David A. Snyder

Department of Electrical and Systems Engineering.

Philadelphia, PA 19104

I am a postdoctoral research fellow in the Department of Electrical and Systems Engineering at the University of Pennsylvania, working with George Pappas and Nikolai Matni at the intersection of control, robust decision-making, machine learning, and robotics. Previously, I completed my PhD in the Intelligent Robot Motion Laboratory at Princeton University, advised by Ani Majumdar.

My research develops theory for robotic systems which holds nonasymptotically (i.e., in finite samples) under realistic models of uncertainty in the operating environment. These guarantees are designed to codify, complement, and inform empirical developments within the field. In general, these guarantees can be partitioned according to the modeling assumptions over the uncertainty, spanning the worst-case (adversarial, or ‘nonstochastic’) settings to i.i.d. stochastic realizations of uncertainty. The former occur within-trajectory, where the signals may have strong temporal correlation, whereas the latter tend to arise in batch contexts. One of the most compelling areas of research at present is understanding the scope of the ‘in-between:’ when the data is correlated but admits structure so as to not require fully adversarial treatment.

During my PhD I developed methods tailored to each of these domains. In the adversarial context, I developed an algorithm for learned controller validation in the setting of linear systems (MOTR) using techniques from regret minimization in online learning; this was later lifted to the higher-level problem of obstacle avoidance (OLC). The latter was one of the first examples of practical implementation of online regret-minimizing controllers on hardware. In the stochastic context, we developed methods for online failure prediction and mitigation via extending PAC-Bayes generalization bounds FP. More recently, we have applied techniques from sequential analysis and safe, anytime-valid inference (SAVI) for multivalent problems of evaluation within the robotics context. This has led to fruitful developments within the context of policy comparison and active data collection, as illustrated by STEP.

Prior to my PhD, I received my bachelor’s degree from the University of Maryland, College Park (go Terps!). Outside of work I enjoy cycling, chess, classical music, and playing tennis.

Feel free to contact me at: dsnyder5 at seas dot upenn dot edu.

news

No news so far...

Publications

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, Udaya and Snyder, 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} }
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} }
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, Alec and Snyder, 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} }
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, Eric and Snyder, 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} }
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} }
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 Jun 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} }
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) Jun 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}, }
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} }
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} }

Patents

Omnidirectional flow sensor (US Patent App. 18/367,015)

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

2024

Abs Bib Website

Disclosed is a fast-response sensor system to measure a fluid vector in a plurality of dimensions. This system, known as ‘MAST’ (for MEMS Anemometry Sensing Tower), utilizes microelectromechanical (MEMS) hot-wire devices to produce a solid-state, lightweight, and robust flow sensor system suitable for, e.g., real-time wind estimation onboard a UAV. The MAST uses three through eighteen polygonally-arranged microscale flow sensors to determine the fluid’s vector’s direction and magnitude.
@article{simon2024omnidirectional, title = {Omnidirectional flow sensor (US Patent App. 18/367,015)}, author = {Simon, Nathaniel and Piqu{\'e}, Alexander and Snyder, David and Ikuma, Kyle and Majumdar, Anirudha and Hultmark, Marcus}, year = {2024}, publisher = {Google Patents}, note = {US Patent App. 18/367,015}, patents = {true} }

PhD Thesis

Nonasymptotic Methods for Guaranteed Robotic Policy Synthesis and Evaluation

David Snyder

2025

Abs Bib

In the past decade, robotics research has undergone an unremittingly Schumpeterian evolution, manifesting far-reaching and rapid progress throughout the field. Entire analytical paradigms, developed over decades, have been superseded in empirical performance by novel advances leveraging vast amounts of newly available computation and training data. As a result, current robots are capable of complex, dexterous behaviors which empirically generalize across significant variation in task settings and environments. However, not all is solved; robots which appear to be robust often demonstrate brittle and unpredictable behavior in otherwise benign settings, where small, task-irrelevant fluctuations derail desired system behavior. Without reliable assurances that these autonomous systems are themselves reliable, the potential for deployment to address real-world problems remains fundamentally limited. To further the goal of deploying robots with assured safety and reliability, this dissertation constructs rigorous, interpretable, and implementable guarantees for robotic systems which account for the practical constraints imposed by the empirical nature of the robotics discipline. These guarantees are directed towards two critical ends: (1) policy synthesis, or guarantees on a property of the robot’s decision-making rule; and (2) policy evaluation, or guarantees on a property of an evaluator’s decision-making process. The core challenge in robotics — and in synthesizing guarantees about robots — is the presence of significant, often-irreducible uncertainty in the operating environment. Robots must maintain rich sensor observations to interpret and interact with external objects, which themselves may be reasoning agents capable of adversarial (or collaborative) behaviors. The roboticist cannot arbitrarily reduce uncertainty by pre-filtering what the robot observes, and the representation of the robot’s uncertainty thus matters enormously. Under stochastic uncertainty, we focus on evaluation, including the development of provably near-optimal sequential procedures for comparing robot policies, and online failure predictors with guaranteed class-conditional correctness. Under nonstochastic uncertainty, we develop online learning procedures which construct robust disturbance generators and obstacle avoidance controllers. In each setting, guarantees are tailored to the small-data regime and enforce nonasymptotic (finite-sample) assurances. These methods represent important steps toward understanding the nature of uncertainty “in the robot’s world,’’ which is necessary for future deployment of safe, reliable robots capable of addressing practical problems.
@phdthesis{snyder_nonasymptotic_2025, title = {Nonasymptotic Methods for Guaranteed Robotic Policy Synthesis and Evaluation}, author = {Snyder, David}, year = {2025}, school = {Princeton University}, thesis = {true} }

Talks

(Upcoming) Efficient and General Evaluation Methods for Robotic Systems

March 20th, 2026: RGSO-CARS Seminar, University of Delaware

Is Your Imitation Learning Policy Better Than Mine? Policy Comparison with Near-Optimal Stopping

March 31rst, 2025: USC CPS Seminar, University of Southern California
March 7th, 2025: Pappas Group, University of Pennsylvania

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

June 2nd, 2023: ICRA 2023 Workshop on Bridging the Lab-to-Real Gap

Online Learning for Obstacle Avoidance

June 22, 2022: Google Office Princeton

If you would like to host me for a talk (virtual or in-person), please reach out!