arXiv subjects

Lars Lindemann

Publications and source records attributed to Lars Lindemann.

At least 19 recordsLinked to original sources

arXiv2026

Learning Stabilizing Latent Feedback Controllers via Multi-Step Backward Losses

Can learned latent dynamics models support the design of feedback controllers that provably stabilize the original system? For linear time-invariant systems, we show that learning linear autoencoders and latent dynamics with multi-step prediction-reconstruction losses $\unicode{x2014}$ which we term "backward losses" as they encourage latent trajectories to reconstruct full state trajectories $\unicode{x2014}$ provably recovers the structure needed for stabilization. Specifically, a sufficiently long reconstruction horizon ensures that a minimum ${H}_\infty$-norm controller designed using the learned latent model stabilizes the original system through output-feedback via the corresponding encoder, provided the latent dimension is large enough to capture all non-stable modes of the underlying system. We also show why both reconstruction and a multi-step horizon are essential: forward prediction losses that require only low prediction error along latent trajectories admit global loss minimizers that discard unstable modes regardless of horizon length, while single-step reconstruction losses can yield latent models whose stabilizing controllers fail to stabilize the original system. Finally, experiments on a non-linear flexible-arm system illustrate the practical implications of our results for learning non-linear autoencoders and latent dynamics.

math.OC↗

arXiv2026

Multi-Variable Conformal Prediction: Optimizing Prediction Sets using Multiple Calibration Variables

Split conformal prediction constructs prediction sets with finite-sample coverage guarantees, but its calibration stage is limited to adjusting a single threshold parameter. Hence, the shape of the prediction sets must be fixed beforehand, typically by fitting it on a reserved part of the calibration data. We introduce multi-variable conformal prediction (MCP), a framework that jointly optimizes and calibrates multiple prediction-set parameters in a single optimization problem, eliminating calibration data split without sacrificing finite-sample coverage guarantees. Building on scenario theory, a principled framework for certifying data-driven decisions, we propose two tractable variants: RemMCP, grounded in constrained optimization with constraint removal, which generalizes split conformal prediction; and RelMCP, based on penalized optimization with constraint relaxation, which also supports non-convex problems, albeit at a higher computational cost. In experiments with ellipsoidal and multi-modal prediction sets, RemMCP and a heuristic, adaptive version of RelMCP consistently meet the target coverage, with lower variance across calibration runs than baselines with calibration data split, and in most settings with smaller or comparable prediction sets.

stat.ML↗

arXiv2026

Motion Planning with Temporal Logic Precedence Specifications in Dynamic Environments via Spacetime Augmented Graphs of Convex Sets

We extend the augmented graph of convex sets GCS framework for motion planning with temporal logic precedence specifications to dynamic environments in which obstacles, keys, and doors undergo piecewise-linear translation and/or dilation over time. The main insight is that piecewise-linear motion of polytopic sets in R^d lifts exactly to a static polytopic partition of spacetime R^d X R_>=0. We show that the main result from the static case carries over to spacetime essentially without modification: a shortest path in the spacetime augmented GCS provides an exact optimal solution to the motion planning problem with precedence specifications. Moreover, the layered subgraph lattice that encodes signal temporal logic (STL) precedence specifications retains precise correspondence with the Bellman--Held--Karp (BHK) algorithm, and the full library of restricted but expressive STL specifications generalizes to the dynamic setting. Further, the framework allows time-gated keys and doors, collectible or passable only within a temporal window. The geometric side of the framework requires two modifications: a causality constraint (the time coordinate of a trajectory must be non-decreasing) and a spacetime speed constraint (bounded physical velocity), both of which are convex in the Bézier control points.

eess.SY↗

arXiv2026

Anytime-Valid Certification of Robustness Margins for Safe Control via E-Values

Robust control uses the error between a known model and the true system as a robustness margin. However, this error is usually unknown: conservative estimates restrict feasibility and performance, while underestimates can result in violations of the control property. We estimate this robustness margin from online data using e-values, a statistical tool for hypothesis testing, in the setting of discrete-time control barrier functions (CBFs). Here, we measure the robustness margin as the difference between the observed CBF and the model-based CBF prediction. We then design a robust CBF controller in three steps by: (1) selecting a set of candidate margins, (2) obtaining validity certificates for these candidates via sequential tests based on e-values, and (3) updating the CBF controller with the smallest certified candidate. The deployed tests accumulate evidence against the hypothesis that an exceedance risk, the probability of the robustness margin exceeding the candidate margin, remains at or above a pre-specified failure probability $α$. Our tests are anytime valid and thus enable the use of certified candidates in the CBF controller, guaranteeing that the probability that the exceedance risk of a certified margin exceeds $α$ is at most a user-chosen confidence $δ$. We validate our approach on navigation problems across different environments with visualizations in NVIDIA Isaac Sim.

eess.SY↗

arXiv2026

Conformal Prediction Regions for Continuous-Time Trajectories under Random Sampling

Uncertainty quantification for continuous-time trajectories is a prerequisite in many safety-critical engineering domains. However, a major challenge in data-driven uncertainty quantification is that calibration trajectories are sampled only at discrete, often sparse, and random intervals. Standard conformal prediction methods typically fail to provide guarantees in between sampling times. In this work, we introduce a new technique to obtain valid conformal prediction regions for continuous-time trajectories that are sampled at discrete and possibly random times. To accomplish this goal, we make three contributions: (1) we provide an algorithm that leverages regularity properties of the underlying trajectories to obtain valid prediction regions in between samples, (2) we provide methods that estimate valid bounds on the aforementioned regularity properties from an additional high-frequency calibration dataset, and (3) we introduce and compare several algorithms to deal with random sampling times. Finally, we present experiments where we validate that our methods achieve valid coverage across the entire continuous trajectory.

eess.SY↗

arXiv2026

A Unified Perspective on Conformal Prediction and Wasserstein Distributionally Robust Optimization for Uncertainty Quantification

Uncertainty quantification from finite data is central to machine learning, optimization, and automation systems, where decisions must remain reliable under limited samples and test-time distribution shift. Conformal prediction (CP) and distributionally robust optimization (DRO) offer two complementary approaches: CP constructs data-dependent prediction sets with distribution-free finite-sample validity under exchangeability, while DRO optimizes worst-case performance over an ambiguity set around an empirical distribution. We develop a unified probabilistic perspective on CP and DRO by viewing both as ways to turn finite calibration data into a data-dependent quantile estimator that a test score falls below with high probability. From this perspective, CP and DRO correct the empirical quantile along two coordinates of the same family of estimators: CP inflates the quantile level, whereas DRO shifts the quantile value through an ambiguity radius. Both methods provide the same calibration-conditional guarantee for the true distribution, requiring the target coverage to hold with high probability over the calibration sample. Their constructions differ, however: CP uses a closed-form, distribution-free level correction, while DRO uses a value-space correction whose certified radius depends on properties of the unknown distribution and additionally guarantees coverage uniformly over the ambiguity set. This distinction emerges in the tails of the score distribution. Because CP relies on sparse upper-tail order statistics of the calibration samples, its level inflation barely moves the estimator when those samples are dense near the target quantile but overshoots when they are sparse, whereas a well-chosen DRO radius corrects in value space and may avoid this overshoot.

math.OC↗

arXiv2026

Safety-aware Model Predictive Path Integral Control with Signal Temporal Logic

Safety-aware motion planning remains a challenge in robotics, especially when missions are time-critical and are under complex specifications. In this paper, we propose safety-aware-stl-mppi, a computationally efficient sampling-based receding-horizon planning framework designed to promote satisfaction of constraints expressed in Signal Temporal Logic (STL). Our approach encodes discrete-time STL formulas into candidate time-varying control barrier functions (CBF), which are integrated into a model predictive path integral (MPPI) controller. Our method inherits the benefits of low computational cost from an efficiently parallelizable sampling based planner and utilizes CBF for constraints expressed in STL. We compare against several MPPI baselines using four artificial Mars Rover planning case studies with a diverse environment and cost setups, where we show our method consistently achieving high safety and efficiency. We show a quadcopter planning experiment with NVIDIA Isaac Lab.

cs.RO↗

arXiv2026

Domain-Aware Machine Learning for Accelerating MILP-Based Motion Planning with Temporal Logic and Chance Constraints

Motion-planning problems with temporal-logic or chance constraints are often encoded as mixed-integer linear programs (MILPs). Although these encodings provide rigorous specifications, their combinatorial structure can make planning prohibitively slow. Machine learning for combinatorial optimization (ML4CO) has accelerated general-purpose MILP solving, but its standard graph representations discard semantic information available in control problems, such as variable roles, time indices, sample identities, and formula structure. We introduce a domain-aware ML4CO framework for MILP-based motion planning with temporal logic and chance constraints. The framework augments a conventional variable--constraint bipartite graph with features derived from the planning formulation and uses the resulting representation for two solver-guidance tasks: selecting branching backdoors and configuring solver parameters. We study three domains---Signal Temporal Logic (STL) planning, chance-constrained planning through Conformal Predictive Programming (CPP), and multi-agent Capability Temporal Logic (CaTL) planning---and compare against solver defaults, domain-agnostic learned methods, non-learned branching rules, MCTS transfer, and SMAC3 transfer. Across the tested distributions, domain-aware backdoor selection has the lowest reported mean solve time in all three domains, improving on default Gurobi by 14.4--20.4%. Domain-aware configuration also has the lowest mean primal gap and primal integral in all three domains under a fixed SCIP time limit. These results show that exposing control-specific structure can improve learned MILP guidance beyond generic optimization features.

eess.SY↗

arXiv2026

Multi-Agent Planning with Spatio-Temporal and Topological Constraints using STL-GO

Multi-agent planning problems arise in a variety of engineering applications, such as multi-robot wildfire fighting and unmanned aerial inspection in factories. A particular challenge is the existence of spatio-temporal (i.e., when and/or where an agent should do what) and topological constraints (i.e., how agents should interact), as typically formalized via the notion of graphs. Over the last years, various frameworks have been proposed that can capture such constraints via spatio-temporal logics. We focus here on spatio-temporal logic with graph operators (STL-GO), a recent formalism that supports reasoning about multiple agents and their topologies, such as sensing, communication, and task topologies. In this paper, we consider the problem of planning multi-agent paths that satisfy constraints written in STL-GO. This problem is particularly challenging due to the need of encoding multiple, potentially time-varying graphs via the graph operators inherent to STL-GO. We present two encodings of this problem, one based on mixed-integer programming (MIP) and another based on satisfiability modulo theory (SMT), with soundness guarantees. We provide a unified interface for specifying agent constraints, their graph topologies, and the STL-GO specification, enabling seamless use of both methods and facilitating direct comparison between them. We evaluate both encodings on a multi-UAV search-and-rescue benchmark, ablating over team size and graph complexity, highlighting the expressiveness of the proposed encodings under dynamic multi- graph interactions.

cs.AI↗

arXiv2026

Learning Input-Constrained Funnel Controllers from State Trajectory Data

Designing feedback controllers that satisfy predefined performance specifications while enforcing hard input constraints is a challenging task. Our work is motivated by the idea that state trajectory data, e.g., obtained from an expert controller, often implicitly encode feasible performance attributes and input limitations. We propose an optimization-based framework that uses state trajectory data to jointly learn: (i) a performance funnel that mimics the transient and steady-state behavior encoded within the observed trajectories, and (ii) a feedback controller that enforces the learned performance specifications under hard input constraints. Unlike imitation learning methods, the proposed approach does not rely on control input data and does not reconstruct an expert policy. Instead, it synthesizes a prescribed performance controller by combining nominal model compensation with a learned state-dependent feedback gain. The resulting synthesis problem is nonconvex, for which we develop a feasibility-driven active-set synthesis procedure. Finally, we establish two complementary guarantees: a semi-global conservative actuator-authority-based certificate for prescribed performance and input satisfaction, and a local data-driven certificate ensuring these properties near sufficiently dense demonstrated trajectories.

eess.SY↗

arXiv2026

Conformal Predictive Programming for Chance Constrained Optimization

We propose conformal predictive programming (CPP), a framework to solve chance constrained optimization problems, i.e., optimization problems with constraints that are functions of random variables. CPP utilizes samples from these random variables along with the quantile lemma - central to conformal prediction - to transform the chance constrained optimization problem into a deterministic problem with a quantile reformulation. CPP's main strength is an independent calibration step that provides a posteriori guarantees for the solution of this problem that are of conditional and marginal nature otherwise. These guarantees even apply in settings when assumptions required for obtaining standard a priori guarantees (e.g., in scenario optimization or sample average approximation) are unavailable, difficult to compute, or conservative. Another strength of CPP is that it can easily support different variants of conformal prediction which have been (or will be) proposed within the conformal prediction community. To illustrate this, we present robust CPP to deal with distribution shifts in the random variables and Mondrian CPP to deal with class conditional chance constraints. In a series of case studies, we show the validity of the aforementioned approaches, and illustrate the advantage of CPP as compared to scenario approach.

eess.SY↗

arXiv2026

An Algebraic Framework for Quantitative Semantics of Spatio-Temporal Logic with Graph Operators

Spatio-Temporal Logic with Graph Operators (STL-GO) extends Signal Temporal Logic (STL) to multi-agent systems via graph operators that count neighboring agents satisfying a property, together with multi-agent quantifiers. While Boolean semantics for STL-GO are well-defined, quantitative semantics have not yet been developed and existing quantitative semantics for spatio-temporal logics such as STREL cannot capture the counting constraints in STL-GO's graph operators. We develop quantitative semantics for STL-GO as a layered algebraic construction that separates temporal aggregation from graph-operator aggregation (governed by an abstract accumulator with a monotone fold and readout). We prove that soundness and completeness reduce to monotonicity conditions on these components. We implement the framework and evaluate it on two multi-agent environments: a 2D bounded region with stochastic Dubins-car dynamics and a 3D Earth-satellite system, under four semantic instantiations (Boolean, min-max, signed-deficit, and a hybrid), demonstrating the tradeoffs between accumulator choices and reporting scalability in the number of agents and time horizon.

cs.LO↗

arXiv2026

Robust Conformal CBF and CLF Controllers via Iterative Policy Updates

Conformal prediction (CP) has been used to obtain probabilistic bounds on the error between a learned dynamics model and the true but unknown system. Such CP bounds can then be embedded into robust control Lyapunov function (CLF) and control barrier function (CBF) frameworks. However, such an approach does not retain stability/safety guarantees because of the distribution shift between the closed-loop trajectory distribution under the deployed CLF/CBF policy and the trajectory distribution from which the CP bound and its guarantees were derived. To address this issue, we propose an episodic framework that iteratively updates the robust conformal CLF/CBF policy while maintaining stability/safety guarantees across episodes. We achieve this by (1) using adversarially robust conformal prediction, and (2) quantifying a distribution shift budget that allows us to control how much the model error can increase across policy updates. This distribution shift budget is derived via a closed-loop trajectory sensitivity analysis, yielding an implicit and an explicit update rule for the CP bound. We analyze convergence of our algorithm, which we demonstrate on three case studies. To the best of our knowledge, these are the first results that provide stability/safety guarantees for robust conformal CBF/CLF policies.

eess.SY↗

arXiv2026

Metriplectic Conditional Flow Matching for Dissipative Dynamics

Metriplectic conditional flow matching (MCFM) learns dissipative dynamics without violating first principles. Neural surrogates often inject energy and destabilize long-horizon rollouts; MCFM instead builds the conservative-dissipative split into both the vector field and a structure preserving sampler. MCFM trains via conditional flow matching on short transitions, avoiding long rollout adjoints. In inference, a Strang-prox scheme alternates a symplectic update with a proximal metric step, ensuring discrete energy decay; an optional projection enforces strict decay when a trusted energy is available. We provide continuous and discrete time guarantees linking this parameterization and sampler to conservation, monotonic dissipation, and stable rollouts. On a controlled mechanical benchmark, MCFM yields phase portraits closer to ground truth and markedly fewer energy-increase and positive energy rate events than an equally expressive unconstrained neural flow, while matching terminal distributional fit.

cs.LG↗

arXiv2026

A Reactive Redistribution Mechanism for STL Tasks in Multi-Agent Systems Under Time-Varying Communication

We present a communication-aware task decomposition framework for multi-agent systems with collaborative relative configuration objectives specified in Signal Temporal Logic (STL), allowing for dynamic task reallocation under time-varying communication networks. Building on our prior work, the framework supports the direct use of existing feedback controllers for reactive task satisfaction. We address two key challenges: disjunctive STL specifications and time-varying communication networks. Disjunctive specifications are handled through a graph transition system that captures the alternative task sequences induced by logical OR operators. To address time-varying connectivity, we introduce a redistribution mechanism that transfers tasks from disconnected agents to connected ones as the network evolves while preserving decentralized execution. Simulations and experiments on a swarm of Crazyflie drones demonstrate scalability in the number of agents, communication connectivity, and specification complexity.

eess.SY↗

arXiv2026

Multi-Agent Temporal Logic Planning via Penalty Functions and Block-Coordinate Optimization

Multi-agent planning under Signal Temporal Logic (STL) is often hindered by collaborative tasks that lead to computational challenges due to the inherent high dimensionality of the problem, preventing scalable synthesis with satisfaction guarantees. To address this, we formulate STL planning as an optimization program under multi-agent STL constraints and introduce a penalty-based unconstrained relaxation that can be efficiently solved via a Block-Coordinate Gradient Descent (BCGD) method, where each block corresponds to a single agent's decision variables, thereby mitigating complexity. By utilizing a quadratic penalty function defined via smooth STL semantics, we show that BCGD iterations converge to a stationary point of the penalized problem under standard regularity assumptions. To enforce feasibility, the BCGD solver is embedded within a two-layer optimization scheme: inner BCGD updates are performed for a fixed penalty parameter, which is then increased in an outer loop to progressively improve multi-agent STL robustness. The proposed framework enables scalable computations and is validated through various complex multi-robot planning scenarios.

eess.SY↗

arXiv2026

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation

Reinforcement learning has enabled significant progress in complex domains such as coordinating and navigating multiple quadrotors. However, even well-trained policies remain vulnerable to collisions in obstacle-rich environments. Addressing these infrequent but critical safety failures through retraining or fine-tuning is costly and risks degrading previously learned skills. Inspired by activation steering in large language models and latent editing in computer vision, we introduce a framework for inference-time Latent Activation Editing (LAE) that refines the behavior of pre-trained policies without modifying their weights or architecture. The framework operates in two stages: (i) an online classifier monitors intermediate activations to detect states associated with undesired behaviors, and (ii) an activation editing module that selectively modifies flagged activations to shift the policy towards safer regimes. In this work, we focus on improving safety in multi-quadrotor navigation. We hypothesize that amplifying a policy's internal perception of risk can induce safer behaviors. We instantiate this idea through a latent collision world model trained to predict future pre-collision activations, thereby prompting earlier and more cautious avoidance responses. Extensive simulations and real-world Crazyflie experiments demonstrate that LAE achieves statistically significant reduction in collisions (nearly 90% fewer cumulative collisions compared to the unedited baseline) and substantially increases the fraction of collision-free trajectories, while preserving task completion. More broadly, our results establish LAE as a lightweight paradigm, feasible on resource-constrained hardware, for post-deployment refinement of learned robot policies.

cs.RO↗

arXiv2026

Spatiotemporal Robustness of Temporal Logic Tasks using Multi-Objective Reasoning

The reliability of autonomous systems depends on their robustness, i.e., their ability to meet their objectives under uncertainty. In this paper, we study spatiotemporal robustness of temporal logic specifications evaluated over discrete-time signals. Existing work has proposed robust semantics that capture not only Boolean satisfiability, but also the geometric distance from unsatisfiability, corresponding to admissible spatial perturbations of a given signal. In contrast, we propose spatiotemporal robustness (STR), which captures admissible spatial and temporal perturbations jointly. This notion is particularly informative for interacting systems, such as multi-agent robotics, smart cities, and air traffic control. We define STR as a multi-objective reasoning problem, formalized via a partial order over spatial and temporal perturbations. This perspective has two key advantages: (1) STR can be interpreted as a Pareto-optimal set that characterizes all admissible spatiotemporal perturbations, and (2) STR can be computed using tools from multi-objective optimization. To navigate computational challenges, we propose robust semantics for STR that are sound in the sense of suitably under-approximating STR while being computationally tractable. Finally, we present monitoring algorithms for STR using these robust semantics. To the best of our knowledge, this is the first work to deal with robustness across multiple dimensions via multi-objective reasoning.

cs.AI↗