Vision‐audio fusion SLAM in dynamic environments

Moving humans,agents,and subjects bring many challenges to robot self‐localisation and environment perception.To adapt to dynamic environments,SLAM researchers typically apply several deep learning image segmentation models to eliminate these moving obstacles.However,these moving obstacle segmentation methods cost too much computation resource for the onboard processing of mobile robots.In the current industrial environment,mobile robot collaboration scenario,the noise of mobile robots could be easily found by on‐board audio‐sensing processors and the direction of sound sources can be effectively acquired by sound source estimation algorithms,but the distance estimation of sound sources is difficult.However,in the field of visual perception,the 3D structure information of the scene is relatively easy to obtain,but the recognition and segmentation of moving objects is more difficult.To address these problems,a novel vision‐audio fusion method that combines sound source localisation methods with a visual SLAM scheme is proposed,thereby eliminating the effect of dynamic obstacles on multi‐agent systems.Several heterogeneous robots experiments in different dynamic scenes indicate very stable self‐localisation and environment reconstruction performance of our method.

Visual SLAM in dynamic environments based on object detection

A great number of visual simultaneous localization and mapping(VSLAM)systems need to assume static features in the environment.However,moving objects can vastly impair the performance of a VSLAM system which relies on the static-world assumption.To cope with this challenging topic,a real-time and robust VSLAM system based on ORB-SLAM2 for dynamic environments was proposed.To reduce the influence of dynamic content,we incorporate the deep-learning-based object detection method in the visual odometry,then the dynamic object probability model is added to raise the efficiency of object detection deep neural network and enhance the real-time performance of our system.Experiment with both on the TUM and KITTI benchmark dataset,as well as in a real-world environment,the results clarify that our method can significantly reduce the tracking error or drift,enhance the robustness,accuracy and stability of the VSLAM system in dynamic scenes.

A novel algorithm for SLAM in dynamic environments using landscape theory of aggregation

To tackle the problem of simultaneous localization and mapping(SLAM) in dynamic environments, a novel algorithm using landscape theory of aggregation is presented. By exploiting the coherent explanation how actors form alignments in a game provided by the landscape theory of aggregation, the algorithm is able to explicitly deal with the ever-changing relationship between the static objects and the moving objects without any prior models of the moving objects. The effectiveness of the method has been validated by experiments in two representative dynamic environments: the campus road and the urban road.

Influence of static cartoons combined with dynamic virtual environments on preoperative anxiety of preschool-aged children undergoing surgery

BACKGROUND Preschoolers become anxious when they are about to undergo anesthesia and surgery,warranting the development of more appropriate and effective interventions.AIM To explore the effect of static cartoons combined with dynamic virtual environments on preoperative anxiety and anesthesia induction compliance in preschool-aged children undergoing surgery.METHODS One hundred and sixteen preschool-aged children were selected and assigned to the drug(n=37),intervention(n=40),and control(n=39)groups.All the children received routine preoperative checkups and nursing before being transferred to the preoperative preparation room on the day of the operation.The drug group received 0.5 mg/kg midazolam and the intervention group treatment consisting of static cartoons combined with dynamic virtual environments.The control group received no intervention.The modified Yale Preoperative Anxiety Scale was used to evaluate the children’s anxiety level on the day before surgery(T0),before leaving the preoperative preparation room(T1),when entering the operating room(T2),and at anesthesia induction(T3).Compliance during anesthesia induction(T3)was evaluated using the Induction Compliance Checklist(ICC).Changes in mean arterial pressure(MAP),heart rate(HR),and respiratory rate(RR)were also recorded at each time point.RESULTS The anxiety scores of the three groups increased variously at T1 and T2.At T3,both the drug and intervention groups had similar anxiety scores,both of which were lower than those in the control group.At T1 and T2,MAP,HR,and RR of the three groups increased.The drug and control groups had significantly higher MAP and RR than the intervention group at T2.At T3,the MAP,HR,and RR of the drug group decreased and were significantly lower than those in the control group but were comparable to those in the intervention group.Both the drug and intervention groups had similar ICC scores and duration of anesthesia induction(T3),both of which were higher than those of the control group.CONCLUSION Combining static cartoons with dynamic virtual environments as effective as medication,specifically midazolam,in reducing preoperative anxiety and fear in preschool-aged children.This approach also improve their compliance during anesthesia induction and helped maintain their stable vital signs.

DRO-SLAM: real-time object-aware SLAM for navigation robots and autonomous driving in dynamic environments

Traditional simultaneous localization and mapping(SLAM) mostly performs under the assumption of an ideal static environment, which is not suitable for dynamic environments in the real world. Dynamic real-time object-aware SLAM(DRO-SLAM) is proposed in this paper, which is a visual SLAM that can realize simultaneous localizing and mapping and tracking of moving objects indoor and outdoor at the same time. It can use target recognition, oriented fast and rotated brief(ORB) feature points, and optical flow assistance to track multi-target dynamic objects and remove them during dense point cloud reconstruction while estimating their pose. By verifying the algorithm effect on the public dataset and comparing it with other methods, it can be obtained that the proposed algorithm has certain guarantees in real-time and accuracy, it also provides more functions. DRO-SLAM can provide the solution to automatic navigation which can realize lightweight deployment, provide more vehicles, pedestrians and other environmental information for navigation.

Multi-Agent Dynamic Area Coverage Based on Reinforcement Learning with Connected Agents

Dynamic area coverage with small unmanned aerial vehicle(UAV)systems is one of the major research topics due to limited payloads and the difficulty of decentralized decision-making process.Collaborative behavior of a group of UAVs in an unknown environment is another hard problem to be solved.In this paper,we propose a method for decentralized execution of multi-UAVs for dynamic area coverage problems.The proposed decentralized decision-making dynamic area coverage(DDMDAC)method utilizes reinforcement learning(RL)where each UAV is represented by an intelligent agent that learns policies to create collaborative behaviors in partially observable environment.Intelligent agents increase their global observations by gathering information about the environment by connecting with other agents.The connectivity provides a consensus for the decision-making process,while each agent takes decisions.At each step,agents acquire all reachable agents’states,determine the optimum location for maximal area coverage and receive reward using the covered rate on the target area,respectively.The method was tested in a multi-agent actor-critic simulation platform.In the study,it has been considered that each UAV has a certain communication distance as in real applications.The results show that UAVs with limited communication distance can act jointly in the target area and can successfully cover the area without guidance from the central command unit.

Behavior-based Autonomous Navigation and Formation Control of Mobile Robots in Unknown Cluttered Dynamic Environments with Dynamic Target Tracking

While different species in nature have safely solved the problem of navigation in a dynamic environment, this remains a challenging task for researchers around the world. The paper addresses the problem of autonomous navigation in an unknown dynamic environment for a single and a group of three wheeled omnidirectional mobile robots(TWOMRs). The robot has to track a dynamic target while avoiding dynamic obstacles and dynamic walls in an unknown and very dense environment. It adopts a behavior-based controller that consists of four behaviors: "target tracking", "obstacle avoidance", "dynamic wall following" and "avoid robots". The paper considers the problem of kinematic saturation. In addition, it introduces a strategy for predicting the velocity of dynamic obstacles based on two successive measurements of the ultrasonic sensors to calculate the velocity of the obstacle expressed in the sensor frame. Furthermore, the paper proposes a strategy to deal with dynamic walls even when they have U-like or V-like shapes. The approach can also deal with the formation control of a group of robots based on the leader-follower structure and the behavior-based control, where the robots have to get together and maintain a given formation while navigating toward the target, avoiding obstacles and walls in a dynamic environment. The effectiveness of the proposed approaches is demonstrated via simulation.

Study of main factors influencing unsteady-state temperature drop in oil tank storage under dynamic thermal environment coupling

With the increasing oil demand, the construction of oil energy reserves in China needs to be further strengthened. However, given that there has been no research on the main influencing factors of crude oil temperature drop in storage tanks under actual dynamically changing environments, this paper considers the influence of dynamic thermal environment and internal crude oil physical properties on the fluctuating changes in crude oil temperature. A theoretical model of the unsteady-state temperature drop heat transfer process is developed from a three-dimensional perspective. According to the temperature drop variation law of crude oil storage tank under the coupling effect of various heat transfer modes such as external forced convection, thermal radiation, and internal natural convection, the external dynamic thermal environment influence zone, the internal crude oil physical property influence zone, and the intermediate transition zone of the tank are proposed. And the multiple non-linear regression method is used to quantitatively characterize the influence of external ambient temperature, solar radiation, wind speed, internal crude oil density, viscosity, and specific heat capacity on the temperature drop of crude oil in each influencing zone. The results of this paper not only quantitatively explain the main influencing factors of the oil temperature drop in the top, wall, and bottom regions of the tank, but also provide a theoretical reference for oil security reserves under a dynamic thermal environment.

Coal and gas outburst dynamic system

Coal and gas outburst is an extremely complex dynamic disaster in coal mine production process which will damage casualties and equipment facilities, and disorder the ventilation system by suddenly ejecting a great amount of coal and gas into roadway or working face. This paper analyzed the interaction among the three essential elements of coal and gas outburst dynamic system. A stress-seepage-damage coupling model was established which can be used to simulate the evolution of the dynamical system, and then the size scale of coal and gas outburst dynamical system was investigated. Results show that the dynam- ical system is consisted of three essential elements, coal-gas medium （material basis）, geology dynamic environment （internal motivation） and mining disturbance （external motivation）. On the case of CI 3 coal seam in Panyi Mine, the dynamical system exists in the range of 8-12 m in front of advancing face. The size scale will be larger where there are large geologic structures. This research plays an important guid- ing role for developing measures of coal and gas outburst prediction and prevention.

Grain-Size Distribution of Surface Sediments in the Bohai Sea and the Northern Yellow Sea: Sediment Supply and Hydrodynamics

The grain-size distribution of surface sediments in the Bohai Sea(BS) and the northern Yellow Sea(NYS), and its relationship with sediment supply and hydrodynamic environment were investigated based on grain-size compositions of surface sediments and modern sedimentation rates. The results showed that the surface sediments in the BS and the NYS were primarily composed of silty sand and clayey silt with a dominant size of silt. In addition, the Yellow River delivered high amount of water and sediments to the BS, and they are dominated in surface sediments(mainly silt) in the Bohai Bay, the Yellow River mouth, the center of the BS, and the north coast of Shandong Peninsula. The coarse-grained sediments were mainly deposited at the river mouth due to the estuarine filtration and physical sorting. Meanwhile, there was a significant relationship among the modern sedimentation rate, the surface sediment grain size distribution and sediment transport pattern. The areas with coarser surface sediments generally corresponded low sedimentation rates because of strong erosion;whereas the sedimentation rate was relatively high at the place that the surface sediments were fine-grained. Furthermore, the grain-size trend analysis showed that the areas with fine-grained surface sediments such as the mud area in the central BS and the upper Liaodong Bay were the convergent centers of surface sediments, except for the Bohai Bay and the subaqueous Yellow River Delta where offshore sediment transport was evident.

Weighted Time-Based Global Hierarchical Path Planning in Dynamic Environment

A weighted time-based global hierarchical path planning method is proposed to obtain the global optimal path from the starting point to the destination with time optimal control. First, the grid-or graph-based modeling is performed and the environment is divided into a set of grids or nodes. Then two time-based features of time interval and time cost are presented. The time intervals for each grid are built, during each interval the condition of the grid remains stable, and a time cost of passing through the grid is defined and assigned to each interval. Furthermore, the weight is introduced for taking both time and distance into consideration, and thus a sequence of multiscale paths with total time cost can be achieved. Experimental results show that the proposed method can handle the complex dynamic environment, obtain the global time optimal path and has the potential to be applied to the autonomous robot navigation and traffic environment.

Dynamic path planning strategy based on improved RRT^(*)algorithm

In order to solve the problem of path planning of mobile robots in a dynamic environment,an improved rapidly-exploring random tree^(*)(RRT^(*))algorithm is proposed in this paper.First,the target bias sampling is introduced to reduce the randomness of the RRT^(*)algorithm,and then the initial path planning is carried out in a static environment.Secondly,apply the path in a dynamic environment,and use the initially planned path as the path cache.When a new obstacle appears in the path,the invalid path is clipped and the path is replanned.At this time,there is a certain probability to select the point in the path cache as the new node,so that the new path maintains the trend of the original path to a greater extent.Finally,MATLAB is used to carry out simulation experiments for the initial planning and replanning algorithms,respectively.More specifically,compared with the original RRT^(*)algorithm,the simulation results show that the number of nodes used by the new improved algorithm is reduced by 43.19%on average.

Statistical landslide susceptibility assessment in a dynamic environment:A case study for Lanzhou City,Gansu Province,NW China

This study presents a statistical landslide susceptibility assessment(LSA) in a dynamic environment. The study area is located in the eastern part of Lanzhou, NW China. The Lanzhou area has exhibited rapid urbanization rates over the past decade associated with greening, continuous land use change, and geomorphic reshaping activities. To consider the dynamics of the environment in the LSA, multitemporal data for landslide inventories and the corresponding causal factors were collected. The weights of evidence(Wof E) method was used to perform the LSA. Three time stamps, i.e., 2000, 2012, and 2016, were selected to assess the state of landslide susceptibility over time. The results show a clear evolution of the landslide susceptibility patterns that was mainly governed by anthropogenic activities directed toward generating safer building grounds for civil infrastructure. The low and very low susceptibility areas increased by approximately 10% between 2000 and 2016. At the same time, areas of medium, high and very high susceptibility zones decreased proportionally. Based on the results, an approach to design the statistical LSA under dynamic conditions is proposed, the issues and limitations of this approach are also discussed. The study shows that under dynamic conditions, the requirements for data quantity and quality increase significantly. A dynamic environment requires greater effort to estimate the causal relations between the landslides and controlling factors as well as for model validation.

Dynamic environmentprediction of spacecraft usingdynamic substructuring

A low frequency dynamic environment prediction of spacecraft using dynamic substructu- ring is presented. The dynamic environment could be used to describe the level of the excitation on the spacecraft itself and auxiliary equipment. In addition, the dynamic environment is a criterion for the structural dynamic design as well as the ground verification test. The proposed prediction method could solve two major problems. The first is the time consumption of analyzing the whole spacecraft model due to the huge amount of degrees of freedom, and the second is multi-source for component structural dynamic models from distributive departments. To demonstrate the feasibility and efficien- cy, the proposed prediction method is applied to resolve a launching satellite case, and the results were compared with those obtained by the traditional prediction technology using the finite element method.

Research on the relationship between financial slack and R ＆ D investment in manufacturing industry under dynamic environment

As a part of the redundancy of organization, financial slack has become the focus of academic research. This paper takes the listed companies of manufacturing industry above Designated Size as sample, using multiple regression to examine the relationship between corporate financial slack and R ＆ D investment under dynamic environment, using the Malmquist index method based on DEA model to analyze the innovation efficiency of Chinese manufacturing industry during the period of2009-2013. The results show that： Financial slack and R ＆ D investment intensity presents inverted ＂U＂ type relationship in？sample？companies, and the relationship is positively regulated by environmental dynamism; Financial slack promotes R ＆ D investment but have lag effect.

Research on the relationship between financial slack and R ＆ D investment in manufacturing industry under dynamic environment

As a part of the redundancy of organization, financial slack has become the focus of academic research. This paper takes the listed companies of manufacturing industry above Designated Size as sample, using multiple regressionto examine the relationship between corporate financial slack and R ＆ D investment under dynamic environment, using the Malmquist index method based on DEA model to analyze the innovation efficiency of Chinese manufacturing industry during the period of 2009-2013. The results show that： Financial slack and R ＆ D investment intensity presents inverted ＂U＂ type relationship in？sample？companies, and the relationship is positively regulated by environmental dynamism; Financial slackpromotes R ＆ D investment but have lag effect.

Population,Environment Dynamics,Poverty and Quality of Life in China

Ｐｏｐｕｌａｔｉｏｎ，ＥｎｖｉｒｏｎｍｅｎｔＤｙｎａｍｉｃｓ，ＰｏｖｅｒｔｙａｎｄＱｕａｌｉｔｙｏｆＬｉｆｅｉｎＣｈｉｎａ￥／／ＢａｏｃｈａｎｇＧｕ；Ｐｈ．Ｄ．ＤｅｍｏｇｒａｐｈｉｃＤｉｌｅｍｍａｉｎＣｈｉｎａＴｈｅｐｏｐｕｌａｔｉｏｎｓｉｚｅｏｆＣ...

Magnetic Field-Based Reward Shaping for Goal-Conditioned Reinforcement Learning

Goal-conditioned reinforcement learning(RL)is an interesting extension of the traditional RL framework,where the dynamic environment and reward sparsity can cause conventional learning algorithms to fail.Reward shaping is a practical approach to improving sample efficiency by embedding human domain knowledge into the learning process.Existing reward shaping methods for goal-conditioned RL are typically built on distance metrics with a linear and isotropic distribution,which may fail to provide sufficient information about the ever-changing environment with high complexity.This paper proposes a novel magnetic field-based reward shaping(MFRS)method for goal-conditioned RL tasks with dynamic target and obstacles.Inspired by the physical properties of magnets,we consider the target and obstacles as permanent magnets and establish the reward function according to the intensity values of the magnetic field generated by these magnets.The nonlinear and anisotropic distribution of the magnetic field intensity can provide more accessible and conducive information about the optimization landscape,thus introducing a more sophisticated magnetic reward compared to the distance-based setting.Further,we transform our magnetic reward to the form of potential-based reward shaping by learning a secondary potential function concurrently to ensure the optimal policy invariance of our method.Experiments results in both simulated and real-world robotic manipulation tasks demonstrate that MFRS outperforms relevant existing methods and effectively improves the sample efficiency of RL algorithms in goal-conditioned tasks with various dynamics of the target and obstacles.

Task analysis approach based on perceptual control theory

Based on perceptual control theory,a task analysis approach is proposed to describe more accurately user tasks in dynamic environments,which is of more powerful and flexible descriptive ability. Theoretically,a task meta model is established to describe the interactive process in an individual,dynamic,and flexible way.Methodologically,an implementation framework is illustrated to map the user-oriented description into implementation-oriented models,which will be as a technical tool to transform from a task model to a user interface prototype.

Performance Analysis of Intelligent Robust Facility Layout Design

Design of a robust production facility layout with minimum handling cost （MHC） presents an appropriate approach to tackle facility layout problems in a dynamic volatile environment, in which product demands randomly change in each planning period. The objective of the design is to find the robust facility layout with minimum total material handling cost over the entire multiperiod planning horizon. This paper proposes a new mathematical model for designing robust machine layout in the stochastic dynamic environment of manufacturing systems using quadratic assignment problem （QAP） formulation. In this investigation, product demands are assumed to be normally distributed random variables with known expected value, variance, and covariance that randomly change from period to period. The proposed model was verified and validated using randomly generated numerical data and benchmark examples. The effect of dependent product demands and varying interest rate on the total cost function of the proposed model has also been investigated. Sensitivity analysis on the proposed model has been performed. Dynamic programming and simulated annealing optimization algorithms were used in solving the modeled example problems.