Papers

Emerging non-matrix ML kernels, such as LayerNorm, GeLu, FFT or circular convolutions, demand low-latency, energy-efficient spatial accelerators beyond MatMul-centric arrays. STELLA presents a spatio-temporal elastic 16 nm coarse-grained reconfigurable array (CGRA) with a rapid configuration path, per-PE hardware loop control, and a low-latency, deeply pipelined elastic fabric with spatio-temporal data reuse. STELLA reaches up to 110 GOPS/mm2 at 850 MHz, and improves effective kernel throughput by 4.84-7.14x over baseline CGRAs.

In this paper, the dispersion behavior of periodic cross-shaped unit cells is investigated with emphasis on Dirac-type dispersion using an equivalent circuit modeling approach. Two unit-cell geometries, including a simple cross structure and a modified configuration with a central patch, are analyzed using full-wave eigenmode simulations and scattering-parameter-based dispersion extraction. An equivalent circuit model is developed to capture the dominant coupling mechanisms and accurately reproduce the dispersion characteristics near the $\Gamma$-point. The results demonstrate that the proposed circuit model exhibits good agreement with full-wave simulations and provides a physically intuitive framework for analyzing stopband behavior and mode degeneracy. Furthermore, the limitations of S-parameter-based dispersion extraction in the presence of low-Q radiative modes are highlighted.

Accurate human torque estimation is crucial for enabling task-agnostic control in robotic exoskeleton systems. However, estimation errors may cause mismatches between the robot assistance and the human intention, degrading controllability and task performance. In this paper, we address this issue by formally defining matched assistance as scenarios in which the robot positively contributes to human movement. Based on this definition, we develop a theoretical framework to design the robot's desired interaction torque that guarantees a lower bound on the matched assistance probability. Importantly, the proposed guarantee holds over the entire torque distribution, including unseen data beyond the training tasks. This provides our method with strong reliability and generalization, both of which are critical for effective exoskeleton control. The proposed strategy is implemented on the ABLE upper-limb exoskeleton and evaluated in a multi-task setup. Experimental results validate the theoretical guarantees and demonstrate that the proposed strategy achieves effective general performance across several tasks, guaranteeing movement smoothness while reducing human physical effort.

In integrated sensing and communication (ISAC) systems involving multiple operators, unmanned aerial vehicle (UAV) tracking can benefit from sensing at multiple base stations, while raw sensing records, channel information, and transmit decisions remain local to each operator. The resulting problem is to obtain a reliable UAV prediction from different track estimates and use it to guide transmission without centralizing their data or control variables. To resolve this, we propose a two-timescale framework comprising slow-timescale motion-uncertainty calibration and online track fusion with predictive beamforming. Local radar innovations calibrate the uncertainty assigned by each tracker to unmodeled UAV motion, with only the resulting parameters shared across operators. During online tracking, covariance intersection (CI) combines local estimates without requiring knowledge of correlations between their estimation errors. The fused prediction then guides each operator's transmission design subject to communication QoS, power, and tracking constraints. We further establish exact rank one recovery for the communication covariances and finite interval bounds on local tracking uncertainty. Simulations show improved consistency of tracking uncertainty under substantial motion model mismatch. CI avoids overconfidence under correlated errors, while using the current fused prediction reduces RMSE by about 31% relative to transmission designed for communication alone, with less than 2% additional power. Ablation further shows that the power difference between current and outdated predictions is driven mainly by predictive covariance rather than predictive mean.

This paper proposes a communication-free multi-robot task allocation framework based solely on local observations. In this study, tasks are defined as reaching target locations. Each robot estimates the positions of neighboring robots using a Labeled Multi-Bernoulli (LMB) filter and independently assigns tasks through a greedy auction-based strategy. By continuously updating state estimates and reallocating tasks during execution, the proposed method enables decentralized coordination without explicit communication. Monte Carlo simulations demonstrate that the proposed method enables effective cooperative task allocation without inter-robot communication while remaining robust to measurement clutter and observation uncertainty.

A facilitator is an intermediary that offers renewable producers and consumers fixed-price contracts and, acting as their balance responsible party, manages the residual imbalances in the market. Pooling imperfectly correlated residuals nets consumers' imbalances and reduces the portfolio's total imbalance cost, but raises an allocation question: how should these savings be divided among heterogeneous consumers? We formulate this as a cooperative game, the imbalance netting game, and compare six allocation mechanisms under a two-price imbalance settlement in terms of computational requirements, budget balance, group rationality, and additivity. We establish three analytical results: a necessary and sufficient condition for budget balance of the marginal cost contribution mechanism, group rationality of the marginal cost contribution and Vickrey-Clarke-Groves mechanisms, and a necessary and sufficient condition for when the Gately point is well-defined. On Danish 2024 data for 19 consumers, aggregation reduces imbalance cost by 10%, but how these savings are shared depends strongly on the allocation rule. A flat-rate allocation proportional to consumption, used as a benchmark for socialized imbalance pricing, charges some consumers more than twice their standalone cost, whereas all the game-theoretic mechanisms studied produce stable allocations in practice.

Unit Commitment is a computationally demanding mixed-integer linear optimisation problem requiring many binary commitment decisions across a scheduling horizon. To reduce this computational burden, machine learning approaches can predict a subset of these decisions, thereby shrinking the search space explored by the optimisation solver. Existing confidence-based approaches determine which variables to fix based on user-defined probability thresholds, which are agnostic to the downstream optimisation problem. We address this limitation by introducing an optimisation-aware framework that yields generator-specific confidence thresholds based on the impact of fixing errors on Unit Commitment solution quality. This approach won first place in the 2025 EPRI AI-ccelerating Unit Commitment competition. The proposed framework achieves a mean optimality gap below 0.5% while also delivering an average speed-up of more than 20x. It therefore provides a general mechanism for translating probabilistic predictions into controlled reductions of mixed-integer search spaces, directly linking learning decisions to their downstream computational and economic consequences.

Deep learning methods like neural networks have greatly simplified the computation of safety certificates for complex nonlinear systems with unknown dynamics. However, due to the data-driven nature of these certificates and the complex architecture of neural networks, computation time as well as robustness guarantees across unseen data remain a challenge. This work aims to formally verify safety properties of discrete-time unknown systems by synthesizing extreme learning machine (ELM)-based barrier certificates. Compared to neural network counterparts, this approach greatly improves convergence guarantees and computational time due to its architectural simplicity and the convex nature of the underlying optimization problem. By minimizing the Lipschitz constant of the candidate barrier, we present a grid-based sampling technique to formally verify its validity using the minimum number of samples required. We demonstrate through numerical examples the effectiveness of our approach, and compare with traditional deep-learning based certificate synthesis to highlight its benefits.

A deep classifier is defined not only by the decision it produces, but also by the sequence of transformations through which that decision is formed. Treating this evolution as a dynamical system across layers provides a natural framework for asking how decision geometry emerges through depth and how far back we can trace a boundary's dynamical signature. We model a feed-forward classifier as a finite, nonautonomous discrete dynamical system, with layers playing the role of discrete time steps. We study the Finite-Time Maximum Lyapunov Exponent (FTMLE) of the data samples' dynamical trajectory through depths of the classifier. The FTMLE measures the rate of convergence/divergence of nearby trajectories. We move the observation endpoint backward from probabilities to logits and then to hidden representations. For Gaussian classes, we prove that probability-level FTMLE carries a clear geometric signature of the decision boundary, with its dominant direction aligned with the boundary normal. Moving one step backward to the logits, we prove this relationship is no longer universal but depends critically on how the classifier is trained, particularly on the choice of loss function. Moving further backward to the hidden representation, the connection becomes more conditional: boundary-related FTMLE can persist, but only under identifiable structural conditions. We propose geometry-aware fine-tuning for restructuring the classifier's hidden FTMLE, and propose conditions for guaranteed concentration of high hidden FTMLE near the decision boundary. Through our numerical results, we show the generality and validity of our theoretical results. Understanding the evolution of data samples as traveling through the layers of classifier provides a principled foundation for identifying where boundary-relevant sensitivity emerges and for developing layer-aware regularization strategies.

This paper presents a scalable optimal-transport-based framework for terminal distribution matching in multi-agent systems. While optimal transport provides a natural way to measure distributional mismatch and assign agents to a desired spatial distribution, global discrete transport can become computationally expensive for large-scale systems. We address this bottleneck by partitioning agents and target samples into spatially corresponding blocks and solving smaller local transport problems. Under a mass-balance condition, the resulting restricted coupling remains feasible for the global problem and provides an upper bound on the Wasserstein cost. The local assignments generate target locations for finite-horizon agent control, applicable to both linear and nonlinear dynamics. By alternating local assignment and control, we establish a cycle-to-cycle descent guarantee for the resulting transport surrogate. The proposed framework therefore enables scalable terminal distribution matching while retaining a rigorous connection to the Wasserstein objective. The technical soundness of the proposed results is validated through simulations.

A stochastic hybrid system (SHS) is governed by a stochastic differential equation (SDE) describing the continuous dynamics and a Markov reset kernel triggered on the guard surface. Its probability evolution can be described by a hybrid Fokker-Planck (HFP) equation with a partial differential term corresponding to the SDE and an integral term arising from the reset kernel. This work shows that such an SHS can be approximated by an SDE in a higher-dimensional latent space where the sample paths are continuous. The key to this result is to encode different branches of the reset kernel using auxiliary variables, transforming the resets into deterministic ones that enable topological gluing. By the embedding theorem, the glued manifold can then be embedded into a higher-dimensional Euclidean space. We show that the probability evolution on the embedded image no longer requires explicit reset terms in the HFP equation. Building on this theorem, we design a loss that matches the evolving state distributions, enabling a single latent SDE to recover the probability evolution of the SHS without mode labeling, trajectory segmentation, or event-based simulations.

Robots operating in human-centered environments must safely navigate among multiple dynamic obstacles to avoid collisions with people and surrounding infrastructure. Control barrier functions (CBFs) provide an effective mechanism for safety filtering, and recent CBF-based reinforcement learning (RL) methods embed such safety information into learned policies. However, executing only safety-filtered actions during training can restrict policy exploration, a limitation that becomes particularly consequential in dynamic scenes where safety depends on relative robot-obstacle motion. We propose DODGER, a safety-guided RL framework that directly executes policy-generated actions to drive training rollouts while using CBF-filtered references and constraint violations to shape the policy toward collision-avoidance behavior. We evaluate DODGER through a Dubins-car safety analysis and demonstrate goal-directed navigation among multiple dynamic obstacles in full-order humanoid simulation and real-world humanoid experiments using LiDAR-based perception, without a runtime safety filter.

Vision-Language-Action (VLA) models based on generative frameworks, such as Flow Matching, have recently achieved impressive performance in robotic manipulation. Unlike deterministic policies, Flow Matching enables VLA models to learn conditional action trajectory distributions, where latent noise vectors induce different actions under the same task scenario. However, we observe that these distributions are often ill-formed, with successful and failed behaviors coexisting while considerable probability mass remains in unfavorable regions. To this end, we propose Online-ES, an online adaptation framework for Flow Matching VLAs based on Evolution Strategy (ES), which refines the learned action trajectory distribution through interaction feedback. Instead of pruning the latent noise space, our method performs evolutionary exploration directly in the action trajectory space, where diverse trajectories generated by Flow Matching provide candidate solutions for adaptation. By perturbing sampled trajectories and evaluating their execution outcomes, we derive a self-supervised MSE objective that transfers the evolution direction from trajectory space into model parameter space. Mathematically, we prove that the proposed objective provides an unbiased estimator of the optimal evolution direction. Moreover, we also incorporate failure experiences as negative feedback to regularize the evolution direction, steering the policy away from previously explored failure regions. Experiments in both simulation and real-world environments demonstrate that Online-ES achieves policy improvement comparable to reinforcement fine-tuning, without learning a value model or computing advantages.

In this paper we give a polynomial-time reduction from the Subset Sum Problem to unconstrained static output feedback stabilization, establishing its NP-hardness. The construction uses two scalar building blocks to impose approximate discrete choices and a weighted-sum constraint. Once the problem is encoded, we relate the stability of the $N+1$ decoupled loops encoding the problem to that of a coupled plant. This is accomplished by leveraging frequency separation via a band-pass transformation, and comparing the root counts of the true characteristic polynomial with that of the different blocks in different regions of the right half-plane. The construction then naturally bounds every stabilizing gain and gives explicit modulus-margin estimates, ensuring that the plant data have polynomial binary encoding length.

We develop a task-relative framework for certifying residual wrench authority after hover and contact loading in multirotors with bounded actuators. Using convex geometry, we derive signed margins for prescribed convex reserves, including Euclidean balls and weighted ellipsoids. We obtain computable reserve certificates from actuator-interiority bounds to support slack-maximizing allocation. To preserve the required reserve, we propose command projection onto a tightened feasible set. We then connect the available reserve to structured gain synthesis and certify a local tracking region that respects actuator limits. Within this region, we establish nominal exponential convergence and robust ultimate boundedness. For the prescribed task and morphology family, we show that the optimized octarotor attains a larger margin than the optimized hexarotor at equal total thrust. We evaluate the proposed framework in closed-loop simulations of sustained rigid-wall contact using a fixed-geometry octarotor and a variable-tilt quadrotor with matched installed thrust. The quadrotor's local certificate admits a higher normalized push limit for the prescribed task family. In tests beyond the realizability boundaries, we observe the predicted loss of authority through rotor-thrust limits for the octarotor and tilt-servo limits for the quadrotor.

This paper proposes a reinforcement learning (RL) framework for safe gain scheduling based on forwardinvariance-induced action-space design. Under stated nominalmodel and inversion-domain assumptions, rather than enforcing safety through runtime shielding or penalty-based constraints, safety is embedded directly into the policy class. Specifically, we construct a finite library of feedback controllers sharing a common Lyapunov certificate that establishes forward invariance of a prescribed admissible set under arbitrary switching. Consequently, any policy whose actions are restricted to this library, including policies encountered during RL exploration, inherits the same certificate. Policy optimization can therefore focus on closed-loop performance without runtime safety filtering or action projection. The framework is instantiated for quadcopter hover regulation, where a DQN schedules among certified feedback controllers. Nonlinear MuJoCo simulations demonstrate state-dependent gain scheduling and empirically evaluate robustness to wind, model mismatch, sensor noise, and sensing delay. The results illustrate how safety certification can be separated from policy optimization by learning over a forward-invariant policy class.

Meteor Burst Communication (MBC) utilizes the transient ionized trails left by meteors to reflect Very High Frequency (VHF) signals, enabling long-range, beyond-line-of-sight communication without reliance on terrestrial or satellite infrastructure. Despite its resilience in austere and contested environments, MBC is limited by brief communication windows, low signal-to-noise ratio (SNR), and inconsistent channel availability. Recent advancements in Reconfigurable Intelligent Surfaces (RIS) offer a transformative solution by enabling dynamic control over signal propagation through programmable reflective elements. This paper proposes a novel system architecture that integrates RIS into MBC networks, incorporating real-time adaptive control, optimized deployment strategies, and Monte Carlo simulations to refine RIS placement and operational parameters.

This paper presents a method for approximating occupancy distributions, a common probabilistic representation used in trajectory planning for autonomous vehicles operating in uncertain environments. The proposed method employs B-spline surfaces in conjunction with regularization techniques to ensure smoothness and differentiability. Interpreting the resulting approximation as an intensity function of a Poisson random field enables seamless integration of multiple occupancy distributions into a coherent risk representation, while retaining compatibility with the semantics of probability distributions. The method is tailored to optimal control problems (OCPs), where solvers benefit from gradient and higher-order derivative information. It also preserves information about the spatial and temporal structure of occupancy distributions, which is critical for handling dynamic obstacles. We demonstrate the feasibility of the approach in a trajectory planning scenario involving autonomous vehicles and moving obstacles with time-varying uncertainty. By enabling controlled risk acceptance, our formulation extends beyond conservative "no-collision" strategies and allows for admissible trajectories that would otherwise be ruled out. In our application scenario, we report a reduction in solver computational load of up to 50% through proper tuning of the regularization.

In distributed control schemes, the communication topology that defines information sharing between agents must be designed prior to online control execution. Previous data-driven works typically decouple the topology and controller design problems. This paper investigates data-driven approaches to topology design that guarantee the existence of a stabilizing controller, whilst trading off the level of required communication against control performance. We formulate a data-driven co-design scheme that directly co-optimizes the topology and controller over the link costs and closed-loop control cost. When the topology designer does not have access to the agents' control objectives, we propose a control-aware approach that couples the two design problems within a sequential scheme. In both cases, the topology is optimized within a mixed-integer semidefinite program (MISDP). Simulations including the IEEE 14-bus power system test case demonstrate the effectiveness of both co-design and control-aware schemes. Numerical examples show lower computation time for the control-aware case than for co-design.

The discrete algebraic Riccati equation (DARE) is used to solve for the optimal feedback gain in linear-quadratic regulator (LQR) control of discrete-time systems. In this letter, we consider the effect of perturbations to the LQR data on the DARE solutions. We present a new frequency domain approach to derive an explicit bound on the difference in DARE solutions under such perturbations. Our bounds are similar to other results that have recently appeared in the literature with two distinctions. First, we use a frequency domain constant that measures the degree of closed-loop stability, in contrast to other results that use a time domain measure. Second, we start from weaker detectability assumptions on the LQR state cost matrix.

Autonomous underwater robots require robust perception, estimation and control to operate in confined environments. This paper presents an open-source BlueROV2 platform combining onboard vision with nonlinear Model Predictive Control (NMPC) for autonomous navigation and docking. The platform integrates an NVIDIA Jetson Orin NX and an Intel RealSense D435i stereo camera in a modular pressure housing. Underwater-calibrated stereo depth and realtime object detection provide relative position measurements of nearby BlueROV2 vehicles in the camera and body frames. A quaternion-based estimator fuses external pose and inertial measurements, while an NMPC controller based on a nonlinear six-degree-of-freedom model tracks planned navigation and docking trajectories. To support reproducible development, we also provide open-source physics-based PX4 SITL and Gazebo environments, multi-robot simulation tools and a lowcost physical docking station. Experiments evaluate underwater perception, onboard computational performance, state estimation, trajectory tracking and autonomous docking.

Effective AI adoption in cyber-physical systems (CPS) depends on embedding design knowledge into engineering practice. Yet as AI-enabled components increasingly replace analytically derived control laws, this occurs without a systematic understanding of how controller architectures differ or remain similar across paradigms. We address this gap with an empirical study of traditional and AI-enabled Simulink controllers, guided by a literature-derived taxonomy of ten structural categories and nine functional roles. The study analyzes 62 real-world models spanning 8 controller types and 10 application domains, and surveys 13 practitioners, identifying three architectural tensions. First, subsystem organization dominates all controller structures regardless of paradigm, occupying 68-72% of controller footprint, while core control logic occupies minimal space. Second, AI-enabled controllers rely heavily on discrete dynamics and user-defined abstraction, categories largely absent from AI literature, exposing a gap between described and implemented architectures. Third, constraint enforcement blocks largely disappear from AI-enabled models despite practitioner expectations. This reveals a misalignment where safety mechanisms shift from explicit structure to implicit training-time artifacts, breaking traceability.

Many maintenance models implicitly assume that maintenance can be performed whenever intervention is warranted. In practice, however, environmental uncertainty, such as weather and sea conditions, can make maintenance opportunities intermittent and dynamically evolving. We consider a degrading asset for which preventive maintenance may be performed before failure, but intervention is possible only when the asset is accessible. Accessibility evolves stochastically over time and therefore affects not only whether maintenance can be performed now, but also the value of waiting for future opportunities. We formulate this setting as a finite-state Markov decision process under a long-run average cost criterion and investigate the structure of the optimal maintenance policy. Under monotone degradation and cost conditions, we show that an optimal policy retains a threshold form in asset condition, but unlike a single threshold, the optimal threshold varies with the accessibility state. Thus, intervention depends jointly on the asset condition and the expected evolution of future maintenance opportunities. Through a numerical study motivated by offshore wind turbine maintenance, we examine how accessibility dynamics, degradation characteristics, and economic parameters shape the optimal thresholds and compare the optimal policy with constant-threshold and age-based maintenance policies. In a representative setting, adapting the condition threshold to accessibility reduces long-run average cost by 4.31% relative to an optimized condition-based maintenance policy. Relative to an optimized age-based policy, the optimal policy reduces long-run average cost by 33.95%. The results show that maintenance thresholds are not universal: they should adapt to the degradation and accessibility characteristics of the system, and failing to account for these conditions can lead to substantial cost increases.

Can a local solver return the guaranteed globally optimal solution to a nonconvex mixed-integer polynomial power grid optimization problem? By mixing low-rank semidefinite programming (SDP) and moment-based lifting in the Lasserre hierarchy, this paper provides anecdotal evidence in the affirmative. Specifically, we iteratively tighten a moment-based relaxation of the AC Optimal Transmission Switching (AC-OTS) problem, including higher order moment-based constraints, rooted in the Lasserre hierarchy, until it is tight (i.e., primal feasible). We then re-solve this problem using a local, low-rank SDP solver (Knitro), plugging the associated dual variables into a bounding Lagrange dual function. By demonstrating primal and dual objective agreement and primal feasibility, we confirm the solution as the exact, global solution. From these initial results, we hypothesize that mixing (i) low-rank (i.e., highly scalable) SDP methods with (ii) moment-based relaxation tightening could be a scalable alternative to global branch-and-bound-based methods.

Stochastic differential equations (SDEs) can be studied via Itô calculus and rough path theory. For stochastic optimal control, these two frameworks give distinct Pontryagin Maximum Principle (PMP) optimality conditions with forward-backward SDEs (FBSDEs) or rough differential equations. We show that the adjoint equations of the Itô and rough PMPs are connected via the conditional expectation $p_t^{\text{It\^{o}}}=\mathbb{E}[p_t^{\text{rough}} \mid \mathcal{F}_t]$, where $\mathcal{F}_t$ represents information available at time $t$. First, we derive a rough stochastic PMP for problems with adapted controls that does not use FBSDEs. Its proof extends the rough stochastic PMP over deterministic controls by considering stochastic needle variations. Second, we derive a unified PMP connecting the Itô and rough PMPs, using Itô-Stratonovich conversion formulas and duality identities between the forward tangent and backward adjoint SDEs. As a first application, we rederive the adjoint matching method for fine-tuning generative models. As a second application, we propose an indirect shooting method for a class of feedback problems. Overall, these results give a new conditional bridge connecting two popular frameworks for stochastic optimal control.

A comparison between adaptive and fixed-time traffic signals can change when only their timing settings change. We examine this sensitivity in 240 simulation runs on one OpenStreetMap-derived urban network, using eight configurations, three arrival rates and ten paired demand seeds. The experiment varies the maximum green of presence-based actuation, retimes the fixed baseline, and includes a discharge-based phase-termination rule. The endpoint is finite-window time spent per offered trip, including entry waiting and penalties for removed or abandoned trips. At the highest tested load, actuation with a maximum green of twice the planned split has a mean endpoint 57.4 per cent above the original fixed plan. Reducing that multiplier to 1.25 puts it 70.7 per cent below the same plan. Against the best of three tested fixed plans, discharge-based termination reduces the mean endpoint by 14.8, 15.8 and 18.3 per cent across the three loads. Both timing sweeps favour their shortest tested setting, so neither identifies an optimum. This exploratory study uses synthetic demand, negligible start-up lost time and physical removal of persistently stationary vehicles. The results support testing timing sensitivity before attributing performance to a controller family; they do not establish a setting for real-world deployment.

The scaled relative graph (SRG) represents the joint gain and phase properties of an input–output operator in the complex plane. This paper characterizes the SRG closure of causal, stable, square discrete-time linear time-invariant (LTI) systems on one-sided square-summable sequences. The Beltrami–Klein image of this closure equals the convex hull of the numerical ranges of the transformed frequency-response matrices. For real-coefficient single-input single-output systems, this yields the hyperbolic convex hull of the discrete-time Nyquist locus. The proof addresses the Hardy-space restriction imposed by one-sided inputs, which excludes persistent sinusoids, by replacing them with explicitly constructed finite-duration sinusoids. This construction shows how points in frequency-wise SRGs arise as limits of operator SRG points generated by admissible inputs. The characterization enables model-based computation of the closure from a state-space realization using frequency-response evaluations, numerical ranges, and planar convex hulls, without solving linear matrix inequalities.

Verifying a vision-based neural feedback system requires a model of the observations its controller acts upon. Such a model must capture the variation the sensor produces, while remaining tractable for closed-loop analysis. Generative adversarial networks (GANs) have served as perception surrogates, but they are large, reproduce complex scenes poorly, and are hard to verify. We explore stochastic world models as a richer class of perception surrogates. We train a world model with physically grounded latents, built from operations that standard verifiers bound. It reproduces held-out frames more faithfully than GAN surrogates with up to 130 times as many parameters. To verify these surrogates, we develop a procedure that combines falsification, adaptive refinement, symbolic, and backward analyses. On an emergency braking benchmark with a GAN surrogate, our procedure resolves the entire state space, 38% of which the state-of-the-art verifier left unresolved. On the RGB version of the benchmark, where no verification results have previously been reported, our procedure resolves over 80% of the state space with a world model surrogate.

We propose a continuous-time algorithm for zeroth-order global optimization of smooth functions on compact manifolds that synthesizes Riemannian gradient dynamics using only objective measurements, without evaluating gradients. The algorithm is formulated as an ordinary differential equation driven by piecewise-smooth McShane-type approximations of the Wiener process, with a geometric compensation term that depends only on the actuation frame and not on the objective function. Our main result establishes infinite-horizon practical probabilistic guarantees for fixed approximation parameters. To this end, we show that the algorithm's trajectories approximate, in the mean-square sense, a Riemannian Langevin diffusion whose unique invariant Gibbs measure concentrates on the set of global minimizers. We exploit this approximation to establish finite-horizon probabilistic convergence guarantees and directly analyze the algorithm's long-time behavior to obtain the infinite-horizon result.

We study generalized learning dynamics in multi-agent systems whose joint state evolves on a manifold and whose agents act through state-dependent, potentially nonholonomic vector fields. Under a bundle-splitting condition, we show that these dynamics admit an intrinsic representation as projected Riemannian gradients, giving rise to a class of nonholonomic gradient play dynamics. We characterize the local stability of its equilibria through an intrinsic linearization that explicitly captures the effects of the Riemannian connection and the nonholonomy of the actuation frame. The framework recovers classical gradient play on Euclidean spaces and manifolds as special cases while accommodating nonholonomic actuation. We then develop a geometric theory of deception under asymmetric information, whereby an agent exploits privileged knowledge of other agents' learning rules to manipulate the emerging equilibrium. We show that deception effectively tilts the Riemannian geometry perceived by the oblivious agents, distorting their projected gradient directions. We establish persistence of exponentially stable equilibria over an open set of deception parameters and derive an explicit first-order characterization of the resulting equilibrium displacement. Analytical and numerical examples illustrate the framework and its implications for equilibrium manipulation in games.