pid-based latent control

本文通过条件流匹配方法将控制潜变量解码为四旋翼模型分布，以实现固定策略的在线预测调优和鲁棒性分析。

This study addresses the challenge of composite adaptive tracking control under dynamic coupled disturbances. To this end, it proposes a predictive control framework grounded in representation learning. Specifically, the framework employs statistical methods to identify disturbance dynamics representations exhibiting contraction properties. By introducing a hard expectation-maximization algorithm augmented with a Kalman smoother, it extends conventional fixed-decay approaches into learnable predictive models and integrates Bayesian filtering for precise state estimation. Experimental evaluations on vehicles traversing slippery terrains and coupled Duffing oscillators demonstrate that the proposed method achieves accurate disturbance prediction, significantly enhancing both adaptive tracking performance and control robustness.

This work addresses control-affine nonlinear systems subject to nonholonomic constraints. We propose a novel deterministic feedback control and motion planning framework grounded in denoising diffusion probabilistic models (DDPMs). Methodologically, we introduce a control-oriented time-reversal diffusion mechanism—proving for the first time that controllable driftless nonlinear systems admit exact deterministic feedback laws capable of perfectly inverting the forward diffusion process. We further design constraint-embedded forward noise to eliminate stochastic sampling in the reverse process. Integrating score matching, Lyapunov stability analysis, and nonholonomic modeling, our approach enables analytical construction of control laws while ensuring strict fidelity in density evolution. Evaluated on single-vehicle obstacle avoidance, a 5D drifting system, and a 4D linear system, the method achieves fully deterministic reverse-time trajectories—zero sampling randomness—thereby enhancing interpretability and real-time deployability of the controller.

This paper addresses the joint learning of state representations and controllers for unknown partially observable linear systems under the LQG control paradigm. Unlike conventional representation learning approaches that require observation reconstruction, we propose a cost-driven latent dynamics modeling framework that directly optimizes multi-step control costs—bypassing observation reconstruction and enabling end-to-end joint learning of representations and controllers. Theoretically, we establish the first finite-sample, provably guaranteed analysis for cost-driven latent model learning, revealing that accurate multi-step cost prediction is both necessary and sufficient for representation identifiability and near-optimal control performance. Methodologically, our approach integrates empirical risk minimization, system identification, and robust control analysis. Under finite-sample conditions, the learned representation and controller converge to the optimal solution, thereby closing a long-standing gap in provable guarantees for this paradigm.

This work addresses trajectory tracking control for linear time-invariant (LTI) systems. We propose a physics-informed Gaussian process (GP) model predictive control (MPC) framework. Methodologically, we embed the LTI system’s constant-coefficient linear differential equation as a hard constraint into the GP prior—enabling “control-as-inference”—and introduce a virtual setpoint mechanism to explicitly encode and enforce pointwise soft constraints. Theoretically, we prove asymptotic stability of the resulting closed-loop system under the optimal control law. Numerical experiments demonstrate superior constraint satisfaction, tracking accuracy, and robustness compared to baseline methods. Our approach establishes a new paradigm for data-driven control that unifies physical interpretability—through first-principles differential equation constraints—with rigorous stability guarantees.

This work addresses the degradation of stability guarantees in Model Predictive Path Integral (MPPI) control for nonlinear systems due to mismatch between the assumed and the true additive process noise covariance, which is unknown, spatially varying, and slowly time-varying. To mitigate this issue, the authors propose a block-wise recursive covariance estimator augmented with a spatial diffusion mechanism that continuously updates the disturbance covariance online and embeds it into the MPPI sampling distribution. By integrating a weighted Lyapunov analysis, the approach provides adaptive stability guarantees. The method innovatively incorporates spatial smoothing and an invertible diffusion kernel to disentangle stochastic approximation error, smoothing bias, and time-varying drift effects. Theoretically, it is shown that after a finite transient period, the proposed scheme yields a strictly tighter stability bound than any fixed covariance choice. Numerical experiments corroborate the estimator’s convergence and its efficacy in enhancing closed-loop stability.

This work addresses the challenge of achieving general and efficient control of partial differential equation (PDE) systems without task-specific objectives or reward signals. To this end, it proposes a goal-agnostic PDE control framework that combines an offline-trained, frozen Vision Transformer (ViT) encoder with an action-conditional latent dynamics model based on the Joint Embedding Predictive Architecture (JEPA), integrated with Model Predictive Path Integral (MPPI) control for online planning. Innovatively, the approach couples goal-agnostic latent space modeling with probes on physically meaningful observables—such as kinetic energy—enabling a single frozen world model to support diverse control tasks. Evaluated on Navier–Stokes benchmarks, the method substantially improves performance: kinetic-energy-probe-based planning raises the 50-episode average reward from −12.08 to −10.90 and reduces late-stage velocity field RMSE by 9.5%; across three unseen non-periodic targets, it cuts late-field RMSE by 53% and wins all 30 head-to-head trials; steady-state control achieves a 2.7% average relative error.

This study addresses the challenge of ensuring safety when embedding industrial control models into deployed systems, particularly regarding safety constraints in pressurized water reactor (PWR) load-following operations. To this end, a physics-decomposition-based structured representation learning method is proposed. This approach constructs a multi-timescale separation embedding architecture that maps variables across different timescales into independent latent spaces to emulate expert policies. It further enables hybrid deployment by integrating behavioral cloning with nonlinear model predictive control (NMPC). Experimental results demonstrate that the proposed method significantly improves the accuracy and feasibility of long-horizon trajectories, achieving fully feasible solutions with near-optimal costs while reducing computation time by approximately 15% compared to the expert controller.

This work addresses the challenge that traditional PID tuning relies heavily on model identification and fails to capture the empirical expertise of engineers who iteratively adjust parameters based on observed system responses. To bridge this gap, the authors propose a novel tuning framework that integrates control-domain knowledge with the reasoning capabilities of large and small language models. The approach formalizes the engineer’s tuning process into an executable task by leveraging closed-loop response characteristics, diagnostic cues, tuning preferences, and IMC-based examples to guide parameter generation and refinement. Physical constraints and reinforcement learning are incorporated to enhance performance, with the method employing supervised fine-tuning (SFT) and a physics-informed group relative policy optimization (PI-GRPO). Evaluated on 200 FOPDT/SOPDT processes, the cloud-based large model achieves a success rate of 75–89%, while a locally deployed Qwen3-0.6B model, after optimization, attains a first-recommendation success rate of 94.0%.

This study addresses the computational bottleneck associated with dynamically constrained sampling of state spaces in feedback control and planning. To overcome this challenge, the work reformulates control as a dynamically constrained sampling problem, establishing a mapping framework that bridges controllability, optimal control theory, and generative modeling. Specifically, it integrates flow matching, normalizing flows, and denoising diffusion techniques to guide system evolution toward target states or distributions. The proposed approach enables efficient reachable set sampling and precise trajectory planning while unifying control-theoretic and generative-modeling paradigms. Furthermore, the authors provide an accessible open-source tutorial to facilitate practical adoption by the research community.