In object classification, feature combination can usually be used to combine the strength of multiple complementary features and produce better classification results than any single one. While kernel learning (MKL) is a popular approach in it does not always perform well practical applications. On one hand, optimization process MKL involves huge consumption computation memory space. other some cases, found no baseline methods. This observation motivates us investigate underlying mechanism...

The electric sail (E-sail), as an emerging propulsion system with infinite specific impulse, is particularly suitable for ultra-long-distance multi-target deep-space exploration missions. If multiple gravity assists are considered during the process, it can effectively improve efficiency of E-sail. This paper proposes a fast optimization algorithm trajectories E-sail, which achieves celestial bodies and solar-system boundaries in one flight, introduces assist to flight speed E-sail process....

A triple‐stage path prediction algorithm is proposed for real‐time mission planning. In every planning horizon, each unmanned aerial vehicle (UAV) utilises the A* first to estimate task. Then, estimated result serve as input of cluster method generate quasi‐optimal task assignment. The shortest assigned further calculated using algorithm. Finally, it smoothed obtain flyable reference guide UAV by cubic B‐spline curve. Numerical experiments demonstrate effectiveness and efficiency

To maximize the advantages of being low-cost, highly mobile, and having a high flexibility, aerial recovery technology is important for unmanned vehicle (UAV) swarms. In particular, operation mode “launch-recovery-relaunch” will greatly improve efficiency UAV swarm. However, it difficult to realize large-scale swarms because this process involves complex multi-UAV scheduling, path planning, rendezvous, acquisition problems. study, problem swarm by mother aircraft has been investigated. solve...

In the dynamical environment with forbidden areas, achievement of multiple unmanned aerial vehicles (UAVs) executing cooperative missions strongly depends on validity mission planning results, which may be affected by error flight time estimation. this paper, a hierarchical path generation scheme for improving adaptability and performance distributed (DMP) system UAVs is proposed. The effectiveness market-based task allocation enhanced conducting rough beforehand, where only neighboring...

The ability to deploy multiple unmanned aerial vehicles expands their application range, but recovery of presents many unique challenges owing the number and limited time. In this paper, scheduling by one mothership is posed as a combinatorial optimization problem. A mathematical model with time windows developed formulate Furthermore, genetic algorithm proposed for finding optimal sequence. adopts path representation chromosomes simplify encoding process operations. It also resolves...

Dominant sets clustering is a promising approach based on graph-theoretic concept of cluster. With the pairwise similarity matrix data as input, dominant determines number clusters by itself and possesses some other nice properties. However, original algorithm sensitive to measures, appropriate parameters are required generate satisfactory results. In order solve this problem, we firstly use histogram equalization transform remove sensitiveness parameters. second step extend merging DBSCAN....

In this paper, the traditional shortest path planning problem for vehicle is advanced to length-targeted problem, i.e., plan with its length being as close a specified value possible. Lengthening and shortening of given initial paths are used solve problem. Based on an operation set consisting three basic homotopies, we build comprehensive systematic framework target length, which generalization existing related studies. Thereby, expected can be independently searched through such...

The fuel carried by deep space exploration spacecraft is crucial for the completion of their missions, and attitude control engines even more precious. In order to reduce requirements systems, this paper proposes a shape-based trajectory optimization algorithm that considers constraints low-thrust spacecraft. This method obtains accurate transfer considering change rate range propulsion acceleration direction By comparing simulation results without constraints, it confirmed proposed very...

This letter investigates a special task allocation problem with constraints of path planning. The planning process involved is defined as the follow-up step allocation. coupled constraints, which will affect utility solution. A homotopic approach featuring two homotopy primitives proposed to resolve complexity caused by coupling between and Reference paths generated are transformed desired bundles for robots via transformation functions. distributed architecture market mechanism employed...

Although there is no shortage of clustering algorithms, existing algorithms are often afflicted by problems one kind or another. Dominant sets a graph‐theoretic approach to and exhibits significant potential in various applications. However, the authors' work indicates that this suffers from two major problems, namely over‐segmentation tendency sensitiveness distance measures. In order overcome these authors present density‐based enhancement dominant where cluster merging step used fuse...

In this paper, we focus on coordinated motion planning of dual-arm robot. The kinematics model the robotic arm is established by Denavit-Hartenberg (D-H) coordinate method and mathematical cooperative problem established. rapidly-exploring random trees (RRT) algorithm deep deterministic policy gradient (DDPG) are used to carry out planning, respectively. simulation results show that these algorithms can effectively complete robot task, but RRT improved cannot balance efficiency result...

This paper presents an application of Boolean networks-based auction algorithm (BNAA) for task assignment in unmanned aerial vehicles (UAVs) systems. Under reasonable assumptions, the framework consists mission control system, communication network, and ground station. As improved consensus-based bundle (CBBA), BNAA utilizes a cluster-based combinatorial policy to handle multiple tasks. Instead empirical method based on look-up table about conditional variables, network is introduced into...

This article addresses the trajectory consensus problem of coordinating trajectories vehicles at multiple future time points. The objective is geometry vehicles' planned trajectories. geometric feature parameterized by a set states defined as required lengths along to reduce distance its ending point specific values. To solve this special involving coupled state variables, conventional model extended attaching it mapping from variables trajectory's geometry. established using homotopic...

Aerial recovery technology for aircrafts plays a significant role in practical applications, which presents challenging problem cooperative trajectory planning. To solve the problem, hierarchical planning architecture is proposed this paper. Firstly, waypoints of mother aircraft are obtained based on distribution child by using clustering algorithm. A greedy algorithm used to obtain traverse sequence and generated Dubins path. Secondly, genetic employed optimize position time each aircraft....