotics applications through self-learning and biological plausibility. Despite its advancements, challenges remain in applying these machine learning techniques in dynamic environments. This thesis explores the performance of Deep Q-Networks (DQN), using images as an input, for mobile robot navigation in dynamic maze puzzles and aims to contribute to advancements in deep reinforcement learning applications for simulated and real-life robotic systems. This project is a step towards implementation in a hardware-based system. The proposed approach uses a DQN algorithm with experience replay and an epsilon-greedy annealing schedule. Experiments are conducted to train DQN agents in static and dynamic maze environments, and various reward functions and training strategies are explored to optimize learning outcomes. In this context, the dynamic aspect involves training the agent on fixed mazes and then testing its performance on modified mazes, where obstacles like walls alter previously optimal paths to the goal. In game play, the agent achieved a 100\% win rate in both 4x4 and 10x10 static mazes, successfully making it to the goal regardless of slip conditions. The number of rewards obtained during the game-play episodes indicates that the agent took the optimal path in all 100 episodes of the 4x4 maze without the slip condition, whereas it took the shortest, most optimal path in 99 out of 100 episodes in the 4x4 maze with the slip condition. Compared to the 4x4 maze, the agent more frequently chose sub-optimal paths in the larger 10x10 maze, as indicated by the amount of times the agent maximized rewards obtained. In the 10x10 static maze game-play, the agent took the optimal path in 96 out of 100 episodes for the no slip condition, while it took the shortest path in 93 out of 100 episodes for the slip condition. In the dynamic maze experiment, the agent successfully solved 7 out of 8 mazes with a 100\% win rate in both original and modified maze environments. The results indicate that adequate exploration, well-designed reward functions, and diverse training data significantly impacted both training performance and game play outcomes. The findings suggest that DQN approaches are plausible solutions to stochastic outcomes, but expanding upon the proposed method and more research is needed to improve this methodology. This study highlights the need for further efforts in improving deep reinforcement learning applications in dynamic environments.

This thesis is concerned with the robots' motion planning problem. In particular it is focused on the path planning and motion planning for Autonomously Guided Vehicles (AGVs) in well-structured, two-dimensional static and dynamic environments. Two algorithms are proposed for solving the aforementioned problems. The first algorithm establishes the shortest collision-semi-free path for an AGV from its start point to its goal point, in a two-dimensional static environment populated by simple polygonal obstacles. This algorithm constructs and searches a reduced visibility graph, within the AGV's configuration space, using heuristic information about the problem domain. The second algorithm establishes the time minimal collision-semi-free motion for an AGV, from its start point to is goal point, in a two-dimensional dynamic environment populated by simple polygonal obstacles. This algorithm considers the AGV's spacetime configuration space, thus reducing the dynamic motion planning problem to the static path planning problem. A reduced visibility graph is then constructed and searched using information about the problem domain, in the AGV's space-time configuration space in order to establish the time-minimal motion between the AGV's start and goal configurations. The latter algorithm is extended to solve more complicated instances of the dynamic motion planning problem, where the AGV's environment is populated by obstacles, which change their size as well as their position over time and obstacles, which have piecewise linear motion. The proposed algorithms can be used to efficiently and safely navigate AGVs in well structured environments. For example, for the navigation of an AGV, in industrial environments, where it operates as part of the manufacturing process or in chemical and nuclear plants, where the hostile environment is inaccessible to humans. The main contributions in this thesis are, the systematic study of the V*GRAPH algorithm and identification of its methodic and algorithmic deficiencies; recommendation of corrections and further improvements on the V* GRAPH algorithm, which in turn lead to the proposition of the V*MECHA algorithm for robot path planning; proposition of the D*MECHA algorithm for motion planning in dynamic environments; extension to the D*MECHA algorithm to solve more complicated instances of the dynamic robot motion planning problem; discussion of formal proofs of the proposed algorithms' correctness and optimality and critical comparisons with existing similar algorithms for solving the motion planning problem.

The usage of Unmanned Aerial Vehicles (UAVs) to navigate autonomously in a dynamic environment is becoming more common. It is important that a UAV can generate collision-free trajectories and also be able to modify them to adapt to environment changes over the entire duration of navigation. The objective of this thesis is to present an optimized motion planning framework for UAV in dynamic environments. The proposed framework consists of two modules, which are optimized motion planner and dynamic scene generator. The optimized motion planner utilizes an asymptotically optimal sampling-based motion planning algorithm, RRTX, and extends RRTX with an optimizer based on Covariant Hamiltonian Optimization for Motion Planning (CHOMP) algorithm to optimize trajectories. A dynamic environment has obstacles that unpredictably appear, disappear or move. The optimized motion planner reacts to environment changes and finds collision-free trajectories during the navigation. Dynamic scene generator contains an obstacle information messenger and UAV simulator. This module is to simulate UAV, obstacles, and planned trajectories in a Unity scene. UAV simulator utilizes Flightmare, which is a flexible modular quadrotor simulator that contains a rendering engine built on Unity and a physics engine for dynamics simulation. The built framework is evaluated in simulations and the results show that the framework enables a UAV to navigate autonomously without colliding with any obstacles in dynamic environments. / Användningen av obemannade luftfarkoster för att navigera autonomt i dynamiska miljöer blir allt vanligare. Det är viktigt att en obemannade luftfarkost kan generera kollisionsfria banor och ändra dem för förändringar i miljöer under hela navigering. Detta examensarbete undersöker optimerad banplanering ramverket för obemannade luftfarkoster i dynamiska miljöer. Ramverket består av två delar: en optimerad banplanerare, och en dynamiska scen modul. Den optimerad banplaneraren använder en asymptotiskt optimala samplingsbaserade banplaneringsalgoritm, RRTX, och förlänger RRTX med en optimala lösning baserad på Covariant Hamiltonian Optimization for Motion Planning (CHOMP) algoritm för att optimera banor. En dynamiska miljö har hinder som oförutsägbart dyker upp, försvinner eller rör sig. Den optimerad banplaneraren reagerar på förändringar i miljöer och hittar kollisionsfria banor under navigeringen. Den dynamiska scen modulen består av en informationsbudbärare för hinder och en simulator för obemannade luftfarkoster. Denna modul ska simulera obemannade luftfarkoster, hinder och banor i en Unity scen. Den simulatorn för obemannade luftfarkoster använder Flightmare, som är en flexibel modulär simulator för quadrotorer. Flightmare består av en återgivningsmotor byggd på Unity och en fysikmotor för dynamiska simuleringar. Ramverket har testats i simuleringar. Resultat från simuleringar bekräftar att det ramverket gör att en obemannade luftfarkost kan navigera autonomt utan att kollidera med några hinder i dynamiska miljöer.