arXiv subjects

Namhoon Cho

Publications and source records attributed to Namhoon Cho.

13 recordsLinked to original sources

arXiv2026

HJ-Gauss: A Monte-Carlo HJ Reachability Scheme

Backward reachable sets or tubes (BRS/Ts), evaluated with grid-based level-set methods over viscous Hamilton-Jacobi (HJ) equations, furnish principled reachability certificates for learning-enabled control. However, these methods incur an $O(M^n)$ memory cost, where $M$ is the number of grid points for every $n$-state dimension, which has precluded their applications in high-dimensional physical phenomena. Towards scalable reachability analysis, we propose a frozen-coefficient Picard iterative Gaussian sampling scheme: with a Cole-Hopf-type transformation, the HJ PDE effectively reduces to a sequence of linear heat equations, whose values are then iteratively recovered via Gaussian heat-kernel expectations. In this sentiment, Monte Carlo roll-outs over Gaussian densities ultimately recover the (approximate) HJ value and its spatial gradient. Ours is a storage- and discretization-free algorithm whose memory footprint scales (for \textit{i.i.d} samples, $N$) as $N\cdot n$; we show that sampling is a polynomial power law in $N$ and provide a conditional linear convergence analysis to the \textit{consistent} viscosity solution. Furthermore, we provide a quasilinearization defect per iteration between frozen coefficient samples to make our HJ sampling scheme tight. Our theoretical machinery is rigorously benchmarked on rocket launch and Dubins pursuit-evasion (P-E) games over Holm-Bonferroni-informed experiments: for a $45D$-multi-rocket launch P-E game, we find an \textit{almost zero} Picard residual floor. Certifying the safety of \textbf{$100,000$} European starlings (\textit{sturnus vulgaris}) in murmurations over their collective value functions reveals vacuole nucleation, cordon formation, and flock splitting on the resulting BRT zero-levelset phase topology as predator attacks evolve , demonstrating the scalability of our approach to large-scale multi-agent systems.

eess.SY↗

arXiv2026

Combinatorial Safety-Critical Coordination of Multi-Agent Systems via Mixed-Integer Responsibility Allocation and Control Barrier Functions

This paper presents a hybrid safety-critical coordination architecture for multi-agent systems operating in dense environments. While control barrier functions (CBFs) provide formal safety guarantees, decentralized implementations typically rely on ego-centric safety filtering and may lead to redundant constraint enforcement and conservative collective behavior. To address this limitation, we introduce a combinatorial coordination layer formulated as a mixed-integer linear program (MILP) that assigns collision-avoidance responsibilities among agents. By explicitly distributing enforcement tasks, redundant reactions are eliminated and computational complexity is reduced. Each agent subsequently solves a reduced local quadratic program enforcing only its assigned constraints.

eess.SY↗

arXiv2025

Hierarchical Vision Language Action Model Using Success and Failure Demonstrations

Prior Vision-Language-Action (VLA) models are typically trained on teleoperated successful demonstrations, while discarding numerous failed attempts that occur naturally during data collection. However, these failures encode where and how policies can be fragile, information that can be exploited to improve robustness. We address this problem by leveraging mixed-quality datasets to learn failure-aware reasoning at planning time. We introduce VINE, a hierarchical vision-language-action model that separates high-level reasoning (System 2) from low-level control (System 1) under a hierarchical reinforcement learning formalism, making failures usable as a structured learning signal rather than noisy supervision. System 2 performs feasibility-guided tree search over a 2D scene-graph abstraction: it proposes subgoal transitions, predicts success probabilities from both successes and failures, and prunes brittle branches before execution, effectively casting plan evaluation as feasibility scoring. The selected subgoal sequence is then passed to System 1, which executes low-level actions without modifying the agent's core skills. Trained entirely from offline teleoperation data, VINE integrates negative experience directly into the decision loop. Across challenging manipulation tasks, this approach consistently improves success rates and robustness, demonstrating that failure data is an essential resource for converting the broad competence of VLAs into robust execution.

cs.RO↗

arXiv2025

Data-Driven Hamiltonian for Direct Construction of Safe Set from Trajectory Data

In continuous-time optimal control, evaluating the Hamiltonian requires solving a constrained optimization problem using the system's dynamics model. Hamilton-Jacobi reachability analysis for safety verification has demonstrated practical utility only when efficient evaluation of the Hamiltonian over a large state-time grid is possible. In this study, we introduce the concept of a data-driven Hamiltonian (DDH), which circumvents the need for an explicit dynamics model by relying only on mild prior knowledge (e.g., Lipschitz constants), thus enabling the construction of reachable sets directly from trajectory data. Recognizing that the Hamiltonian is the optimal inner product between a given costate and realizable state velocities, the DDH estimates the Hamiltonian using the worst-case realization of the velocity field based on the observed state trajectory data. This formulation ensures a conservative approximation of the true Hamiltonian for uncertain dynamics. The reachable set computed based on the DDH is also ensured to be a conservative approximation of the true reachable set. Next, we propose a data-efficient safe experiment framework for gradual expansion of safe sets using the DDH. This is achieved by iteratively conducting experiments within the computed data-driven safe set and updating the set using newly collected trajectory data. To demonstrate the capabilities of our approach, we showcase its effectiveness in safe flight envelope expansion for a tiltrotor vehicle transitioning from near-hover to forward flight.

eess.SY↗

arXiv2024

Generalized Gaussian Temporal Difference Error for Uncertainty-aware Reinforcement Learning

Conventional uncertainty-aware temporal difference (TD) learning often models TD errors as zero-mean Gaussian. This assumption can miss the heavy-tailed and heteroscedastic residuals induced by bootstrapping and exploration. We introduce a state-conditioned shape head based on the Generalized Gaussian Distribution (GGD) and use a numerically modified GGD loss as an online surrogate for nonstationary TD residuals. We distinguish two mathematical facts that are sometimes conflated: the exact GGD likelihood is normalized for every $\beta>0$, whereas its exponential density kernel is positive definite for $\beta\in(0,2]$. We use the learned shape to construct a simple monotone weighting heuristic and propose Batch Inverse Error Variance (BIEV) regularization from the variance and sample excess kurtosis of ensemble TD errors. Across continuous and discrete control benchmarks, the shape-aware variants improve over Gaussian-based variants in several settings, although the gains are task- and regime-dependent.

cs.LG↗

arXiv2024

Synchronisation-Oriented Design Approach for Adaptive Control

This study presents a synchronisation-oriented perspective towards adaptive control which views model-referenced adaptation as synchronisation between actual and virtual dynamic systems. In the context of adaptation, model reference adaptive control methods make the state response of the actual plant follow a reference model. In the context of synchronisation, consensus methods involving diffusive coupling induce a collective behaviour across multiple agents. We draw from the understanding about the two time-scale nature of synchronisation motivated by the study of blended dynamics. The synchronisation-oriented approach consists in the design of a coupling input to achieve desired closed-loop error dynamics followed by the input allocation process to shape the collective behaviour. We suggest that synchronisation can be a reasonable design principle allowing a more holistic and systematic approach to the design of adaptive control systems for improved transient characteristics. Most notably, the proposed approach enables not only constructive derivation but also substantial generalisation of the previously developed closed-loop reference model adaptive control method. Practical significance of the proposed generalisation lies at the capability to improve the transient response characteristics and mitigate the unwanted peaking phenomenon at the same time.

eess.SY↗

arXiv2023

Automatic Optimisation of Normalised Neural Networks

We propose automatic optimisation methods considering the geometry of matrix manifold for the normalised parameters of neural networks. Layerwise weight normalisation with respect to Frobenius norm is utilised to bound the Lipschitz constant and to enhance gradient reliability so that the trained networks are suitable for control applications. Our approach first initialises the network and normalises the data with respect to the $\ell^{2}$-$\ell^{2}$ gain of the initialised network. Then, the proposed algorithms take the update structure based on the exponential map on high-dimensional spheres. Given an update direction such as that of the negative Riemannian gradient, we propose two different ways to determine the stepsize for descent. The first algorithm utilises automatic differentiation of the objective function along the update curve defined on the combined manifold of spheres. The directional second-order derivative information can be utilised without requiring explicit construction of the Hessian. The second algorithm utilises the majorisation-minimisation framework via architecture-aware majorisation for neural networks. With these new developments, the proposed methods avoid manual tuning and scheduling of the learning rate, thus providing an automated pipeline for optimizing normalised neural networks.

cs.LG↗

arXiv2023

Dynamic Deep-Reinforcement-Learning Algorithm in Partially Observable Markov Decision Processes

Recent studies have greatly improved reinforcement learning, and an increased interest in real-world implementation has emerged. In many cases, the implementation is challenged by time-varying disturbances as it introduces hidden states, which makes the problem best described with Partially Observable Markov Decision Processes. An effective approach to address this problem is to introduce a Recurrent Neural Network (RNN) in place of a state estimator. However, only a few studies have investigated the types of information to be supplied to the RNN and the network architecture to handle them. This study discusses the effectiveness of the inclusion of action along with observation and the impact of network architecture to handle them by providing interpretations of how the trajectories are summarized at LSTM networks. Specifically, three novel approaches with different architectures are introduced. All algorithms demonstrated the effectiveness of the inclusion of the action trajectories in simulation environments. In particular, one of the developed algorithms, H-TD3, differs from the typical actor and critic network as the critic network is trained by utilizing the hidden states generated by the actor network as the summarized trajectory information. This novel approach exhibited the potential improvement of the computational time while maintaining the performance.

cs.LG↗

arXiv2023

A Passivity-Based Method for Accelerated Convex Optimisation

This study presents a constructive methodology for designing accelerated convex optimisation algorithms in continuous-time domain. The two key enablers are the classical concept of passivity in control theory and the time-dependent change of variables that maps the output of the internal dynamic system to the optimisation variables. The Lyapunov function associated with the optimisation dynamics is obtained as a natural consequence of specifying the internal dynamics that drives the state evolution as a passive linear time-invariant system. The passivity-based methodology provides a general framework that has the flexibility to generate convex optimisation algorithms with the guarantee of different convergence rate bounds on the objective function value. The same principle applies to the design of online parameter update algorithms for adaptive control by re-defining the output of internal dynamics to allow for the feedback interconnection with tracking error dynamics.

math.OC↗

arXiv2022

Incremental Correction in Dynamic Systems Modelled with Neural Networks for Constraint Satisfaction

This study presents incremental correction methods for refining neural network parameters or control functions entering into a continuous-time dynamic system to achieve improved solution accuracy in satisfying the interim point constraints placed on the performance output variables. The proposed approach is to linearise the dynamics around the baseline values of its arguments, and then to solve for the corrective input required to transfer the perturbed trajectory to precisely known or desired values at specific time points, i.e., the interim points. Depending on the type of decision variables to adjust, parameter correction and control function correction methods are developed. These incremental correction methods can be utilised as a means to compensate for the prediction errors of pre-trained neural networks in real-time applications where high accuracy of the prediction of dynamical systems at prescribed time points is imperative. In this regard, the online update approach can be useful for enhancing overall targeting accuracy of finite-horizon control subject to point constraints using a neural policy. Numerical example demonstrates the effectiveness of the proposed approach in an application to a powered descent problem at Mars.

math.OC↗

arXiv2022

ORFit: One-Pass Learning via Bridging Orthogonal Gradient Descent and Recursive Least-Squares

While large machine learning models have shown remarkable performance in various domains, their training typically requires iterating for many passes over the training data. However, due to computational and memory constraints and potential privacy concerns, storing and accessing all the data is impractical in many real-world scenarios where the data arrives in a stream. In this paper, we investigate the problem of one-pass learning, in which a model is trained on sequentially arriving data without retraining on previous datapoints. Motivated by the demonstrated effectiveness of overparameterized models and the phenomenon of benign overfitting, we propose Orthogonal Recursive Fitting (ORFit), an algorithm for one-pass learning which seeks to perfectly fit each new datapoint while minimally altering the predictions on previous datapoints. ORFit updates the parameters in a direction orthogonal to past gradients, similar to orthogonal gradient descent (OGD) in continual learning. We show that, interestingly, ORFit's update leads to an operation similar to the recursive least-squares (RLS) algorithm in adaptive filtering but with significantly improved memory and computational efficiency, i.e., linear, instead of quadratic, in the number of parameters. To further reduce memory usage, we leverage the structure of the streaming data via an incremental principal component analysis (IPCA). We show that using the principal components is minimax optimal, i.e., it minimizes the worst-case forgetting of previous predictions for unknown future updates. Further, we prove that, for overparameterized linear models, the parameter vector obtained by ORFit matches what the standard multi-pass stochastic gradient descent (SGD) would converge to. Finally, we extend our results to the nonlinear setting for highly overparameterized models, relevant for deep learning.

cs.LG↗

arXiv2022

Bayesian Learning Approach to Model Predictive Control

This study presents a Bayesian learning perspective towards model predictive control algorithms. High-level frameworks have been developed separately in the earlier studies on Bayesian learning and sampling-based model predictive control. On one hand, the Bayesian learning rule provides a general framework capable of generating various machine learning algorithms as special instances. On the other hand, the dynamic mirror descent model predictive control framework is capable of diversifying sample-rollout-based control algorithms. However, connections between the two frameworks have still not been fully appreciated in the context of stochastic optimal control. This study combines the Bayesian learning rule point of view into the model predictive control setting by taking inspirations from the view of understanding model predictive controller as an online learner. The selection of posterior class and natural gradient approximation for the variational formulation governs diversification of model predictive control algorithms in the Bayesian learning approach to model predictive control. This alternative viewpoint complements the dynamic mirror descent framework through streamlining the explanation of design choices.

cs.LG↗

arXiv2022

Optimisation of Structured Neural Controller Based on Continuous-Time Policy Gradient

This study presents a policy optimisation framework for structured nonlinear control of continuous-time (deterministic) dynamic systems. The proposed approach prescribes a structure for the controller based on relevant scientific knowledge (such as Lyapunov stability theory or domain experiences) while considering the tunable elements inside the given structure as the point of parametrisation with neural networks. To optimise a cost represented as a function of the neural network weights, the proposed approach utilises the continuous-time policy gradient method based on adjoint sensitivity analysis as a means for correct and performant computation of cost gradient. This enables combining the stability, robustness, and physical interpretability of an analytically-derived structure for the feedback controller with the representational flexibility and optimised resulting performance provided by machine learning techniques. Such a hybrid paradigm for fixed-structure control synthesis is particularly useful for optimising adaptive nonlinear controllers to achieve improved performance in online operation, an area where the existing theory prevails the design of structure while lacking clear analytical understandings about tuning of the gains and the uncertainty model basis functions that govern the performance characteristics. Numerical experiments on aerospace applications illustrate the utility of the structured nonlinear controller optimisation framework.

cs.LG↗