A distributed algorithm for signal coordination of multiple agents with embedded platoon dispersion model

In order to reduce average arterial vehicle delay, a novel distributed and coordinated traffic control algorithm is developed using the multiple agent system and the reinforce learning （RL）. The RL is used to minimize average delay of arterial vehicles by training the interaction ability between agents and exterior environments. The Robertson platoon dispersion model is embedded in the RL algorithm to precisely predict platoon movements on arteries and then the reward function is developed based on the dispersion model and delay equations cited by HCM2000. The performance of the algorithm is evaluated in a Matlab environment and comparisons between the algorithm and the conventional coordination algorithm are conducted in three different traffic load scenarios. Results show that the proposed algorithm outperforms the conventional algorithm in all the scenarios. Moreover, with the increase in saturation degree, the performance is improved more significantly. The results verify the feasibility and efficiency of the established algorithm.

Fuzzy collaborative filtering with multiple agents

Automated collaborative filtering has become a popular technique for reducing information overload. We have developed a new method for recommending items using multiple agents. The agents were established by employing the fuzzy C-means clustering technique. We employ these agents collaborating each other to get recommendation for users. The results were evaluated by using MovieLens movie＇s rating data. It is shown that the algorithm is an effective metrics in collaborative filtering.

Collaborative visual SLAM for multiple agents:A brief survey

This article presents a brief survey to visual simultaneous localization and mapping (SLAM) systems applied to multiple independently moving agents, such as a team of ground or aerial vehicles, a group of users holding augmented or virtual reality devices. Such visual SLAM system, name as collaborative visual SLAM, is different from a typical visual SLAM deployed on a single agent in that information is exchanged or shared among different agents to achieve better robustness, efficiency, and accuracy. We review the representative works on this topic proposed in the past ten years and describe the key components involved in designing such a system including collaborative pose estimation and mapping tasks, as well as the emerging topic of decentralized architecture. We believe this brief survey could be helpful to someone who are working on this topic or developing multi-agent applications, particularly micro-aerial vehicle swarm or collaborative augmented/virtual reality.

A Three-Dimensional Model of Transport and Diffusion of Seeding Agents within Stratus

It is essential to learn the temporal and spatial concentration distributions and variations of seeding agents in cloud seeding of precipitation enhancement. A three-dimensional puff trajectory model incorporating a mesoscale nonhydrostatic model has been formulated, and is applied to simulating the transporting and diffusive characteristics of multiple line sources of seeding agents within super-cooled stratus. Several important factors are taken into consideration that affect the diffusion of seeding materials such as effects of topography and vertical wind shear, temporal and spatial variation of seeding parameters and wet deposition. The particles of seeding agents are assumed to be almost inert, they have no interaction with the particles of the cloud or precipitation except that they are washed out by precipitation. The model validity is demonstrated by the analyses and comparisons of model results, and checked by the sensitivity experiments of diffusive coefficients and atmospheric stratification. The advantage of this model includes not only its exact reflection of heterogeneity and unsteadiness of background fields, but also its good simulation of transport and diffusion of multiple line sources. The horizontal diffusion rate and the horizontal transport distance have been proposed that they usually were difficult to obtain in other models. In this simulation the horizontal diffusion rate is 0.82 m s(-1) for average of one hour, and the horizontal average transport distance reaches 65 km after 1 4 which are closely related to the background Fields.

Coordinated dynamic mission planning scheme for intelligent multi-agent systems

Mission planning was thoroughly studied in the areas of multiple intelligent agent systems,such as multiple unmanned air vehicles,and multiple processor systems.However,it still faces challenges due to the system complexity,the execution order constraints,and the dynamic environment uncertainty.To address it,a coordinated dynamic mission planning scheme is proposed utilizing the method of the weighted AND/OR tree and the AOE-Network.In the scheme,the mission is decomposed into a time-constraint weighted AND/OR tree,which is converted into an AOE-Network for mission planning.Then,a dynamic planning algorithm is designed which uses task subcontracting and dynamic re-decomposition to coordinate conflicts.The scheme can reduce the task complexity and its execution time by implementing real-time dynamic re-planning.The simulation proves the effectiveness of this approach.

Autonomous Cooperative Vehicle Coordination at Road Intersections

Appropriate traffic coordination at road intersections plays a crucial part in modern intelligent transportation systems.In this paper,we first try to extend the traditional single collision-set coordination strategy to multiple-collision-set strategies,by which the traffic throughput can be significantly improved.Unlike the existing centralized coordination methods,two low complexity coordination methods are proposed based on the multi-agents Q-learning frameworks.Numerical results show that,the proposed high throughput strategies are able to provide safe and efficient traffic coordination.Meanwhile,since only local information is required,the coordination complexity can be reduced,which is attractive in highly dynamic real time scenarios.