arXiv subjects

Steve Chien

Publications and source records attributed to Steve Chien.

At least 19 recordsLinked to original sources

arXiv2026

Distributed Constraint Optimization via Online Learning and Iterative Pricing with Application to Large-Scale Satellite Scheduling

Distributed constraint optimization problems (DCOPs) provide a popular framework for distributed decision making under limited communication, but many real-world instances are too large to solve monolithically. We address this challenge from two complementary directions. We revisit the connection between DCOPs and potential games, and adapt modern online learning algorithms for equilibrium finding to DCOPs. We show that these algorithms are competitive with representative incomplete DCOP algorithms. We then turn to decomposition frameworks for large-scale DCOPs, motivated by large-scale decentralized satellite scheduling. We propose a new framework that separates a DCOP into two interacting subproblems: a high-level meta-DCOP for task allocation, and independent local optimization problems for scheduling. To couple the two levels, we develop a novel iterative pricing method that updates the meta-level utilities using feedback from the local optimizers. Combining our online learning methods with our iterative pricing framework, we obtain near-optimal performance on real-world decentralized satellite scheduling problem instances, fulfilling over 99% of observation requests compared with 87% for state-of-the-art baselines.

cs.AI↗

arXiv2026

Dynamic Targeting of Satellite Observations Using Supplemental Geostationary Satellite Data and Hierarchical Planning

The Dynamic Targeting (DT) mission concept is an approach to satellite observation in which a lookahead sensor gathers information about the upcoming environment and uses this information to intelligently plan observations. Previous work has shown that DT has the potential to increase the science return across applications. However, DT mission concepts must address challenges, such as the limited spatial extent of onboard lookahead data and instrument mobility, data throughput, and onboard computation constraints. In this work, we show how the performance of DT systems can be improved by using supplementary data streamed from geostationary satellites that provide lookahead information up to 35 minutes ahead of time rather than the 1 minute latency from an onboard lookahead sensor. While there is a greater volume of geostationary data, the search space for observation planning explodes exponentially with the size of the horizon. To address this, we introduce a hierarchical planning approach in which the geostationary data is used to plan a long-term observation blueprint in polynomial time, then the onboard lookahead data is leveraged to refine that plan over short-term horizons. We compare the performance of our approach to that of traditional DT planners relying on onboard lookahead data across four different problem instances: three cloud avoidance variations and a storm hunting scenario. We show that our hierarchical planner outperforms the traditional DT planners by up to 41% and examine the features of the scenarios that affect the performance of our approach. We demonstrate that incorporating geostationary satellite data is most effective for dynamic problem instances in which the targets of interest are sparsely distributed throughout the overflight.

cs.RO↗

arXiv2026

Scalable Dynamic Distributed Constraint Optimization with Metareasoning and Application to Continual Satellite Operations

Dynamic distributed constraint optimization problems (DDCOPs) provide a general framework for coordinating autonomous agents in changing environments. However, existing DDCOP formulations do not adequately address settings where optimization and execution overlap, resources persist across time, and agents operate under limited computational and communication constraints. We extend the DDCOP model to address these challenges by introducing an execution-aware formulation, together with new algorithms and frameworks for efficiently computing solutions. We develop a general framework for metareasoning in DDCOPs, enabling agents to determine when the estimated benefit of recomputing solutions outweighs its computational cost. We further extend the neighborhood stochastic search algorithm to the dynamic setting, introducing dynamic incremental neighborhood stochastic search (D-NSS), a scalable decomposition-based DDCOP algorithm that efficiently repairs previous solutions in response to problem dynamics. We apply our methods to the real-world application of large-scale satellite scheduling. Deploying autonomy to satellites requires efficient computation and communication in the face of highly dynamic environments. We demonstrate that D-NSS stabilizes to high-quality solutions, outperforming standard DDCOP baselines in solution quality, computation time, and message volume, while our metareasoning framework successfully balances resource conservation with utility. These methods will support the NASA FAME mission, the largest in-space demonstration of distributed multi-agent AI to date.

cs.AI↗

arXiv2025

Learning-Based Planning for Improving Science Return of Earth Observation Satellites

Earth observing satellites are powerful tools for collecting scientific information about our planet, however they have limitations: they cannot easily deviate from their orbital trajectories, their sensors have a limited field of view, and pointing and operating these sensors can take a large amount of the spacecraft's resources. It is important for these satellites to optimize the data they collect and include only the most important or informative measurements. Dynamic targeting is an emerging concept in which satellite resources and data from a lookahead instrument are used to intelligently reconfigure and point a primary instrument. Simulation studies have shown that dynamic targeting increases the amount of scientific information gathered versus conventional sampling strategies. In this work, we present two different learning-based approaches to dynamic targeting, using reinforcement and imitation learning, respectively. These learning methods build on a dynamic programming solution to plan a sequence of sampling locations. We evaluate our approaches against existing heuristic methods for dynamic targeting, showing the benefits of using learning for this application. Imitation learning performs on average 10.0\% better than the best heuristic method, while reinforcement learning performs on average 13.7\% better. We also show that both learning methods can be trained effectively with small amounts of data.

cs.AI↗

arXiv2025

Real-Time Instrument Planning and Perception for Novel Measurements of Dynamic Phenomena

Advancements in onboard computing mean remote sensing agents can employ state-of-the-art computer vision and machine learning at the edge. These capabilities can be leveraged to unlock new rare, transient, and pinpoint measurements of dynamic science phenomena. In this paper, we present an automated workflow that synthesizes the detection of these dynamic events in look-ahead satellite imagery with autonomous trajectory planning for a follow-up high-resolution sensor to obtain pinpoint measurements. We apply this workflow to the use case of observing volcanic plumes. We analyze classification approaches including traditional machine learning algorithms and convolutional neural networks. We present several trajectory planning algorithms that track the morphological features of a plume and integrate these algorithms with the classifiers. We show through simulation an order of magnitude increase in the utility return of the high-resolution instrument compared to baselines while maintaining efficient runtimes.

cs.RO↗

arXiv2025

Flight of Dynamic Targeting on the CogniSAT-6 Spacecraft

Dynamic targeting (DT) is a spacecraft autonomy concept in which sensor data is acquired and rapidly analyzed and used to drive subsequent observation. We describe the low Earth orbit application of this approach in which lookahead imagery is analyzed to detect clouds, thermal anomalies, or land use cases to drive higher quality near nadir imaging. Use cases for such a capability include: cloud avoidance, storm hunting, search for planetary boundary layer events, plume study, and beyond. The DT concept requires a lookahead sensor or agility to use a primary sensor in such a mode, edge computing to analyze images rapidly onboard, and a primary followup sensor. Additionally, an inter-satellite or low latency communications link can be leveraged for cross platform tasking. We describe implementation in progress to fly DT in early 2025 on the CogniSAT-6 (Ubotica/Open Cosmos) spacecraft that launched in March 2024 on the SpaceX Transporter-10 launch.

eess.SY↗

arXiv2025

Demonstrating Onboard Inference for Earth Science Applications with Spectral Analysis Algorithms and Deep Learning

In partnership with Ubotica Technologies, the Jet Propulsion Laboratory is demonstrating state-of-the-art data analysis onboard CogniSAT-6/HAMMER (CS-6). CS-6 is a satellite with a visible and near infrared range hyperspectral instrument and neural network acceleration hardware. Performing data analysis at the edge (e.g. onboard) can enable new Earth science measurements and responses. We will demonstrate data analysis and inference onboard CS-6 for numerous applications using deep learning and spectral analysis algorithms.

cs.AI↗

arXiv2025

Planning, scheduling, and execution on the Moon: the CADRE technology demonstration mission

NASA's Cooperative Autonomous Distributed Robotic Exploration (CADRE) mission, slated for flight to the Moon's Reiner Gamma region in 2025/2026, is designed to demonstrate multi-agent autonomous exploration of the Lunar surface and sub-surface. A team of three robots and a base station will autonomously explore a region near the lander, collecting the data required for 3D reconstruction of the surface with no human input; and then autonomously perform distributed sensing with multi-static ground penetrating radars (GPR), driving in formation while performing coordinated radar soundings to create a map of the subsurface. At the core of CADRE's software architecture is a novel autonomous, distributed planning, scheduling, and execution (PS&E) system. The system coordinates the robots' activities, planning and executing tasks that require multiple robots' participation while ensuring that each individual robot's thermal and power resources stay within prescribed bounds, and respecting ground-prescribed sleep-wake cycles. The system uses a centralized-planning, distributed-execution paradigm, and a leader election mechanism ensures robustness to failures of individual agents. In this paper, we describe the architecture of CADRE's PS&E system; discuss its design rationale; and report on verification and validation (V&V) testing of the system on CADRE's hardware in preparation for deployment on the Moon.

cs.RO↗

arXiv2024

Training Large ASR Encoders with Differential Privacy

Self-supervised learning (SSL) methods for large speech models have proven to be highly effective at ASR. With the interest in public deployment of large pre-trained models, there is a rising concern for unintended memorization and leakage of sensitive data points from the training data. In this paper, we apply differentially private (DP) pre-training to a SOTA Conformer-based encoder, and study its performance on a downstream ASR task assuming the fine-tuning data is public. This paper is the first to apply DP to SSL for ASR, investigating the DP noise tolerance of the BEST-RQ pre-training method. Notably, we introduce a novel variant of model pruning called gradient-based layer freezing that provides strong improvements in privacy-utility-compute trade-offs. Our approach yields a LibriSpeech test-clean/other WER (%) of 3.78/ 8.41 with ($10$, 1e^-9)-DP for extrapolation towards low dataset scales, and 2.81/ 5.89 with (10, 7.9e^-11)-DP for extrapolation towards high scales.

cs.SD↗

arXiv2023

Using Unsupervised and Supervised Learning and Digital Twin for Deep Convective Ice Storm Classification

Smart Ice Cloud Sensing (SMICES) is a small-sat concept in which a primary radar intelligently targets ice storms based on information collected by a lookahead radiometer. Critical to the intelligent targeting is accurate identification of storm/cloud types from eight bands of radiance collected by the radiometer. The cloud types of interest are: clear sky, thin cirrus, cirrus, rainy anvil, and convection core. We describe multi-step use of Machine Learning and Digital Twin of the Earth's atmosphere to derive such a classifier. First, a digital twin of Earth's atmosphere called a Weather Research Forecast (WRF) is used generate simulated lookahead radiometer data as well as deeper "science" hidden variables. The datasets simulate a tropical region over the Caribbean and a non-tropical region over the Atlantic coast of the United States. A K-means clustering over the scientific hidden variables was utilized by human experts to generate an automatic labelling of the data - mapping each physical data point to cloud types by scientists informed by mean/centroids of hidden variables of the clusters. Next, classifiers were trained with the inputs of the simulated radiometer data and its corresponding label. The classifiers of a random decision forest (RDF), support vector machine (SVM), Gaussian na\"ive bayes, feed forward artificial neural network (ANN), and a convolutional neural network (CNN) were trained. Over the tropical dataset, the best performing classifier was able to identify non-storm and storm clouds with over 80% accuracy in each class for a held-out test set. Over the non-tropical dataset, the best performing classifier was able to classify non-storm clouds with over 90% accuracy and storm clouds with over 40% accuracy. Additionally both sets of classifiers were shown to be resilient to instrument noise.

cs.LG↗

arXiv2023

How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy

ML models are ubiquitous in real world applications and are a constant focus of research. At the same time, the community has started to realize the importance of protecting the privacy of ML training data. Differential Privacy (DP) has become a gold standard for making formal statements about data anonymization. However, while some adoption of DP has happened in industry, attempts to apply DP to real world complex ML models are still few and far between. The adoption of DP is hindered by limited practical guidance of what DP protection entails, what privacy guarantees to aim for, and the difficulty of achieving good privacy-utility-computation trade-offs for ML models. Tricks for tuning and maximizing performance are scattered among papers or stored in the heads of practitioners. Furthermore, the literature seems to present conflicting evidence on how and whether to apply architectural adjustments and which components are "safe" to use with DP. This work is a self-contained guide that gives an in-depth overview of the field of DP ML and presents information about achieving the best possible DP ML model with rigorous privacy guarantees. Our target audience is both researchers and practitioners. Researchers interested in DP for ML will benefit from a clear overview of current advances and areas for improvement. We include theory-focused sections that highlight important topics such as privacy accounting and its assumptions, and convergence. For a practitioner, we provide a background in DP theory and a clear step-by-step guide for choosing an appropriate privacy definition and approach, implementing DP training, potentially updating the model architecture, and tuning hyperparameters. For both researchers and practitioners, consistently and fully reporting privacy guarantees is critical, and so we propose a set of specific best practices for stating guarantees.

cs.LG↗

arXiv2023

Planetary Exploration Horizon 2061 Report Chapter 5: Enabling technologies for planetary exploration

The main objective of this chapter is to present an overview of the different areas of key technologies that will be needed to fly the technically most challenging of the representative missions identified in chapter 4 (the Pillar 2 Horizon 2061 report). It starts with a description of the future scientific instruments which will address the key questions of Horizon 2061 described in chapter 3 (the Pillar 1 Horizon 2061 report) and the new technologies that the next generations of space instruments will require (section 2). From there, the chapter follows the line of logical development and implementation of a planetary mission: section 3 describes some of the novel mission architectures that will be needed and how they will articulate interplanetary spacecraft and science platforms; section 4 summarizes the system-level technologies needed: power, propulsion, navigation, communication, advanced autonomy on board planetary spacecraft; section 5 describes the diversity of specialized science platforms that will be needed to survive, operate and return scientific data from the extreme environments that future missions will target; section 6 describes the new technology developments that will be needed for long-duration missions and semi-permanent settlements; finally, section 7 attempts to anticipate on the disruptive technologies that should emerge and progressively prevail in the decades to come to meet the long-term needs of future planetary missions.

astro-ph.IM↗

arXiv2023

Enabling Astronaut Self-Scheduling using a Robust Advanced Modelling and Scheduling system: an assessment during a Mars analogue mission

Human long duration exploration missions (LDEMs) raise a number of technological challenges. This paper addresses the question of the crew autonomy: as the distances increase, the communication delays and constraints tend to prevent the astronauts from being monitored and supported by a real time ground control. Eventually, future planetary missions will necessarily require a form of astronaut self-scheduling. We study the usage of a computer decision-support tool by a crew of analog astronauts, during a Mars simulation mission conducted at the Mars Desert Research Station (MDRS, Mars Society) in Utah. The proposed tool, called Romie, belongs to the new category of Robust Advanced Modelling and Scheduling (RAMS) systems. It allows the crew members (i) to visually model their scientific objectives and constraints, (ii) to compute near-optimal operational schedules while taking uncertainty into account, (iii) to monitor the execution of past and current activities, and (iv) to modify scientific objectives/constraints w.r.t. unforeseen events and opportunistic science. In this study, we empirically measure how the astronauts, who are novice planners, perform at using such a tool when self-scheduling under the realistic assumptions of a simulated Martian planetary habitat.

cs.RO↗

arXiv2022

Temporal Multimodal Multivariate Learning

We introduce temporal multimodal multivariate learning, a new family of decision making models that can indirectly learn and transfer online information from simultaneous observations of a probability distribution with more than one peak or more than one outcome variable from one time stage to another. We approximate the posterior by sequentially removing additional uncertainties across different variables and time, based on data-physics driven correlation, to address a broader class of challenging time-dependent decision-making problems under uncertainty. Extensive experiments on real-world datasets ( i.e., urban traffic data and hurricane ensemble forecasting data) demonstrate the superior performance of the proposed targeted decision-making over the state-of-the-art baseline prediction methods across various settings.

cs.LG↗

arXiv2022

Detecting Unintended Memorization in Language-Model-Fused ASR

End-to-end (E2E) models are often being accompanied by language models (LMs) via shallow fusion for boosting their overall quality as well as recognition of rare words. At the same time, several prior works show that LMs are susceptible to unintentionally memorizing rare or unique sequences in the training data. In this work, we design a framework for detecting memorization of random textual sequences (which we call canaries) in the LM training data when one has only black-box (query) access to LM-fused speech recognizer, as opposed to direct access to the LM. On a production-grade Conformer RNN-T E2E model fused with a Transformer LM, we show that detecting memorization of singly-occurring canaries from the LM training data of 300M examples is possible. Motivated to protect privacy, we also show that such memorization gets significantly reduced by per-example gradient-clipped LM training without compromising overall quality.

cs.CL↗

arXiv2022

Toward Training at ImageNet Scale with Differential Privacy

Differential privacy (DP) is the de facto standard for training machine learning (ML) models, including neural networks, while ensuring the privacy of individual examples in the training set. Despite a rich literature on how to train ML models with differential privacy, it remains extremely challenging to train real-life, large neural networks with both reasonable accuracy and privacy. We set out to investigate how to do this, using ImageNet image classification as a poster example of an ML task that is very challenging to resolve accurately with DP right now. This paper shares initial lessons from our effort, in the hope that it will inspire and inform other researchers to explore DP training at scale. We show approaches that help make DP training faster, as well as model types and settings of the training process that tend to work better in the DP setting. Combined, the methods we discuss let us train a Resnet-18 with DP to $47.9\%$ accuracy and privacy parameters $ε= 10, δ= 10^{-6}$. This is a significant improvement over "naive" DP training of ImageNet models, but a far cry from the $75\%$ accuracy that can be obtained by the same network without privacy. The model we use was pretrained on the Places365 data set as a starting point. We share our code at https://github.com/google-research/dp-imagenet, calling for others to build upon this new baseline to further improve DP at scale.

cs.LG↗

arXiv2021

Multi-Robot On-site Shared Analytics Information and Computing

Computation load-sharing across a network of heterogeneous robots is a promising approach to increase robots capabilities and efficiency as a team in extreme environments. However, in such environments, communication links may be intermittent and connections to the cloud or internet may be nonexistent. In this paper we introduce a communication-aware, computation task scheduling problem for multi-robot systems and propose an integer linear program (ILP) that optimizes the allocation of computational tasks across a network of heterogeneous robots, accounting for the networked robots' computational capabilities and for available (and possibly time-varying) communication links. We consider scheduling of a set of inter-dependent required and optional tasks modeled by a dependency graph. We present a consensus-backed scheduling architecture for shared-world, distributed systems. We validate the ILP formulation and the distributed implementation in different computation platforms and in simulated scenarios with a bias towards lunar or planetary exploration scenarios. Our results show that the proposed implementation can optimize schedules to allow a threefold increase the amount of rewarding tasks performed (e.g., science measurements) compared to an analogous system with no computational load-sharing.

cs.RO↗

arXiv2021

Membership Inference Attacks From First Principles

A membership inference attack allows an adversary to query a trained machine learning model to predict whether or not a particular example was contained in the model's training dataset. These attacks are currently evaluated using average-case "accuracy" metrics that fail to characterize whether the attack can confidently identify any members of the training set. We argue that attacks should instead be evaluated by computing their true-positive rate at low (e.g., <0.1%) false-positive rates, and find most prior attacks perform poorly when evaluated in this way. To address this we develop a Likelihood Ratio Attack (LiRA) that carefully combines multiple ideas from the literature. Our attack is 10x more powerful at low false-positive rates, and also strictly dominates prior attacks on existing metrics.

cs.CR↗