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.

Genesis of the Cenozoic Sodic Alkaline Basalt in the Xiahe–Tongren Area of the Northeastern Tibetan Plateau and its Continental Dynamic Implications

Objective The Cenozoic Indo-Asian collision caused significant crustal shortening and plateau uplift in the central Tibet. The extrusion tectonic model has been widely accepted to explain the strike-slip faults around the Tibetan Plateau. Previous studies indicate that the lower crust flow is the main drive force of the extrusion tectonics. Whether mantle extrusion process occurred during the Cenozoic uplift is a major problem to be addressed, which is significant for understanding the uplift mechanism and tectonic evolution of the Tibetan Plateau.

Assessment of multifunctional landscapes dynamics in the mountainous basin of the Mo River （Togo, West Africa）

In this study, historical landscape dynamics were investigated to（i） map the land use/cover types for the years 1972, 1987, 2000 and 2014;（ii） determine the types and processes of landscape dynamics; and（iii） assess the landscape fragmentation and habitat loss over time. Supervised classification of multi-temporal Landsat images was used through a pixel-based approach. Post–classification methods included systematic and random change detection, trajectories analysis and landscape fragmentation assessment. The overall accuracies（and Kappa statistics） were of 68.86%（0.63）, 91.32%（0.79）, 90.66%（0.88） and 91.88%（0.89） for 1972, 1987, 2000 and 2014, respectively. The spatio-temporal analyses indicated that forests, woodlands and savannahs dominated the landscapes during the four dates, though constant areal decreases were observed. The most important dynamic process was the decline of woodlands with an average annual net loss rate of –2%. Meanwhile, the most important land transformation occurred during the transition 2000–2014, due to anthropogenic pressures. Though the most important loss of vegetation greenness occurred in the unprotected areas, the overall analyses of change indicated a declining trend of land cover quality and an increasing landscape fragmentation. Sustainable conservation strategies should be promoted while focusing restoration attention on degraded lands and fragmented ecosystems in order to support rural livelihood and biodiversity conservation.

Grasping Strategy in Space Robot Capturing Floating Target

When the space robot captures a floating target, contact impact occurs inevitably and frequently between the manipulator hand and the target, which seriously impacts the position and attitude of the robot and grasping security. ＂Dynamic grasping area＂ is introduced to describe the collision process of manipulator grasping target, and grasping area control equation is established. By analyzing the impact of grasping control parameters, base and target mass on the grasping process and combining the life experience, it is found that if the product of speed control parameter and dB adjustment parameter is close to but smaller than the minimum grasping speed, collision impact in the grasping process could be reduced greatly, and then an ideal grasping strategy is proposed. Simulation results indicate that during the same period, the strategy grasping is superior to the accelerating grasping, in that the amplitude of impact force is reduced to 20%, and the attitude control torque is reduced to 15%, and the impact on the robot is eliminated significantly. The results would have important academic value and engineering significance.

Breakthrough CO_2 adsorption in bio-based activated carbons

In this work, the effects of different methods of activation on CO2 adsorption performance of activated carbon were studied. Activated carbons were prepared from biochar, obtained from fast pyrolysis of white wood, using three different activation methods of steam activation, CO2 activation and Potassium hydroxide（KOH） activation. CO2 adsorption behavior of the produced activated carbons was studied in a fixed-bed reactor set-up at atmospheric pressure, temperature range of 25–65°C and inlet CO2 concentration range of10–30 mol% in He to determine the effects of the surface area, porosity and surface chemistry on adsorption capacity of the samples. Characterization of the micropore and mesopore texture was carried out using N2 and CO2 adsorption at 77 and 273 K, respectively.Central composite design was used to evaluate the combined effects of temperature and concentration of CO2 on the adsorption behavior of the adsorbents. The KOH activated carbon with a total micropore volume of 0.62 cm3/g and surface area of 1400 m2/g had the highest CO2 adsorption capacity of 1.8 mol/kg due to its microporous structure and high surface area under the optimized experimental conditions of 30 mol% CO2 and 25°C. The performance of the adsorbents in multi-cyclic adsorption process was also assessed and the adsorption capacity of KOH and CO2 activated carbons remained remarkably stable after50 cycles with low temperature（160°C） regeneration.