Dechao Ran

OSGS: A Framework for Online Scheduling of Satellite-Ground Collaborative Inference With Space Edge Computing

Kongyange Zhao, Yuanming Wang, Zhi Zhou, Ruiting Zhou et autres

cn (code pays fourni par la source)

TSDP: Diverse task sampling for robust multi-agent reinforcement learning in perturbed environments

Xiao Wang, Yuying Han, Fei Zhang, Dechao Ran et autres

cn (code pays fourni par la source)

A Contrastive Free Energy-Enhanced Transformer Framework for Efficient Reinforcement Learning

Y H Pan, Jinlong Lei, Dechao Ran, Peng Yi

To address the challenges of low training efficiency and unstable performance in multiagent reinforcement learning (MARL), this article proposes a novel efficient MARL algorithm called contrastive free energy-enhanced multiagent Transformer (CFMAT), which integrates upstream perception and downstream decision-making in a joint training …

cn (code pays fourni par la source)

A Dynamic Aggregative Game-Based Distributed Approach for Defensive Spacecraft Formations

Hongcheng Liu, Peng Yi, Jinlong Lei, Dechao Ran et autres

cn, pt (code pays fourni par la source)

Dynamic Event-Based Adaptive Optimal Enclosure Control for Spacecraft Formation Against Noncooperative Targets

Hongcheng Liu, Peng Yi, Dechao Ran, Lu Cao et autres

This paper investigates the adaptive optimal enclosure control problem for multi-spacecraft systems surrounding a noncooperative target. Based on the orbital dynamics derived from the two-body problem, a manifold-based invariant estimation method is developed to accurately reconstruct the unknown control input of the …

cn (code pays fourni par la source)

SPOD-YOLO: A Modular Approach for Small and Oriented Aircraft Detection in Satellite Remote Sensing Imagery

Pengyu Guo, Yong Liu, Lu Cao, Dechao Ran et autres

The accurate detection of small, densely packed and arbitrarily oriented aircraft in high-resolution remote sensing imagery remains highly challenging due to significant variations in object scale, orientation and background complexity. Existing detection frameworks often struggle with insufficient representation of small objects, instability …

cn (code pays fourni par la source)

Internet of Satellites (IoS) for Intelligent Satellite Cluster: Applications, Methods, and Challenges

Guangteng Fan, Peng Wu, Mengqi Yang, Jian Wang et autres

The integration of emerging technologies such as artificial intelligence and cloud computing is accelerating the development of intelligent and autonomous satellite systems. However, limitations in onboard sensing, computing, storage, and energy resources continue to constrain the intelligent functionalities of individual satellites. Currently, …

cn (code pays fourni par la source)

Research on Multi satellite Collaborative Task Planning Technology

Jingguo Wang, Weijin Qin, Dechao Ran, Peiming Wu et autres

Abstract As satellite technology advances and its applications expand, multi-satellite collaborative task planning has emerged as a key solution to address the growing demand for observation tasks amid limited satellite resources. By leveraging advanced planning algorithms and collaborative mechanisms, this approach optimizes …

cn (code pays fourni par la source)

Reinforcement learning-based scheduling strategy for low-orbit satellite beam-hopping resources in hot-spot regions

J. S. Wang, Wanting Qin, Dechao Ran, Junhui Xu et autres

This paper presents a reinforcement learning optimization strategy based on the Experience Replay Q-Learning (ERQL) mechanism for dynamic hotspot area beam hopping resource scheduling in low Earth orbit (LEO) satellite communication systems. This approach addresses the issue of premature convergence in traditional …

us, cn (code pays fourni par la source)

Prediction techniques of spatiotemporal trajectory data: progress and framework

Wanting Qin, Dechao Ran, Mingjiang Ji, Jun Tang et autres

With the wide application of intelligent devices, a large amount of spatiotemporal trajectory data can be preserved and recorded. The application of spatiotemporal trajectories has penetrated every aspect of people's daily lives. It is of great applications value to predict the future …

cn (code pays fourni par la source)

A data-knowledge joint-driven reinforcement learning algorithm based on guided policy and state-prediction for satellite continuous-thrust tracking

Xiao Wang, Jiake Li, Lu Cao, Dechao Ran et autres

cn (code pays fourni par la source)

A planar tracking strategy based on multiple-interpretable improved PPO algorithm with few-shot technique

Xiao Wang, Zhe Ma, Lu Cao, Dechao Ran et autres

Facing to a planar tracking problem, a multiple-interpretable improved Proximal Policy Optimization (PPO) algorithm with few-shot technique is proposed, namely F-GBQ-PPO. Compared with the normal PPO, the main improvements of F-GBQ-PPO are to increase the interpretability, and reduce the consumption for real …

cn, us (code pays fourni par la source)