Fixed-time stochastic learning from human-UAV interaction with state-input constraints

Human-unmanned aerial vehicle (UAV) collaboration requires control frameworks that are both efficient and safe. This paper introduces a stochastic fixed-time inverse optimal control (FxT-IOC) approach designed for such systems. The proposed framework constructs inverse optimal control, enabling the extraction of human operator intent. It features a fixed-time adaptive learning mechanism that guarantees parameter convergence within a predetermined time, irrespective of initial conditions. Crucially, the design explicitly incorporates prescribed performance control (PPC) to enforce state constraints while handling input saturation, ensuring operational safety and reliability. Rigorous theoretical analysis establishes the fixed-time stability of the learning process and the closed-loop system under these constraints. The effectiveness of the FxT-IOC framework is validated through comprehensive numerical simulations and physical hardware experiments, demonstrating superior trajectory tracking precision, accelerated learning convergence, and robust constraint satisfaction compared to human demonstrations. This work offers a principled and practical solution for developing high-performance, reliable human-UAV collaborative systems.

Recommended citation: Tan, Junkai and Xue, Shuangsi and Qingshu, Guan and Guo, Zihang and Cao, Hui and Chen, Badong (2025). Fixed-time stochastic learning from human-UAV interaction with state-input constraints. IEEE Transactions on Industrial Electronics.