Searcharxiv⌕ Search

arXiv subjects

Mykel J. Kochenderfer

Publications and source records attributed to Mykel J. Kochenderfer.

At least 19 recordsLinked to original sources

Conformal Uncertainty Quantification of a Normalizing Flow Surrogate for the FACET-II Two-Bunch Beam

Fast surrogate models of the beam can be used for tuning, diagnostics, and control where end-to-end simulation is too slow. At FACET-II, a normalizing flow surrogate predicts the 6D high peak current two-bunch beam used for plasma wakefield acceleration (PWFA) in less than a second, from 37 injector and linac machine parameters (such as the RF phases controlling the bunch compression). However, a surrogate can predict an incorrect beam that seems plausible, so operators and controllers need to know when to trust its predictions. We use conformal prediction to generate a prediction-specific uncertainty with guaranteed coverage. That is, if we sample new machine parameters from the same distribution as our calibration data, the uncertainty will cover the simulation output at least 90% of the time. We provide two implementations: prediction intervals for beam parameters with fixed and adaptive widths, and a region in the full 6D phase space covering 95% of the electrons, 90% of the time. The median size of this region is 5 (drive) and 2 (witness) times smaller than a Gaussian ellipsoid with the same coverage. Across 1,000 independent test simulations, our prediction intervals identify failure cases for the surrogate, specifically the slice peak current of highly compressed bunches.

physics.acc-ph↗

Large Language Model Explainability for Planning Lunar Rover Trajectories under Uncertainty

Planning planetary rover trajectories under probabilistic uncertainty is a multi-objective optimization problem that science teams currently iteratively solve and verify by hand. This process becomes impractical when timelines and constraints frequently shift throughout the mission planning phase. Sampling-based planners such as Monte Carlo tree search can speed up this process, but their outputs do not preserve traceability to the science objectives that justify each plan, which the science team needs to verify. We propose an interactive assistant based on a large language model (LLM) that can explain planner trajectories using domain vocabulary and re-run the planner under user-specified conditions to compare alternatives. Previous work has used LLMs inside planner decision-making loops, but we explore using them for post-planning explanation, where they are more likely to be trusted since they do not directly influence planner decisions. Our framework pairs a simulator inspired by the NASA Volatiles Investigating Polar Exploration Rover (VIPER) mission with a ReAct queryable interface that calls curated action tools and retrieval functions. We evaluate the assistant on a query bank consisting of plan comparisons, feasibility, and lookup queries. Experiments show that 90.9% of the assistant's responses are faithful to the planner's outputs, a nearly 65% improvement over zero-shot prompting of the same LLM without tool access, demonstrating the potential for trustworthy explainability of uncertainty-aware traverses with an LLM-based system.

cs.RO↗

Imperfect World Models are Exploitable

We propose a novel definition of model exploitation in reinforcement learning. Informally, a world model is exploitable if it implies that one policy should be strictly preferred over another while the environment's true transition model implies the reverse. We analogize our definition with a prior characterization of reward hacking but show that the associated proof of inevitability does not transfer to exploitation. To overcome this obstruction, we develop a general theory of reward hacking and model exploitation that proves that exploitation is essentially unavoidable on large policy sets and yields the corresponding claim for hacking as a special case. Unfortunately, we also find that the conditions that guarantee unhackability in finite policy sets have no counterpart that precludes exploitation. Consequently, we introduce a relaxed notion of exploitation and derive a safe horizon within which it can be avoided. Taken together, our results establish a formal bridge between reward hacking and model exploitation and elucidate the limits of safe planning in world models.

cs.AI↗

Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure

Single-axis mitigations of reward-model biases, such as reducing proxy reliance on length, sycophancy, or style, can redirect optimization pressure onto correlated proxies rather than eliminate it, a new type of reward hacking we call reward bias substitution. The failure is enabled by a measurement-versus-optimization gap between mitigation evaluation on the audit distribution and policy training on the policy-induced distribution. Prior reward-hacking analyses assume a fixed reward proxy, whereas we study the mitigation operator that removes one bias from it, the basic step of iterative reward refinement. We formalize mitigation outcomes into a regime taxonomy and prove that successful mitigation, bias substitution, and overcorrection can produce identical observables under every audit-distribution score, including ranking accuracy and win-rate, even when granted oracle access to the true reward. Across 30 published preference-learning mitigation works, no method we survey reports the evidence needed to certify successful mitigation. Augmenting evaluation with policy-induced distributions while tracking multiple biases provably resolves this distributional gap, and we translate this into actionable prescriptions for mitigation methods and benchmarks. We demonstrate bias substitution in RLHF, where a length penalty in GRPO shortens responses as intended yet makes the policy overconfident and less accurate on open-ended questions, show that the same distributional gap hides failures of published mitigations, and find the necessary preconditions for reward bias substitution documented in published results and in our study of length-sycophancy coupling in LLM responses.

cs.AI↗

Where Planning Changes the Outcome of Orbital Games

This paper introduces OrbitalGym, a simulation environment for studying when planning algorithms or system design determine the outcome of adversarial orbital encounters. In an orbital game, two non-cooperative teams of satellites maneuver during rendezvous and proximity operations to win a differential-reward objective. Advances in terrestrial game playing have prompted many methods for orbital games, but studies typically evaluate one method in one scenario, often against a passive or random defender. It is unclear whether better planning matters once vehicle capability (maneuverability, sensing, communications) and adversarial responses are considered. OrbitalGym is a JAX-based environment supporting varying numbers of agents, state representations (position, velocity, attitude, fuel), explicit or implicit communication, and proximity or conical field-of-view sensors. It compiles games to batched GPU code, enabling large-scale parallel simulation of policies across many configurations. This identifies regimes where policy choice affects outcomes and regimes where system capability dominates. We study two close-range games: pursuit-evasion, where one spacecraft tries to capture another, and lady-bandit-guard, where a guard prevents an attacker from reaching a protected asset. We compare PD, LQR, model predictive path integral control, and Monte Carlo tree search over ratios of thrust and propellant, initial separation, game duration, sensor capability, and the definition of capture. In pursuit-evasion the propellant ratio decides most encounters: against five of six evader policies, pursuer policy changes capture probability by 10 percent or more in at most 15 of 90 capability configurations. In lady-bandit-guard, policy matters more: against bandits able to reach the asset, a better guard policy raises defense probability by at least 10 percent in 56 to 74 of 90 configurations.

cs.MA↗

Scalable LEO Conjunction Screening using Adaptive Synthetic-Covariance Thresholds

As orbital populations grow, conjunction screening must search more object pairs for potential collision risks. Existing pipelines use early-stage filters, such as an apsis filter, to eliminate pairs whose orbital altitude ranges cannot produce a close approach. However, these filters apply the same fixed threshold to every object, making the screening unnecessarily conservative for well-constrained objects while potentially insufficient for objects with greater orbit-prediction uncertainty. In this work, we present an uncertainty-aware conjunction screening method that replaces a single fixed apsis threshold with object-specific thresholds derived from propagated radial uncertainty. The resulting thresholds vary across both objects and prediction time, becoming narrower when propagated uncertainty is small and wider when uncertainty grows. We pair this adaptive screening rule with a binary-search altitude sweep that makes resulting heterogeneous intervals efficient to evaluate at catalog scale with log-linear search complexity. We evaluate the method on 33,791 objects from the Space-Track General Perturbations (GP) catalog using the preceding eight public ephemeris snapshots and a seven-day prediction horizon. The adaptive sieve retains 162.8 million candidate pairs, reducing the candidate set by 28.78% relative to a fixed 50 km apsis threshold and by 71.48% relative to brute-force all-pairs screening. It retains all close approaches identified in two independently propagated reference sets. At the largest tested catalog size, the binary-search sweep is 27 times faster than exhaustive interval evaluation while returning the same candidate set. These results demonstrate that uncertainty-aware screening can substantially reduce the candidate burden passed to downstream conjunction analysis, providing a scalable path toward managing increasingly large and heterogeneous orbital populations.

cs.RO↗

Optimal Search for Finding Satellites Post-Launch

This paper introduces Bayesian Continuation Model Predictive Control (BC-MPC), an adaptive method that replans near-term antenna pointings while continuing a feasible baseline sweep, for finding and establishing contact with spacecraft immediately after launch when their true positions are most uncertain. After separation, launch and deployment errors can leave the spacecraft sufficiently far from its predicted position that operators must actively search for it during ground contacts to establish communications. Each missed detection provides information about which orbital hypotheses remain plausible, but searching one part of the uncertainty region can consume the time needed to reach another. BC-MPC updates a particle-based orbital belief after missed detections and replans antenna pointing guidance while retaining feasibility. Its continuation helps preserve future search coverage that greedy and short-horizon methods can sacrifice for immediate acquisition gains. We compare BC-MPC against the operationally prevalent along-track sweep and additional search algorithms under common search-time budgets, initial uncertainty, and antenna constraints. Across 96 simulated deployments with matched uncertainty, BC-MPC improves acquisition probability over the along-track sweep and reduces restricted mean acquisition time. We additionally evaluate the method using pre-launch, post-launch, and initial acquisition ephemerides for 83 spacecraft from the Transporter-16 rideshare launch. Using either pre-deployment or post-deployment two-line element sets (TLEs) for planning, BC-MPC improves modeled acquisition probability over the along-track sweep by approximately 12 percentage points under the commonly assumed uncertainty model.

eess.SY↗

Scaling Zero-Order Pretraining through Model Sharding

Zero-order optimization (ZO) trains without backpropagation, making it relevant to forward-only hardware and non-differentiable loss, but its gradient variance grows with perturbed dimension, inhibiting large-model training. Sharded Optimization Mixture of Assemblies (SOMA) trains LSTM experts independently on $N$ data clusters using simultaneous perturbation stochastic approximation (SPSA), without exchanging gradients, activations or optimizer state. Its separable loss removes cross-expert perturbation noise at the cost of jointly learned representations across domains. Using 80,000 estimated RTX 5090 GPU-hours, we show modest sharding improves training compute efficiency over all tested monolithic ZO controls. At 8.44M parameters and 150 aggregate GPU-hours, SOMA $N=2$ with 64 perturbations reaches 1.76 test nats/byte, versus 2.00--2.11 for monolithic SPSA at 64, 256 or 1,024 perturbations and 2.21 for EGGROLL. On WikiText-103, these frozen checkpoints reach 2.07, 2.25--2.36 and 2.49, respectively. On a fixed separable objective with equal-size blocks, we prove independent losses reduce relative gradient variance to approximately $1/N$ of a shared-loss estimator's. Holding starting weights, data, perturbations and compute fixed, independent rather than summed losses lower SOMA $N=4$ test loss by 0.035 nats/byte after 1,000 updates across three seeds. Larger ensembles offer a separate inference benefit: at similar model size with top-$k$ routing ($k=4$), SOMA $N=256$ achieves 2.36M tokens/s versus 257k for SOMA $N=8$ ($9.19\times$, including routing), at lower test loss (1.68 versus 1.71), albeit using $59.9\times$ as much aggregate training compute. We release all training and evaluation code and checkpoints.

cs.LG↗

Probe-Space Preconditioning for Fast and Stable Zero-Order Training

Backpropagation (BP) dominates deep learning but imposes a massive memory tax. For example, training OPT-30B with Adam requires $\approx$ 600GB of GPU memory (assuming batch size 8 and sequence length 2048). Alternatively, zero-order optimization (ZOO) trains in inference-mode (requiring only $\approx$ 60GB for the same model): no stored activations, no gradients, and no optimizer states. However, ZOO convergence has lagged behind BP. In this work, we evaluate two methods to close this gap. First, we show that reallocating training compute budget from many steps to large effective batch sizes with many perturbations (or probes) but fewer steps, allows 1SPSA (Spall, 1992) to outperform zero order methods like MeZO (Malladi et al., 2023) with less training compute. Next, we introduce 1.5-SPSA, adding a single "clean" forward-pass per step to 1SPSA to calculate a cheap diagonal preconditioner in probe-space, which improves convergence rate and convergence by down-weighting high curvature directions. Benchmarking on 6 post-training datasets on both Qwen3 and OPT model families, we show that 1.5-SPSA achieves State-of-the-Art results over previous ZOO solvers with much less optimization steps. For example, we train OPT-13B (for direct comparison to MeZO) and find 1.5-SPSA achieves +3.1% accuracy on SST-2 over both MeZO and BP in only 70 steps vs. MeZO's 100,000 steps. Finally, we combine an 8-bit-packing random generator, triton fused unpack/apply kernels, and distributed parallelism to achieve fast and stable training of models as large as OPT-30B in-place on commodity GPUs (e.g. A100).

cs.LG↗

Stochastic World Models for Verifying Vision-Based Neural Feedback Systems

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.

cs.AI↗

Risk-Averse Lander Site Selection under Altitude-Limited Information

In aerospace systems, powered descent requires efficiently selecting a landing site while fine-scale hazards remain unresolvable until low altitude. This process presents a decision challenge since the actor must select a site and make corresponding actions before all information is known. To successfully solve this problem, an agent must reason over potential risks and make corrections as new observations are made. We introduce a lightweight model of altitude-limited information where each landing site is summarized by a mean score and a designed ambiguity proxy that contracts as the vehicle descends and senses within a cone-shaped footprint under an altitude-to-resolution schedule. Using this abstraction, we derive closed-form, risk-averse site scoring techniques (an entropic certainty-equivalent and a Gaussian Conditional Value at Risk surrogate) and pair them with greedy and exploratory planners to prioritize sites that are both high-value and robust to late-revealed terrain detail. These rollout-free heuristics improve lower-tail landing outcomes (1st percentile and certainty-equivalent) relative to mean-based baselines, with the largest gains when refinement occurs late and unresolved detail is large. We also demonstrate that these methods perform comparably to or better than Monte Carlo Tree Search baselines with orders-of-magnitude faster computation. Our results are supported by numerical simulations.

eess.SY↗

Self-Organizing Agent Teams Learn to Reason Together

Collective intelligence depends not only on what team members know, but also on how they organize their work. When the structure of a solution is unknown, useful roles and divisions of labor cannot be specified in advance; teams must learn from experience how to organize reasoning as it unfolds. Human teams routinely adapt this way, while existing AI agent teams rely on fixed protocols, explicit task decomposition, or routing. We introduce Self-Organizing Agent Teams (SAT), fixed teams of AI agents that learn reusable strategies from prior collaborations to organize roles, conversational phases, participation, and information flow. These strategies enable what we call collaborative computation: agents exchange, challenge, repair, and synthesize partial reasoning into solutions no member produced independently. In two independent settings, we learn teamwork strategies that transfer unchanged to unseen benchmarks, using only 15 mathematics and 25 graduate-level knowledge problems. Across five mathematics and physics benchmarks, self-organizing teams average 66.7% accuracy, versus 48.8% for their strongest member, 58.7% for compute-matched inference by that agent, and 59.0% for a perfect router over members' independent answers; on AIME 2026, they exceed this router by 13.4 points. Because gains vary across benchmarks, we ask when self-organizing collaboration helps. Across eight benchmarks, demonstrability (the organizational-psychology construct of whether a team can distinguish correct from incorrect reasoning) strongly tracks improvement over the strongest member (Spearman $ρ=0.90$, $p=0.005$): teams benefit most when correct reasoning can be recognized once it appears. More broadly, these results suggest that organization itself can become an agent capability: agent teams can learn how to reason together and produce solutions their members could not reach independently.

cs.AI↗

Closing the Loop: Branch-and-Bound for Scalable Verification of Nonlinear Neural Feedback Systems

Despite recent advances in the verification of nonlinear neural feedback systems, scalability remains the central obstacle, as state-of-the-art solvers do not yet handle the network sizes and nonlinear dynamics of autonomy applications. Combinatorial solvers do not scale to large networks, whereas propagative solvers excessively sacrifice precision. This work seeks to improve the scalability of combinatorial solvers by formulating verification as branch-and-bound on an abstraction of the closed-loop system. We introduce \rail, an interface that exposes polyhedral enclosures of the dynamics to LiRPA-style bound propagation, and \clipper, a branch-and-bound algorithm that jointly refines enclosures and splits controller activations. This framework enables joint reasoning on the computational graph of the closed-loop system, preserving symbolic correlations across time steps. We present our construction and show that it yields significant improvements over the state of the art.

cs.AI↗

Chance-Constrained Belief-Space Maneuver Planning for Autonomous Collision Avoidance Under Uncertainty

Increasing conjunction frequency in low Earth orbit places growing pressure on spacecraft operators to determine not only whether an encounter requires mitigation, but whether sufficient information is available to commit to a maneuver. This work formulates this information-action tradeoff as a belief-space planning problem for conjunctions between a maneuverable spacecraft and an unmaneuverable secondary object. The planner represents the uncertain orbital states as Gaussian beliefs and uses a chance-constrained belief-space Monte Carlo tree search framework to reason over possible future tracking updates before time of closest approach (TCA). A terminal chance constraint limits the probability of reaching TCA above a prescribed collision-risk threshold, allowing the planner to wait for informative tracking while intervening when deferral becomes too risky. We evaluate the approach on eight historical conjunctions from NASA's Conjunction Assessment Risk Analysis dataset. By varying the secondary-object measurement quality and tracking cadence, we generate a total of 96 distinct evaluation scenarios. Across the evaluated conditions, the planner reaches TCA without maneuvering in approximately 40% of episodes while maintaining no terminal collision-risk violations. In contrast, fixed-time rule-based maneuver policies resolve more encounters without maneuvering when intervention is deferred closer to TCA, but at the expense of increasing terminal risk violations. The fraction of episodes reaching TCA without maneuvering depends strongly on tracking quality and measurement cadence, ranging from 76% under accurate, frequent measurements to approximately 18%-20% under the poorest tracking conditions. These results show that tracking quality and frequency are not only inputs to collision-risk estimation: they can determine when intervention becomes necessary.

cs.RO↗

GPU-Accelerated Astrodynamics World Models for Spacecraft Rendezvous and Proximity Operations

World models are an emerging paradigm in representation learning in which an agent jointly learns state-action dynamics and observation models from offline trajectory data, enabling multi-step planning and trajectory prediction with uncertainty estimates. They have shown strong results in robotics and game environments, but, to the best of our knowledge, have not previously been applied to the space domain. This paper introduces a world model-based approach to cooperative and non-cooperative spacecraft rendezvous and proximity operations. First, we introduce an open-source, JAX-based International Space Station (ISS) docking environment supporting parallel GPU simulation of spacecraft orbit and attitude dynamics, generating the thousands of state-action transitions that world model training requires. Second, we introduce Out-of-this-World-Model, a transformer-based world model that encodes relative kinematic states and body-fixed camera imagery into a latent state and predicts its evolution under commanded thrusts and torques using one-step flow matching. It produces a distribution over future observations, capturing stochastic dynamics and per-timestep uncertainty, and outperforms DreamerV3-style posterior-correction baselines with fewer trainable parameters and hyperparameters. Third, we apply the approach to a capsule autonomously docking with the ISS under keep-out-zone constraints, demonstrating improved sample efficiency and task performance over reinforcement learning baselines (53% versus 29% docking success across ports), better out-of-distribution generalization (on held-out ports the world model more than doubles baseline success, 40% versus 17%), and detection of anomalous objects encountered during approach with 98% classification accuracy. We open-source the simulation environment and model architecture to enable further study of this paradigm.

cs.RO↗

Protection Levels for Vision-Based Pose Estimation

Vision-based navigation complements Global Navigation Satellite Systems, but certification demands integrity guarantees that account for faulty measurements. Previous work presented a probabilistic computer vision pipeline for runway-based pose estimation with fault detection inspired by Receiver Autonomous Integrity Monitoring. This work extends that framework by deriving protection levels, which provide probabilistic bounds on pose error that remain valid under undetected faults. We present an algorithm for computing protection levels for the nonlinear Perspective-$n$-Point problem applied to an aviation setting. The algorithm covers all six degrees of freedom of the aircraft pose (position and orientation) directly. We analyze the effect of measurement redundancy, pixel-level prediction uncertainty, and runway distance on the resulting protection levels. To make the results tangible, we demonstrate tradeoffs in the protection levels on an illustrative runway example.

cs.RO↗

Semi-Decentralized Multi-Spacecraft Collision Avoidance under Communication Constraints

Current spacecraft collision-avoidance operations rely on intermittent ground-station contacts, requiring operators to plan with delayed and asynchronously updated information. Consequently, maneuvers must be planned with only intermittent information sharing between operators, raising the question of how much coordination is needed to achieve collision-avoidance performance comparable to centralized planning. Although decision-theoretic approaches such as partially observable Markov decision processes (POMDPs) capture the sequential and uncertain nature of collision avoidance, existing multiagent extensions typically assume either continuous information sharing or communication models that do not reflect operational ground-station constraints. To explicitly model this intermittent information availability, we formulate the spacecraft-to-spacecraft collision avoidance problem as a semi-decentralized POMDP (SDec-POMDP), where we govern information propagation directly by realistic ground-station visibility windows. Joint maneuver policies are computed using approximate Recursive Small-Step Semi-Decentralized A* (RS-SDA*), following the state-of-the-art A*-based lineage for decentralized multiagent planning. Across a representative suite of conjunction scenarios, semi-decentralized planning recovers near-centralized maneuver quality while requiring 28.5% fewer synchronization events than continuous coordination. Comparisons with representative rule-based operator heuristics further show that communication-aware planning more consistently achieves the desired operational miss-distance band while minimizing unnecessary trajectory deviation. Together, these results establish a practical planning framework for autonomous collision avoidance under realistic intermittent communication, bridging the gap between idealized centralized coordination and fully decentralized planning execution.

cs.RO↗

Real-Time Flight Test Maneuver Selection with Monte Carlo Tree Search

Flight test is shifting toward a data-centric approach in which data contribute to model refinement, reducing reliance on pre-scripted test points. An open problem is how to sequence maneuvers within a sortie to maximize uncertainty reduction under resource limits. We present a real-time planning framework that combines a Gaussian Process (GP) belief model with Monte Carlo Tree Search (MCTS) to select pilot-actionable maneuvers under fuel constraints. Candidate maneuvers are scored using weighted integrated variance reduction (wIVR), and shallow lookahead is performed with a propagated per-evaluation-point variance state to account for downstream coverage redundancy and transition cost. The planner is evaluated in a closed, human-in-the-loop X-Plane simulation against greedy wIVR selection and a fixed test-card baseline. Sortie-summary statistics show significant directional differences, with MCTS-wIVR achieving higher uncertainty reduction per unit fuel over both baselines. The results indicate that posterior-aware adaptive planning is a promising approach to increase efficiency of flight tests.

eess.SY↗