Publications

Working Papers

1. [3] Physics-Informed Learning of Feedback-Linearizing Representations

   Pavlos Kallinikidis, Fengjun Yang, David Snyder, and 4 more authors

   In 2026 IEEE 65th Conference on Decision and Control (CDC) Dec 2026

   Abs

   Feedback linearization is a powerful tool in nonlinear control, but finding the linearizing coordinate transformation remains challenging. Feedback linearizing transformations are governed by well-established partial differential equations (PDEs) whose well-posedness is based on the Lie-algebraic Frobenius theorem. Even if the conditions of the Frobenius theorem are satisfied, solving the PDEs becomes computationally intractable for large system dimensions. To address this challenge, we propose a cascaded physics-informed neural network (PINN) framework to approximately solve these PDEs. By separately parameterizing terms of different Lie derivative orders, we mitigate the compounding errors inherent in taking high-order Lie derivatives of neural networks. Furthermore, we use the learned transformation to design a tracking controller and establish theoretical bounds on its error with respect to inaccuracies in the learned feedbacklinearizing representation. We validate our method on a broad class of feedback linearizable systems, including a multi-input, multi-output planar quadrotor and synthetic examples for which analytical approaches are impractical, and demonstrate that our approach can computationally discover effective feedback-linearizing representations of nonlinear systems for control tasks.

2. [2] Contextual Safety Reasoning and Grounding for Open-World Robots

   Zachary Ravichandran, David Snyder, Alexander Robey, and 3 more authors

   Feb 2026

   Abs

   Robots are increasingly operating in open-world environments where safe behavior depends on context: the same hallway may require different navigation strategies when crowded versus empty, or during an emergency versus normal operations. Traditional safety approaches enforce fixed constraints in user-specified contexts, limiting their ability to handle the open-ended contextual variability of real-world deployment. We address this gap via CORE, a safety framework that enables online contextual reasoning, grounding, and enforcement without prior knowledge of the environment (e.g., maps or safety specifications). CORE uses a vision-language model (VLM) to continuously reason about context-dependent safety rules directly from visual observations, grounds these rules in the physical environment, and enforces the resulting spatially-defined safe sets via control barrier functions. We provide probabilistic safety guarantees for CORE that account for perceptual uncertainty, and we demonstrate through simulation and real-world experiments that CORE enforces contextually appropriate behavior in unseen environments, significantly outperforming prior semantic safety methods that lack online contextual reasoning. Ablation studies validate our theoretical guarantees and underscore the importance of both VLM-based reasoning and spatial grounding for enforcing contextual safety in novel settings. We provide additional resources at https://zacravichandran.github.io/CORE.

3. 

   [1] Guiding Data Collection via Factored Scaling Curves

   Lihan Zha, Apurva Badithela, Michael Zhang, and 7 more authors

   May 2025

   Abs arXiv Bib Website

   Generalist imitation learning policies trained on large datasets show great promise for solving diverse manipulation tasks. However, to ensure generalization to different conditions, policies need to be trained with data collected across a large set of environmental factor variations (e.g., camera pose, table height, distractors) \- a prohibitively expensive undertaking, if done exhaustively. We introduce a principled method for deciding what data to collect and how much to collect for each factor by constructing factored scaling curves (FSC), which quantify how policy performance varies as data scales along individual or paired factors. These curves enable targeted data acquisition for the most influential factor combinations within a given budget. We evaluate the proposed method through extensive simulated and real-world experiments, across both training-from-scratch and fine-tuning settings, and show that it boosts success rates in real-world tasks in new environments by up to 26% over existing data-collection strategies. We further demonstrate how factored scaling curves can effectively guide data collection using an offline metric, without requiring real-world evaluation at scale.

   @misc{zha_guiding_2025,
     title = {Guiding {Data} {Collection} via {Factored} {Scaling} {Curves}},
     author = {Zha, Lihan and Badithela, Apurva and Zhang, Michael and Lidard, Justin and Bao, Jeremy and Zhou, Emily and Snyder, David and Ren, Allen Z. and Shah, Dhruv and Majumdar, Anirudha},
     publisher = {arXiv},
     month = may,
     year = {2025},
     keywords = {Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Computer Science - Robotics},
     doi = {10.48550/arXiv.2505.07728},
   }

Refereed Conference Papers

1. [10] Beyond Binary Success: Sample-Efficient and Statistically Rigorous Robot Policy Comparison

   David Snyder, Apurva Badithela, Nikolai Matni, and 4 more authors

   Mar 2026

   Abs

   Generalist robot manipulation policies are becoming increasingly capable, but are limited in evaluation to a small number of hardware rollouts. This strong resource constraint in real-world testing necessitates both more informative performance measures and reliable and efficient evaluation procedures to properly assess model capabilities and benchmark progress in the field. This work presents a novel framework for robot policy comparison that is sample-efficient, statistically rigorous, and applicable to a broad set of evaluation metrics used in practice. Based on safe, anytime-valid inference (SAVI), our test procedure is sequential, allowing the evaluator to stop early when sufficient statistical evidence has accumulated to reach a decision at a pre-specified level of confidence. Unlike previous work developed for binary success, our unified approach addresses a wide range of informative metrics: from discrete partial credit task progress to continuous measures of episodic reward or trajectory smoothness, spanning both parametric and nonparametric comparison problems. Through extensive validation on simulated and real-world evaluation data, we demonstrate up to 70% reduction in evaluation burden compared to standard batch methods and up to 50% reduction compared to state-of-the-art sequential procedures designed for binary outcomes, with no loss of statistical rigor. Notably, our empirical results show that competing policies can be separated more quickly when using fine-grained task progress than binary success metrics.

2. 

   [9] Reliable and Scalable Robot Policy Evaluation with Imperfect Simulators

   Apurva Badithela, David Snyder, Lihan Zha, and 4 more authors

   Oct 2025

   Abs Bib Website

   Rapid progress in imitation learning, foundation models, and large-scale datasets has led to robot manipulation policies that generalize to a wide-range of tasks and environments. However, rigorous evaluation of these policies remains a challenge. Typically in practice, robot policies are often evaluated on a small number of hardware trials without any statistical assurances. We present SureSim, a framework to augment large-scale simulation with relatively small-scale real-world testing to provide reliable inferences on the real-world performance of a policy. Our key idea is to formalize the problem of combining real and simulation evaluations as a prediction-powered inference problem, in which a small number of paired real and simulation evaluations are used to rectify bias in large-scale simulation. We then leverage non-asymptotic mean estimation algorithms to provide confidence intervals on mean policy performance. Using physics-based simulation, we evaluate both diffusion policy and multi-task fine-tuned }(π_0}) on a joint distribution of objects and initial conditions, and find that our approach saves over }(20-25}%}) of hardware evaluation effort to achieve similar bounds on policy performance.

   @misc{badithela_reliable_2025,
     title = {Reliable and {Scalable} {Robot} {Policy} {Evaluation} with {Imperfect} {Simulators}},
     author = {Badithela, Apurva and Snyder, David and Zha, Lihan and Mikhail, Joseph and O'Kelly, Matthew and Dixit, Anushri and Majumdar, Anirudha},
     publisher = {arXiv},
     month = oct,
     year = {2025},
     note = {arXiv:2510.04354 [cs]},
     keywords = {Computer Science - Artificial Intelligence, Computer Science - Robotics, Electrical Engineering and Systems Science - Systems and Control},
     doi = {10.48550/arXiv.2510.04354},
   }

3. 

   [8] Is Your Imitation Learning Policy Better than Mine? Policy Comparison with Near-Optimal Stopping

   David Snyder, Asher James Hancock, Apurva Badithela, and 6 more authors

   In Proceedings of the Robotics: Science and Systems XVIII Conference (RSS 2022) Jun 2025

   Abs arXiv Bib Website

   Imitation learning has enabled robots to perform complex, long-horizon tasks in challenging dexterous manipulation settings. As new methods are developed, they must be rigorously evaluated and compared against corresponding baselines through repeated evaluation trials. However, policy comparison is fundamentally constrained by a small feasible sample size (e.g., 10 or 50) due to significant human effort and limited inference throughput of policies. This paper proposes a novel statistical framework for rigorously comparing two policies in the small sample size regime. Prior work in statistical policy comparison relies on batch testing, which requires a fixed, pre-determined number of trials and lacks flexibility in adapting the sample size to the observed evaluation data. Furthermore, extending the test with additional trials risks inducing inadvertent p-hacking, undermining statistical assurances. In contrast, our proposed statistical test is sequential, allowing researchers to decide whether or not to run more trials based on intermediate results. This adaptively tailors the number of trials to the difficulty of the underlying comparison, saving significant time and effort without sacrificing probabilistic correctness. Extensive numerical simulation and real-world robot manipulation experiments show that our test achieves near-optimal stopping, letting researchers stop evaluation and make a decision in a near-minimal number of trials. Specifically, it reduces the number of evaluation trials by up to 32% as compared to state-of-the-art baselines, while preserving the probabilistic correctness and statistical power of the comparison. Moreover, our method is strongest in the most challenging comparison instances (requiring the most evaluation trials); in a multi-task comparison scenario, we save the evaluator more than 160 simulation rollouts.

   @inproceedings{snyder_policy_comparison_2025,
     title = {Is Your {Imitation} {Learning} {Policy} Better than Mine? {Policy} {Comparison} with {Near}-{Optimal} {Stopping}},
     author = {Snyder, David and Hancock, Asher James and Badithela, Apurva and Dixon, Emma and Miller, Patrick and Ambrus, Rares Andrei and Majumdar, Anirudha and Itkina, Masha and Nishimura, Haruki},
     booktitle = {Proceedings of the {Robotics}: {Science} and {Systems} XVIII {Conference} ({RSS} 2022)},
     volume = {21},
     shorttitle = {{Policy} {Comparison} with {Near}-{Optimal} {Stopping}},
     month = jun,
     year = {2025},
     isbn = {979-8-9902848-1-4},
   }

4. 

   [7] Privacy-Preserving Map-Free Exploration for Confirming the Absence of a Radioactive Source

   Eric Lepowsky^*, David Snyder^*, Alexander Glaser, and 1 more author

   In 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024) Oct 2024

   Abs arXiv Bib Website

   Performing an inspection task while maintaining the privacy of the inspected site is a challenging balancing act. In this work, we are motivated by the future of nuclear arms control verification, which requires both a high level of privacy and guaranteed correctness. For scenarios with limitations on sensors and stored information due to the potentially secret nature of observable features, we propose a robotic verification procedure that provides map-free exploration to perform a source verification task without requiring, nor revealing, any task-irrelevant, site-specific information. We provide theoretical guarantees on the privacy and correctness of our approach, validated by extensive simulated and hardware experiments.

   @inproceedings{lepowsky_snyder_privacy-preserving_2024,
     title = {{Privacy}-{Preserving} {Map}-{Free} {Exploration} for {Confirming} the {Absence} of a {Radioactive} {Source}},
     author = {Lepowsky<sup>*</sup>, Eric and Snyder<sup>*</sup></u>, <u>David and Glaser, Alexander and Majumdar, Anirudha},
     booktitle = {2024 {IEEE}/{RSJ} {International} {Conference} on {Intelligent} {Robots} and {Systems} ({IROS} 2024)},
     url = {https://ieeexplore.ieee.org/document/10802428},
     month = oct,
     year = {2024},
     publisher = {IEEE},
     pages = {10073--10080},
     issn = {2153-0866},
     doi = {10.1109/IROS58592.2024.10802428},
   }

5. 

   [6] Online Learning for Obstacle Avoidance

   David Snyder, Meghan Booker, Nathaniel Simon, and 4 more authors

   In Proceedings of The 7th Conference on Robot Learning (CoRL 2023) Dec 2023

   Abs arXiv Bib Website

   We approach the fundamental problem of obstacle avoidance for robotic systems via the lens of online learning. In contrast to prior work that either assumes worst-case realizations of uncertainty in the environment or a stationary stochastic model of uncertainty, we propose a method that is efficient to implement and provably grants instance-optimality with respect to perturbations of trajectories generated from an open-loop planner (in the sense of minimizing worst-case regret). The resulting policy adapts online to realizations of uncertainty and provably compares well with the best obstacle avoidance policy in hindsight from a rich class of policies. The method is validated in simulation on a dynamical system environment and compared to baseline open-loop planning and robust Hamilton-Jacobi reachability techniques. Further, it is implemented on a hardware example where a quadruped robot traverses a dense obstacle field and encounters input disturbances due to time delays, model uncertainty, and dynamics nonlinearities.

   @inproceedings{snyder_online_2023,
     title = {{Online} {Learning} for {Obstacle} {Avoidance}},
     author = {Snyder, David and Booker, Meghan and Simon, Nathaniel and Xia, Wenhan and Suo, Daniel and Hazan, Elad and Majumdar, Anirudha},
     booktitle = {Proceedings of {The} 7th {Conference} on {Robot} {Learning} (CoRL 2023)},
     month = dec,
     year = {2023},
     publisher = {PMLR},
     pages = {2926--2954},
     issn = {2640-3498},
   }

6. 

   [5] FlowDrone: wind estimation and gust rejection on UAVs using fast-response hot-wire flow sensors

   Nathaniel Simon, Allen Z Ren, Alexander Piqué, and 4 more authors

   In International Conference on Robotics and Automation (ICRA) Dec 2023

   Abs arXiv Bib PDF Website video

   Unmanned aerial vehicles (UAVs) are finding use in applications that place increasing emphasis on robustness to external disturbances including extreme wind. However, traditional multirotor UAV platforms do not directly sense wind; conventional flow sensors are too slow, insensitive, or bulky for widespread integration on UAVs. Instead, drones typically observe the effects of wind indirectly through accumulated errors in position or trajectory tracking. In this work, we integrate a novel flow sensor based on micro-electro-mechanical systems (MEMS) hot-wire technology developed in our prior work onto a multirotor UAV for wind estimation. These sensors are omnidirectional, lightweight, fast, and accurate. In order to achieve superior tracking performance in windy conditions, we train a ‘wind-aware’ residual-based controller via reinforcement learning using simulated wind gusts and their aerodynamic effects on the drone. In extensive hardware experiments, we demonstrate the wind-aware controller outperforming two strong ‘wind-unaware’ baseline controllers in challenging windy conditions.

   @inproceedings{simon2023flowdrone,
     title = {FlowDrone: wind estimation and gust rejection on UAVs using fast-response hot-wire flow sensors},
     author = {Simon, Nathaniel and Ren, Allen Z and Piqu{\'e}, Alexander and Snyder, David and Barretto, Daphne and Hultmark, Marcus and Majumdar, Anirudha},
     booktitle = {International Conference on Robotics and Automation (ICRA)},
     pages = {5393--5399},
     year = {2023},
     organization = {IEEE},
   }

7. 

   [4] Failure Prediction with Statistical Guarantees for Vision-Based Robot Control

   Alec Farid^*, David Snyder^*, Allen Z. Ren, and 1 more author

   In Proceedings of the Robotics: Science and Systems XVIII Conference (RSS 2022) Jun 2022

   Abs arXiv Bib Website

   We are motivated by the problem of performing failure prediction for safety-critical robotic systems with high-dimensional sensor observations (e.g., vision). Given access to a black-box control policy (e.g., in the form of a neural network) and a dataset of training environments, we present an approach for synthesizing a failure predictor with guaranteed bounds on false-positive and false-negative errors. In order to achieve this, we utilize techniques from Probably Approximately Correct (PAC)-Bayes generalization theory. In addition, we present novel class-conditional bounds that allow us to trade-off the relative rates of false-positive vs. false-negative errors. We propose algorithms that train failure predictors (that take as input the history of sensor observations) by minimizing our theoretical error bounds. We demonstrate the resulting approach using extensive simulation and hardware experiments for vision-based navigation with a drone and grasping objects with a robotic manipulator equipped with a wrist-mounted RGB-D camera. These experiments illustrate the ability of our approach to (1) provide strong bounds on failure prediction error rates (that closely match empirical error rates), and (2) improve safety by predicting failures.

   @inproceedings{farid_snyder_failure_2022,
     title = {{Failure} {Prediction} with {Statistical} {Guarantees} for {Vision}-{Based} {Robot} {Control}},
     author = {Farid<sup>*</sup>, Alec and Snyder<sup>*</sup></u>, <u>David and Ren, Allen Z. and Majumdar, Anirudha},
     booktitle = {Proceedings of the {Robotics}: {Science} and {Systems} XVIII {Conference} ({RSS} 2022)},
     volume = {18},
     month = jun,
     year = {2022},
     isbn = {978-0-9923747-8-5},
   }

8. 

   [3] Generating Adversarial Disturbances for Controller Verification

   Udaya Ghai^*, David Snyder^*, Anirudha Majumdar, and 1 more author

   In Proceedings of the 3rd Conference on Learning for Dynamics and Control (L4DC 2021) May 2021

   Oral Presentation Abs arXiv Bib Website

   Selected for Oral Presentation (< 10%) at the 3rd Conference on Learning for Dynamics and Control (L4DC 2021)

   We consider the problem of generating maximally adversarial disturbances for a given controller assuming only blackbox access to it. We propose an online learning approach to this problem that adaptively generates disturbances based on control inputs chosen by the controller. The goal of the disturbance generator is to minimize regret versus a benchmark disturbance-generating policy class, i.e., to maximize the cost incurred by the controller as well as possible compared to the best possible disturbance generator in hindsight (chosen from a benchmark policy class). In the setting where the dynamics are linear and the costs are quadratic, we formulate our problem as an online trust region (OTR) problem with memory and present a new online learning algorithm (MOTR) for this problem. We prove that this method competes with the best disturbance generator in hindsight (chosen from a rich class of benchmark policies that includes linear-dynamical disturbance generating policies). We demonstrate our approach on two simulated examples: (i) synthetically generated linear systems, and (ii) generating wind disturbances for the popular PX4 controller in the AirSim simulator. On these examples, we demonstrate that our approach outperforms several baseline approaches (including H-infinity disturbance generation and gradient-based methods).

   @inproceedings{ghai_snyder_generating_2021,
     title = {{Generating} {Adversarial} {Disturbances} for {Controller} {Verification}},
     author = {Ghai<sup>*</sup>, Udaya and Snyder<sup>*</sup></u>, <u>David and Majumdar, Anirudha and Hazan, Elad},
     booktitle = {Proceedings of the 3rd {Conference} on {Learning} for {Dynamics} and {Control} (L4DC 2021)},
     month = may,
     year = {2021},
     publisher = {PMLR},
     pages = {1192--1204},
     issn = {2640-3498},
   }

9. [2] Output Feedback Control for Lift Maximization of a Pitching Airfoil

   Justin Lidard, Debdipta Goswami, David Snyder, and 3 more authors

   In AIAA Scitech 2020 Forum Jan 2020
10. [1] Tip-Vortex Localization for Cross-Stream Position Control of a Multi-Hole Probe Relative to a Stationary Wing in a Free-Jet Wind Tunnel

    Nathan Lauer, Derrick W. Yeo, David Snyder, and 1 more author

    In AIAA Guidance, Navigation, and Control Conference Jan 2017

Journal Papers

1. 

   [2] Fast-response hot-wire flow sensors for wind and gust estimation on UAVs

   Nathaniel Simon, Alexander Piqué, David Snyder, and 3 more authors

   Measurement Science and Technology 2022

   Abs arXiv Bib PDF

   Due to limitations in available sensor technology, unmanned aerial vehicles (UAVs) lack an active sensing capability to measure turbulence, gusts, or other unsteady aerodynamic phenomena. Conventional in situ anemometry techniques fail to deliver in the harsh and dynamic multirotor environment due to form factor, resolution, or robustness requirements. To address this capability gap, a novel, fast-response sensor system to measure a wind vector in two dimensions is introduced and evaluated. This system, known as ‘MAST’ (for MEMS Anemometry Sensing Tower), leverages advances in microelectromechanical (MEMS) hot-wire devices to produce a solid-state, lightweight, and robust flow sensor suitable for real-time wind estimation onboard a UAV. The MAST uses five pentagonally-arranged microscale hot-wires to determine the wind vector’s direction and magnitude. The MAST’s performance was evaluated in a wind tunnel at speeds up to 5 m/s and orientations of 0 - 360 degrees. A neural network sensor model was trained from the wind tunnel data to estimate the wind vector from sensor signals. The average error of the sensor is 0.14 m/s for speed and 1.6 degrees for direction. Furthermore, 95% of measurements are within 0.36 m/s error for speed and 5.0 degree error for direction. With a bandwidth of 570 Hz determined from square-wave testing, the MAST stands to greatly enhance UAV wind estimation capabilities and enable capturing relevant high-frequency phenomena in flow conditions.

   @article{simon2022fast,
     title = {Fast-response hot-wire flow sensors for wind and gust estimation on UAVs},
     author = {Simon, Nathaniel and Piqu{\'e}, Alexander and Snyder, David and Ikuma, Kyle and Majumdar, Anirudha and Hultmark, Marcus},
     journal = {Measurement Science and Technology},
     volume = {34},
     number = {2},
     pages = {025109},
     year = {2022},
   }

2. [1] Feedback Control and Parameter Estimation for Lift Maximization of a Pitching Airfoil

   Justin M. Lidard, Debdipta Goswami, David Snyder, and 3 more authors

   Journal of Guidance, Control, and Dynamics Mar 2021