arXiv subjects

Mo Chen

Publications and source records attributed to Mo Chen.

At least 19 recordsLinked to original sources

arXiv2026

Control Barrier--Value Functions under Partial Observability: Safety Guarantees via Conformal Prediction

This paper studies safety analysis and controller synthesis for partially observable nonlinear control systems. We extend the control barrier--value function (CBVF) framework, which combines Hamilton--Jacobi reachability and control barrier functions, to settings where full state information is not available and control is based on an estimated state. Given an estimator, we apply conformal prediction to the estimation error and obtain an error bound at a user-chosen miscoverage level. We incorporate this bound into the estimator-space safety analysis and define a CBVF-based safety certificate for partially observable systems. We then derive a finite-horizon probabilistic safety guarantee for the true system state. Finally, we propose a QP-based online safety filter for systems affine in the control and disturbance, whose solution enforces the CBVF safety condition in real time against bounded disturbance. The proposed framework is illustrated on a partially observable obstacle-avoidance case study.

eess.SY↗

arXiv2026

NeuMoSync: End-to-End Neuromodulatory Control for Plasticity and Adaptability in Continual Learning

Continual learning (CL) requires models to learn tasks sequentially, yet deep neural networks often suffer from plasticity loss and poor knowledge transfer, which can impede their long-term adaptability. Drawing high-level inspiration from global neuromodulatory mechanisms in the brain, we introduce Neuromodulation and Synchronization (NeuMoSync), a novel architecture that integrates dynamic, neuron-specific modulation into deep neural networks to enhance their adaptability and plasticity. NeuMoSync extends standard neural network architectures with learnable feature vectors for each neuron that track network-wide historical context and with a module operating at a higher level of abstraction. This module synthesizes neuron-specific signals, conditioned on both current inputs and the network's evolving state, to adaptively regulate activation dynamics and synaptic plasticity. Evaluated on diverse CL benchmarks, including memorization (Random Label CIFAR-10 and Random Label MNIST), concept drift (Shuffle CIFAR-10 and Shuffle Mini-ImageNet), class-incremental learning (Class Split ImageNet and Class Split CIFAR-100), and domain-incremental learning (Permuted MNIST), NeuMoSync demonstrates strong performance in retaining plasticity and achieves improvements in both forward and backward adaptation compared with existing methods. Ablation studies validate the necessity of each component, while analysis of the learned modulatory signals reveals interpretable coordination patterns across tasks. Our work underscores the potential of integrating global coordination mechanisms into deep learning systems to advance robust, adaptive continual learning. The code is publicly available at https://github.com/RoozbehRazavi/NeuMoSync.

cs.AI↗

arXiv2026

Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPs

We study policy optimization for infinite-horizon, discounted constrained Markov decision processes (CMDPs). While existing theoretical guarantees typically hold for the mixture policy, deploying such a policy is computationally and memory intensive. This leads to a practical mismatch where a single (last-iterate) policy must be deployed. Recent theoretical works have thus focused on proving last-iterate convergence, but are largely limited to the tabular setting or to algorithmic variants that are rarely used in practice. To address this, we use the classic inexact augmented Lagrangian ($\texttt{AL}$) method from constrained optimization, and propose a general framework with provable last-iterate convergence for CMDPs. We first focus on the tabular setting and propose to solve the $\texttt{AL}$ sub-problem with projected Q-ascent ($\texttt{PQA}$). Combining the theoretical guarantees of $\texttt{PQA}$ and the standard $\texttt{AL}$ analysis enables us to establish global last-iterate convergence. We generalize these results to handle log-linear policies, and demonstrate that an efficient, projected variant of $\texttt{PQA}$ can achieve last-iterate convergence with comparable guarantees as prior work. Finally, we demonstrate that our framework scales to complex non-linear policies, and evaluate it on continuous control tasks.

cs.LG↗

arXiv2026

A Hamilton-Jacobi Reachability-Guided Search Framework for Efficient and Safe Indoor Planar Robot Navigation

Autonomous navigation requires planning to reach a goal safely and efficiently in complex and potentially dynamic environments. Graph search-based algorithms are widely adopted due to their generality and theoretical guarantees when equipped with admissible heuristics. However, the computational complexity of graph search grows rapidly with the dimensionality of the search space, often making real-time planning in dynamic environments intractable. In this paper, we combine offline Hamilton-Jacobi (HJ) reachability with online graph search to leverage the complementary strengths of both. Precomputed HJ value functions, used as informative heuristics and proactive safety constraints, amortize online computation of the graph search process. At the same time, graph search enables reachability-based reasoning to be incorporated into online planning, overcoming the long-standing challenge of HJ reachability requiring full knowledge of the environment. Extensive simulation studies and real-world experiments demonstrate that the proposed approach consistently outperforms baseline methods in terms of planning efficiency and navigation safety, in environments with and without human presence.

cs.RO↗

arXiv2026

Implicit Maximum Likelihood Estimation for Real-time Generative Model Predictive Control

Diffusion-based models have recently shown strong performance in trajectory planning, as they are capable of capturing diverse, multimodal distributions of complex behaviors. A key limitation of these models is their slow inference speed, which results from the iterative denoising process. This makes them less suitable for real-time applications such as closed-loop model predictive control (MPC), where plans must be generated quickly and adapted continuously to a changing environment. In this paper, we investigate Implicit Maximum Likelihood Estimation (IMLE) as an alternative generative modeling approach for planning. IMLE offers strong mode coverage while enabling inference that is two orders of magnitude faster, making it particularly well suited for real-time MPC tasks. Our results demonstrate that IMLE achieves competitive performance on standard offline reinforcement learning benchmarks compared to the standard diffusion-based planner, while substantially improving planning speed in both open-loop and closed-loop settings. We further validate IMLE in a closed-loop human navigation scenario, operating in real-time, demonstrating how it enables rapid and adaptive plan generation in dynamic environments. Real-world videos and code are available at https://gmpc-imle.github.io/.

cs.RO↗

arXiv2026

Glass Segmentation with Fusion of Learned and General Visual Features

Glass surface segmentation from RGB images is a challenging task, with a number of applications in robotics and scene understanding. As glass lacks coherent visual characteristics, rich context and semantic information is crucial for accurate segmentation. Consequently, prior works on the task have explored utilization of foundation models and separate semantic backbones. This paper presents a novel dual-backbone architecture for glass segmentation, applying a frozen foundation model backbone in parallel with a learned backbone trained on task-specific segmentation data. The learned backbone enables the network to specialize to glass related visual clues, while preserving the general visual feature representations of the foundation model. The hierarchical multi-scale features acquired from the dual-backbone are compressed and decoded into segmentation masks. Benchmarking of the architecture was carried out on four commonly used glass segmentation datasets, achieving state-of-the-art results. Ablation studies highlight the performance gains of the dual-backbone design and demonstrate the generalizability of the architecture with different backbone choices. The model also has a competitive inference speed compared to the previous state-of-the-art method, and surpasses it when using a lighter backbone variant. The implementation source code and model weights are available at: https://github.com/ojalar/lgnet.

cs.CV↗

arXiv2026

Fast Confidence-Aware Human Prediction via Hardware-accelerated Bayesian Inference for Safe Robot Navigation

As robots increasingly integrate into everyday environments, ensuring their safe navigation around humans becomes imperative. Efficient and safe motion planning requires robots to account for human behavior, particularly in constrained spaces such as grocery stores or care homes, where interactions with multiple individuals are common. Prior research has employed Bayesian frameworks to model human rationality based on navigational intent, enabling the prediction of probabilistic trajectories for planning purposes. In this work, we present a simple yet novel approach for confidence-aware prediction that treats future predictions as particles. This framework is highly parallelized and accelerated on an graphics processing unit (GPU). As a result, this enables longer-term predictions at a frequency of 125 Hz and can be easily extended for multi-human predictions. Compared to existing methods, our implementation supports finer prediction time steps, yielding more granular trajectory forecasts. This enhanced resolution allows motion planners to respond effectively to subtle changes in human behavior. We validate our approach through real-world experiments, demonstrating a robot safely navigating among multiple humans with diverse navigational goals. Our results highlight the methods potential for robust and efficient human-robot coexistence in dynamic environments.

cs.RO↗

arXiv2026

Multi-time Loewner energy: rate function for large deviation

The classification of probability measures that satisfy both conformal invariance and domain Markov property is equivalent to characterizing solutions to the Belavin--Polyakov--Zamolodchikov (BPZ) equations, as established by Dub\'edat~[Dub07]. In this context, the partition functions for half-watermelon SLE and for multi-radial SLE serve as fundamental solutions to the BPZ equations. In this article, we investigate the large deviation principle for both half-watermelon SLE and multi-radial SLE. The associated rate function is given by the multi-time Loewner energy, introduced in~[CHPW26]. As applications, we provide an alternative proof of the large deviation principle for Dyson Brownian motion, as well as a new derivation of the boundary perturbation property of the multi-time Loewner energy.

math.PR↗

arXiv2026

Beyond Static Datasets: Robust Offline Policy Optimization via Vetted Synthetic Transitions

Offline Reinforcement Learning (ORL) holds immense promise for safety-critical domains like industrial robotics, where real-time environmental interaction is often prohibitive. A primary obstacle in ORL remains the distributional shift between the static dataset and the learned policy, which typically mandates high degrees of conservatism that can restrain potential policy improvements. We present MoReBRAC, a model-based framework that addresses this limitation through Uncertainty-Aware latent synthesis. Instead of relying solely on the fixed data, MoReBRAC utilizes a dual-recurrent world model to synthesize high-fidelity transitions that augment the training manifold. To ensure the reliability of this synthetic data, we implement a hierarchical uncertainty pipeline integrating Variational Autoencoder (VAE) manifold detection, model sensitivity analysis, and Monte Carlo (MC) dropout. This multi-layered filtering process guarantees that only transitions residing within high-confidence regions of the learned dynamics are utilized. Our results on D4RL Gym-MuJoCo benchmarks reveal significant performance gains, particularly in ``random'' and ``suboptimal'' data regimes. We further provide insights into the role of the VAE as a geometric anchor and discuss the distributional trade-offs encountered when learning from near-optimal datasets.

cs.LG↗

arXiv2025

Reach-Avoid Differential game with Reachability Analysis for UAVs: A decomposition approach

Reach-avoid (RA) games have significant applications in security and defense, particularly for unmanned aerial vehicles (UAVs). These problems are inherently challenging due to the need to consider obstacles, consider the adversarial nature of opponents, ensure optimality, and account for nonlinear dynamics. Hamilton-Jacobi (HJ) reachability analysis has emerged as a powerful tool for tackling these challenges; however, while it has been applied to games involving two spatial dimensions, directly extending this approach to three spatial dimensions is impossible due to high dimensionality. On the other hand, alternative approaches for solving RA games lack the generality to consider games with three spatial dimensions involving agents with non-trivial system dynamics. In this work, we propose a novel framework for dimensionality reduction by decomposing the problem into a horizontal RA sub-game and a vertical RA sub-game. We then solve each sub-game using HJ reachability analysis and consider second-order dynamics that account for the defender's acceleration. To reconstruct the solution to the original RA game from the sub-games, we introduce a HJ-based tracking control algorithm in each sub-game that not only guarantees capture of the attacker but also tracking of the attacker thereafter. We prove the conditions under which the capture guarantees are maintained. The effectiveness of our approach is demonstrated via numerical simulations, showing that the decomposition maintains optimality and guarantees in the original problem. Our methods are also validated in a Gazebo physics simulator, achieving successful capture of quadrotors in three spatial dimensions space for the first time to the best of our knowledge.

eess.SY↗

arXiv2025

Self-Supervised Masked Autoencoders with Dense-Unet for Coronary Calcium Removal in limited CT Data

Coronary calcification creates blooming artifacts in Computed Tomography Angiography (CTA), severely hampering the diagnosis of lumen stenosis. While Deep Convolutional Neural Networks (DCNNs) like Dense-Unet have shown promise in removing these artifacts via inpainting, they often require large labeled datasets which are scarce in the medical domain. Inspired by recent advancements in Masked Autoencoders (MAE) for 3D point clouds, we propose \textbf{Dense-MAE}, a novel self-supervised learning framework for volumetric medical data. We introduce a pre-training strategy that randomly masks 3D patches of the vessel lumen and trains the Dense-Unet to reconstruct the missing geometry. This forces the encoder to learn high-level latent features of arterial topology without human annotation. Experimental results on clinical CTA datasets demonstrate that initializing the Calcium Removal network with our MAE-based weights significantly improves inpainting accuracy and stenosis estimation compared to training from scratch, specifically in few-shot scenarios.

cs.CV↗

arXiv2025

Bayesian Optimization Parameter Tuning Framework for a Lyapunov Based Path Following Controller

Parameter tuning in real-world experiments is constrained by the limited evaluation budget available on hardware. The path-following controller studied in this paper reflects a typical situation in nonlinear geometric controller, where multiple gains influence the dynamics through coupled nonlinear terms. Such interdependence makes manual tuning inefficient and unlikely to yield satisfactory performance within a practical number of trials. To address this challenge, we propose a Bayesian optimization (BO) framework that treats the closed-loop system as a black box and selects controller gains using a Gaussian-process surrogate. BO offers model-free exploration, quantified uncertainty, and data-efficient search, making it well suited for tuning tasks where each evaluation is costly. The framework is implemented on Honda's AI-Formula three-wheeled robot and assessed through repeated full-lap experiments on a fixed test track. The results show that BO improves controller performance within 32 trials, including 15 warm-start initial evaluations, indicating that it can efficiently locate high-performing regions of the parameter space under real-world conditions. These findings demonstrate that BO provides a practical, reliable, and data-efficient tuning approach for nonlinear path-following controllers on real robotic platforms.

cs.RO↗

arXiv2025

Integrated YOLOP Perception and Lyapunov-based Control for Autonomous Mobile Robot Navigation on Track

This work presents a real-time autonomous track navigation framework for nonholonomic differential-drive mobile robots by jointly integrating multi-task visual perception and a provably stable tracking controller. The perception pipeline reconstructs lane centerlines using 2D-to-3D camera projection, arc-length based uniform point resampling, and cubic polynomial fitting solved via robust QR least-squares optimization. The controller regulates robot linear and angular velocities through a Lyapunov-stability grounded design, ensuring bounded error dynamics and asymptotic convergence of position and heading deviations even in dynamic and partially perceived lane scenarios, without relying on HD prior maps or global satellite localization. Real-world experiments on embedded platforms verify system fidelity, real-time execution, trajectory smoothness, and closed-loop stability for reliable autonomous navigation.

cs.RO↗

arXiv2025

Threshold Strategy for Leaking Corner-Free Hamilton-Jacobi Reachability with Decomposed Computations

Hamilton-Jacobi (HJ) Reachability is widely used to compute value functions for states satisfying specific control objectives. However, it becomes intractable for high-dimensional problems due to the curse of dimensionality. Dimensionality reduction approaches are essential for mitigating this challenge, whereas they could introduce the ``leaking corner issue", leading to inaccuracies in the results. In this paper, we define the ``leaking corner issue" in terms of value functions, propose and prove a necessary condition for its occurrence. We then use these theoretical contributions to introduce a new local updating method that efficiently corrects inaccurate value functions while maintaining the computational efficiency of the dimensionality reduction approaches. We demonstrate the effectiveness of our method through numerical simulations. Although we validate our method with the self-contained subsystem decomposition (SCSD), our approach is applicable to other dimensionality reduction techniques that introduce the ``leaking corners".

eess.SY↗

arXiv2025

Preserving Plasticity in Continual Learning with Adaptive Linearity Injection

Loss of plasticity in deep neural networks is the gradual reduction in a model's capacity to incrementally learn and has been identified as a key obstacle to learning in non-stationary problem settings. Recent work has shown that deep linear networks tend to be resilient towards loss of plasticity. Motivated by this observation, we propose Adaptive Linearization (AdaLin), a general approach that dynamically adapts each neuron's activation function to mitigate plasticity loss. Unlike prior methods that rely on regularization or periodic resets, AdaLin equips every neuron with a learnable parameter and a gating mechanism that injects linearity into the activation function based on its gradient flow. This adaptive modulation ensures sufficient gradient signal and sustains continual learning without introducing additional hyperparameters or requiring explicit task boundaries. When used with conventional activation functions like ReLU, Tanh, and GeLU, we demonstrate that AdaLin can significantly improve performance on standard benchmarks, including Random Label and Permuted MNIST, Random Label and Shuffled CIFAR-10, and Class-Split CIFAR-100. Furthermore, its efficacy is shown in more complex scenarios, such as class-incremental learning on CIFAR-100 with a ResNet-18 backbone, and in mitigating plasticity loss in off-policy reinforcement learning agents. We perform a systematic set of ablations that show that neuron-level adaptation is crucial for good performance and analyze a number of metrics in the network that might be correlated to loss of plasticity.

cs.LG↗

arXiv2025

HJRNO: Hamilton-Jacobi Reachability with Neural Operators

Ensuring the safety of autonomous systems under uncertainty is a critical challenge. Hamilton-Jacobi reachability (HJR) analysis is a widely used method for guaranteeing safety under worst-case disturbances. In this work, we propose HJRNO, a neural operator-based framework for solving backward reachable tubes (BRTs) efficiently and accurately. By leveraging neural operators, HJRNO learns a mapping between value functions, enabling fast inference with strong generalization across different obstacle shapes and system configurations. We demonstrate that HJRNO achieves low error on random obstacle scenarios and generalizes effectively across varying system dynamics. These results suggest that HJRNO offers a promising foundation model approach for scalable, real-time safety analysis in autonomous systems.

cs.RO↗

arXiv2025

Inverse design of multiresonance filters via quasi-normal mode theory

We present a practical methodology for inverse design of compact high-order/multiresonance filters in linear passive 2-port wave-scattering systems, targeting any desired transmission spectrum (such as standard pass/stop-band filters). Our formulation allows for both large-scale topology optimization and few-variable parametrized-geometry optimization. It is an extension of a quasi-normal mode theory and analytical filter-design criteria (on the system resonances and background response) derived in our previous work. Our new optimization-oriented formulation relies solely on a scattering solver and imposes these design criteria as equality constraints with easily calculated (via the adjoint method) derivatives, so that our algorithm is numerically tractable, robust, and well-suited for large-scale inverse design. We demonstrate its effectiveness by designing 3rd- and 4th-order elliptic and Chebyshev filters for photonic metasurfaces, multilayer films, and electrical LC-ladder circuits.

physics.app-ph↗

arXiv2025

Unifying and accelerating level-set and density-based topology optimization by subpixel-smoothed projection

We introduce a new "subpixel-smoothed projection" (SSP) formulation for differentiable binarization in topology optimization (TopOpt) as a drop-in replacement for previous projection schemes, which suffer from near-non-differentiability and slow convergence as binarization improves. Our new algorithm overcomes these limitations by depending on both the underlying filtered design field and its spatial gradient, instead of the filtered design field alone. We can now smoothly transition between density-based TopOpt (in which topology can easily change during optimization) and a level-set method (in which shapes evolve in an almost-everywhere binarized structure). We demonstrate the effectiveness of our method on several photonics inverse-design problems and for a variety of computational methods (finite difference, Fourier-modal, and finite-element methods). SSP exhibits both faster convergence and greater simplicity.

physics.optics↗