Policy-based monocular vision autonomous quadrotor obstacle avoidance method

Aiming at the obstacle avoidance control problem of small quadrotor, a method of quadrotor obstacle avoidance based on reinforcement learning is proposed. The proposed method can make training converge quickly and has good environmental robustness. The proposed methods include: (1) a framework adopts perception module and decision module to improve the generalization ability of the obstacle avoidance model; (2) An Actor-Critic framework-based Proximal Policy Optimization (PPO) algorithm to provide quadrotor with policy-based decision-making capabilities; The experimental simulation results show that the strategy-based framework converges quickly and has a high success rate, the training time is much lower than that of the value-based framework. The monocular vision observation ability is limited, which leads to deviations between local observation and global state, So LSTM layer is usually added to increase model performance. Policy -based decision can have a good obstacle avoidance effect without adding the LSTM layer, and have good generalization ability after short relearning after changing.

Immunized Token-Based Approach for Autonomous Deployment of Multiple Mobile Robots in Burnt Area

Collaborative exploration, sensing and communication in previously unknown environments with high network latency, such as outer space, battlefields and disaster hit areas are promising in multi-agent applications. When disasters such as large fires or natural disasters occur, previously established networks might be destroyed or incapacitated. In these cases, multiple autonomous mobile robots (AMR) or autonomous unmanned ground vehicles carrying wireless devices and/or thermal sensors can be deployed to create an end-to-end communication and sensing coverage to support rescue efforts or access the severity of damage. However, a fundamental problem is how to rapidly deploy these mobile agents in such complex and dynamic environments. The uncertainties introduced by the operational environment and wide range of scheduling problem have made solving them as a whole challenging. In this paper, we present an efficient decentralized approach for practical mobile agents deployment in unknown, burnt or disaster hit areas. Specifically, we propose an approach that combines methods from Artificial Immune System (AIS) with special token messages passing for a team of interconnected AMR to decide who, when and how to act during deployment process. A distributed scheme is adopted, where each AMR makes its movement decisions based on its local observation and a special token it receives from its neighbors. Empirical evidence of robustness and effectiveness of the proposed approach is demonstrated through simulation.

Distributed dynamic stochastic approximation algorithm over time-varying networks

In this paper, a distributed stochastic approximation algorithm is proposed to track the dynamic root of a sum of time-varying regression functions over a network. Each agent updates its estimate by using the local observation, the dynamic information of the global root, and information received from its neighbors. Compared with similar works in optimization area, we allow the observation to be noise-corrupted, and the noise condition is much weaker. Furthermore, instead of the upper bound of the estimate error, we present the asymptotic convergence result of the algorithm. The consensus and convergence of the estimates are established. Finally, the algorithm is applied to a distributed target tracking problem and the numerical example is presented to demonstrate the performance of the algorithm.

Study on atomization particle size characteristics of two-phase flow nozzle

Nozzle spray atomization is widely used in industrial and agricultural production processes and is a very complicated physical change. The spray atomization of the nozzle is a process in which the droplets are continuously broken into finer particles under the action of force, in order to study the effect of nozzle atomization, that is, droplet size distribution characteristics. The experimental average mathematical model of droplet size distribution was established by introducing the average diameter of Sutter (SMD). The droplet size distribution in the atomization field of the nozzle is studied by simulation. In the experimental study, the high-speed camera, external mixing air atomizing nozzle platform experimental device and image processing were used, and the atomization field was divided into multiple observation areas. Through the measurement of several local observation areas, the droplet size distribution of the whole atomization field is constructed. It provides a reference for the study of the atomization field of the nozzle and a basis for the intuitive understanding of the droplet size distribution in the atomization field of the nozzle. The effective atomization area of the nozzle atomization was selected to study the influence of the liquid flow rate, the liquid temperature and the nozzle pressure on the atomized particle size distribution of the externally mixed atomizing nozzle. The internal law is obtained, which provides a basis and reference for effectively controlling the atomization effect in the atomization field.

The Impact of GPS RO Data on the Prediction of Tropical Cyclogenesis Using a Nonlocal Observation Operator: An Initial Assessment

In this study, the impact of global positioning system (GPS) radio occultation (RO) data on the prediction of the genesis of 10 tropical cyclones over the western North Pacific Ocean is assessed. With the use of a nonlocal excess phase observation operator in cycling data assimilation, the probability of detection for tropical cyclogenesis is increased from 30% to 70% for the cases considered, all of which developed into typhoons. However, the probability of detection is only increased to 40% when a local observation operator is used, indicating that the observation operator can significantly influence the performance of RO data assimilation in capturing tropical cyclogenesis. A nonlocal excess phase operator, which considers the atmospheric horizontal gradients by integrating the refractivity along a ray path, gives superior performance over the local observation operator. Additional sensitivity experiments on 3 of the 10 typhoon cases show that the RO data in the vicinity of the incipient cyclones (within 500 km of the cyclone center) are most critical to successful cyclogenesis prediction. This reflects the fact that having good RO observations at the right time and place is critical for RO to have beneficial impacts on tropical cyclogenesis. Further analyses for Typhoon Nuri (2008) show that assimilation of RO data using the nonlocal operator leads to moistening of the lower and middle troposphere, organized convection, robust grid-scale vertical motions, and the development of midlevel relative vorticity, all of which are favorable for tropical cyclogenesis.

It's impolite to zoom in on global hydrological models

<p>Large scale or global hydrological models (GHMs) show promise in enabling us to accurately predict floods, droughts, navigation hazards, reservoir operations, and many more water related issues. As opposed to regional hydrological models that have many parameters that need to be calibrated or estimated using local observation data (Sood and Smakhtin 2015). GHMs are able to simulate regions that lack observation data, whilst applying a uniform approach for parameter estimation (Döll, Kaspar, and Lehner 2003; Widén‐Nilsson et al. 2009). Up until recently the GHMs used coarse modelling grids of around 0.5 to 1 degree spatial resolution. However, due to advances in satellite data, climate data, and computational resources, GHMs are modelling on higher resolutions (up to 200 meters) that raise questions about how these models can be adjusted in order to take advantage of the finer modelling grid.</p><p>In this study, we carry out an extensive assessment of how changes in spatial resolution affect the simulations of the Wflow SBM model for 8 basins in the Continental United States. This is done by comparing the model states and fluxes at three spatial resolutions, namely 3 km, 1km, and 200m. A hypothesis driven approach is used to investigate why changes in states and fluxes are taking place at different spatial resolutions and how they relate to model performance. The latter is determined by validating river discharge, snow extent, soil moisture, and actual evaporation. In addition, we make use of two sets of parameters that rely on different pedo-transfer functions. Further investigating the role parameterization in conjunction with changes in spatial resolution.</p><p>By carrying out this study within the eWaterCycle II framework we showcase our ability to handle large datasets (forcing and validation) whilst always complying to the FAIR principles. Furthermore, this study is setup in such that it is scalable in terms of case study areas and hydrological models.</p>

Point-actuated feedback control of multidimensional interfaces

We consider the application of feedback control strategies with point actuators to multidimensional evolving interfaces in order to stabilize desired states. We take a Kuramoto–Sivashinsky equation as a test case; this equation arises in the study of thin liquid films, exhibiting a wide range of dynamics in different parameter regimes, including unbounded growth and full spatiotemporal chaos. The controls correspond physically to mass-flux actuators located in the substrate on which the liquid film lies. In the case of partial state observability, we utilize a proportional control strategy where forcing at a point depends only on the local observation. We find that point-actuated controls may inhibit unbounded growth of a solution, if the actuators are sufficient in number and in strength, and can exponentially stabilize the desired state. We investigate actuator arrangements, and find that the equidistant case is the most favourable for control performance, with a large drop in effectiveness for poorly arranged actuators. Proportional controls are also used to synchronize two chaotic solutions. When the interface is fully observable, we construct model-based controls using the linearization of the governing equation. These improve on proportional controls and are applied to stabilize non-trivial steady and travelling wave solutions.

Research and Educational Centre for Rocket Building, Miass Branch, South Ural State University

The key aspect of radiation-proof manipulators used in nuclear industry is human presence in the manipulator control loop due to a wide variety of performed operations and the nondeterministic nature of the working environment. Relatively large distances between the control stations and the manipulators, imperfect visibility of the sealed chamber’s inner space from the control station necessitate the use of computer vision systems. They serve both for general chamber observation as well as local observation of the manipulator end-effector working area. High levels of radiation impose certain limitations on the primary video sensors with regard to radiation resistance and service life. This requires special technical solutions to ensure additional radiation protection as well as design and algorithmic ways of minimizing the influence of hazardous environment. Modern trends in digital manufacturing design are based on a system of unique identification of materials, package, etc. One of the technically viable ways is applying optical labels containing barcodes that are identified by algorithms. The article covers the design, structure, functional possibilities and experimental results of one of the radiation-proof manipulator vision systems. This system is designed for working together with radiation-proof robotic electromechanical manipulators installed in sealed chambers of nuclear plants.