Skip to content
Log in

Author

B. Li

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Jul 2026

Synthesis of a quasi-optimal fuzzy controller model under a priori uncertainty in intelligent transport underactuated systems

The research paper presents the synthesis of a fuzzy quasi-optimal controller model and an analysis of its effectiveness compared to a known train speed controller for short-term deviations from the specified operating mode. The task of controlling an underactuated system is of particular importance for railway transport, especially for high-speed transportation. Mechanical systems as control objects are essentially nonlinear dynamical systems of high order. In addition, the complexity of optimizing the operating modes of such systems is due to the fact that even detailed modeling does not accurately predict the cumulative effect of all dynamic factors acting on a dynamic system under operating conditions. Traditionally used in practice linear control laws with constant coefficients are designed to stabilize only one specific mode of motion, which makes them ineffective in conditions of control deficit and a priori uncertainty. Using the reduction of the Lagrange optimization problem to the isoperimetric one makes it possible to obtain a quasi-optimal solution to the structural synthesis problem, which increases control efficiency compared to known methods. The use of the fuzzy logic apparatus allows for parametric synthesis of control, providing adaptability to a priori uncertain operating conditions.

V. Zekhtser, A. Kostoglotov, X.-B. Wu et al. · 0 citations
Open access Aug 2026

Modeling Dynamic Obstacle Avoidance Strategy of Drone Swarms Combined with Multi-Agent Reinforcement Learning

This paper proposes the Locally-decoupled and Embedding-enhanced Multi-Agent Deep Deterministic Policy Gradient (LDE-MADDPG) algorithm to address poor scalability and delayed response in drone swarm dynamic obstacle avoidance under complex cooperative environments. Such autonomous coordination capabilities are also important for distributed sensing, wireless networking, and electromagnetic information exchange in future intelligent aerial systems. The algorithm introduces three key innovations beyond standard MADDPG: a Graph Attention Network module that encodes variable-length observations into fixed-dimensional embeddings for swarm-size generalization; a dual-path critic with a global branch guiding policy updates and a local branch specializing in obstacle avoidance evaluation; and a hierarchical reward integrating multi-objective signals. Evaluated across eight static and dynamic obstacle scenarios, LDE-MADDPG achieves significantly lower collision rates (2.1%–4.2% in static scenarios and 3.8%–7.2% in dynamic scenarios) than state-of-the-art baselines and reaches a 97.5% mission completion rate in 100 random scenarios. The proposed framework demonstrates robust scalability and real-time coordination capability for dynamic environments, while providing a reliable decision-making paradigm for intelligent multi-agent systems operating in communication-intensive and electromagnetically complex application scenarios.

X. Fang, K. Chen, C. Ren et al. · 0 citations