About

Ashish Goel is a Professor of Management Science and Engineering at Stanford University, holding the Fortinet Founders Chair of Management Science and Engineering. He is also a Professor, by courtesy, of Computer Science. He received his PhD in Computer Science from Stanford University in 1999. His research interests lie in the design, analysis, and applications of algorithms. Prior to his current position, he was an Assistant Professor of Computer Science at the University of Southern California from 1999 to 2002. His work has garnered recognition, including being named an ACM Fellow for contributions to computing that are transforming science and society. He has been involved in various research projects and initiatives, including efforts related to AI, climate resilience, and democratic deliberation, and has contributed to the academic and broader community through his leadership and research activities.

Research topics

• Computer Science
• Business
• Sociology
• Artificial Intelligence
• Economics
• Physics
• Engineering
• Astrobiology
• Aerospace engineering
• Psychology
• Medicine
• World Wide Web
• Theoretical computer science
• Advertising
• Demographic economics
• Astronomy
• Geography
• Demography
• Socioeconomics
• Environmental health
• Internet privacy
• Geology
• Geophysics
• Remote sensing

Selected publications

• Question the Questions: Auditing Representation in Online Deliberative Processes

  2026-04-12

  articleOpen access

  A central feature of many deliberative processes, such as citizens' assemblies and deliberative polls, is the opportunity for participants to engage directly with experts. While participants are typically invited to propose questions for expert panels, only a limited number can be selected due to time constraints. This raises the challenge of how to choose a small set of questions that best represent the interests of all participants. We introduce an auditing framework for measuring the level of representation provided by a slate of questions, based on the social choice concept known as justified representation (JR). We present the first algorithms for auditing JR in the general utility setting, with our most efficient algorithm achieving a runtime of $O(mn\log n)$, where $n$ is the number of participants and $m$ is the number of proposed questions. We apply our auditing methods to historical deliberations, comparing the representativeness of (a) the actual questions posed to the expert panel (chosen by a moderator), (b) participants' questions chosen via integer linear programming, (c) summary questions generated by large language models (LLMs). Our results highlight both the promise and current limitations of LLMs in supporting deliberative processes. By integrating our methods into an online deliberation platform that has been used for over hundreds of deliberations across more than 50 countries, we make it easy for practitioners to audit and improve representation in future deliberations.

  PublisherDOI

• In situ, Surface-deployed Distributed Instruments for Planetary Science: Scientific Opportunities and Technology Feasibility

  The Planetary Science Journal · 2025-03-01

  articleOpen access

  Abstract In this paper, we assess the scientific promise and technology feasibility of in situ distributed instruments for planetary surface and atmospheric science. A distributed instrument is an instrument designed to collect spatially and temporally correlated data from multiple networked, geographically distributed point sensors. Distributed instruments are ubiquitous in Earth science, where they are routinely employed for weather and climate science, seismic studies and resource prospecting, and detection of industrial emissions. However, to date, their adoption in planetary science has been minimal. It is natural to ask whether this lack of adoption is driven by low potential to address high-priority questions in planetary science, immature technology, or both. To address this question, we survey high-priority planetary science questions that are uniquely well suited to distributed, surface-deployed, in situ instruments. We identify four areas of research where such distributed instruments hold promise to unlock answers that are largely inaccessible to monolithic sensors or remote sensing approaches, or can complement existing approaches, namely, in weather and climate studies; localization of seismic events on rocky and icy bodies; localization of trace gas emissions; and magnetometry studies of internal planetary composition. Next, we survey enabling technologies for distributed sensors and assess their maturity. We identify sensor placement (including descent and landing on planetary surfaces), power, and instrument autonomy as three key areas requiring further investment to enable future distributed instruments. Overall, this work shows that distributed instruments hold great promise for planetary science, and paves the way for follow-up studies of future distributed instruments for solar system science.

  PublisherDOI

• Survey of Mission Concepts for Exploring the Dark Ages Universe

  2025-03-01

  article

  The Dark Ages Epoch of the early Universe has not been explored for cosmological observations to date! Observations of the Dark Ages has the potential to revolutionize physics and cosmology by improving our understanding of fundamental particle physics, Dark matter and Dark energy physics, and inflation. The Dark Ages Epoch represent the period in the early evolution of the Universe, starting immediately after the decoupling of Cosmic Microwave Background (CMB) photons from matter, and ending with the formation of the first stars and galaxies. The Hi signal (with rest wavelength and frequency 21 cm and 1420 MHz, respectively) is the only available probe we can use to understand this crucial phase in the cosmological history of the Universe and answer fundamental questions about the validity of the standard cosmological model, dark matter physics, and inflation. Due to cosmological redshift, this signal is now only observable in the 5–40 MHz frequency band. The biggest challenge with these observations is separating the Dark Ages signal from the 5-orders-of-magnitude stronger Galactic Foreground noise, which is the synchrotron radiation emitted by relativistic electrons that travel on spiraling paths in our Milky Way Galaxy's magnetic field. A number of mission concepts have been proposed that could observe the Dark Ages from the lunar far-side. They are broadly classified into: (1) Single telescope concept on the lunar surface, (2) Sparse dipole array concepts on the lunar surface, (3) Satellite constellation concepts in Moon orbit, and (4) Satellite constellation concepts in Earth-Moon system. This paper presents a survey of different mission concepts that have been proposed to observe the Dark Ages Universe.

  PublisherDOI

• Elucidating Production Bottlenecks in the Indian Pharmaceutical Industry for Enhanced Pandemic Preparedness Using a Combined Theory of Constraints and Six Sigma Approach

  Indian Journal of Pharmaceutical Education and Research · 2025-05-16 · 1 citations

  articleOpen access

  Aim/Background: Early in the COVID-19 epidemic, the dire need for effective and readily available outpatient therapies became apparent as healthcare systems worldwide faced unprecedented strain. This study addressed the initial focus on medications with anecdotal evidence against COVID-19 and the emergence of Hydroxychloroquine (HCQ) as a potential therapeutic option due to its demonstrated in vitro activity and established safety record in treating autoimmune conditions. However, the surge in prescriptions and panic buying led to a significant imbalance in the supply and demand for HCQ, affecting pharmaceutical companies. Focusing on the Pharmaceutical Supply Chain (PSC), the primary objective was to present a new methodology for investigating production processes to identify potential improvements and mitigate the impact of bottlenecks on productivity. Materials and Methods: The study employed an integrated Theory of Constraints (TOC)-Six Sigma (SS) approach to pinpoint constraints within the PSC and proposed strategies to mitigate their effects. The case study presented in this research focused on the Indian pharmaceutical industry. Results: The results revealed that inventory status and production capacity were critical bottlenecks/constraints in the system. The integrated approach successfully identified these constraints and provided insights into potential improvement scenarios. Conclusion: This study presented a unique roadmap for industry practitioners to alleviate production bottlenecks and enhance the resilience of the PSC, especially in the face of pandemics. Implementing these findings could help pharmaceutical companies better navigate future disruptions and contribute to the development of robust therapeutic supply chains.

  PublisherOA PDFDOI

• AI Space Cortex: An Experimental System for Future Era Space Exploration

  IEEE transactions on field robotics. · 2025-01-01

  article

  Our Robust, Explainable Autonomy for Scientific Icy Moon Operations (REASIMO) effort contributes to NASA’s Concepts for Ocean worlds Life Detection Technology (COLDTech) program, which explores science platform technologies for ocean worlds such as Europa and Enceladus. Ocean world missions pose significant operational challenges. These include long communication lags, limited power, and lifetime limitations caused by radiation damage and hostile conditions. Given these operational limitations, onboard autonomy will be vital for future Ocean world missions. Besides the management of nominal lander operations, onboard autonomy must react appropriately in the event of anomalies. Traditional spacecraft rely on a transition into ’safe-mode’ in which non-essential components and subsystems are powered off to preserve safety and maintain communication with Earth. For a severely time-limited Ocean world mission, resolutions to these anomalies that can be executed without Earth-in-the-loop communication and associated delays are paramount for completion of the mission objectives and science goals. To address these challenges, the REASIMO effort aims to demonstrate a robust level of AI-assisted autonomy for such missions, including the ability to detect and recover from anomalies, and to perform missions based on pre-trained behaviors rather than hard-coded, predetermined logic like all prior space missions. We developed an AI-assisted, personality-driven, intelligent framework for control of an Ocean world mission by combining a mix of advanced technologies. To demonstrate the capabilities of the framework, we perform tests of autonomous sampling operations on a lander-manipulator testbed at the NASA Jet Propulsion Laboratory, approximating possible surface conditions such a mission might encounter. This paper presents the architecture and encapsulated functionality of our intelligent mission control framework, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">AI Space Cortex</i>, and reports results from deployment of this technology on a flight-relevant testbed to demonstrate its handling of the challenges of autonomous sampling operations across changing system conditions.

  PublisherDOI

• Technology use in B2B sales: examining the extant literature and identifying future research opportunities using morphological analysis

  Journal of Personal Selling and Sales Management · 2024-07-26 · 24 citations

  article1st author

  International audience

  PublisherDOI

• Geophysical Observations of the 2023 September 24 OSIRIS-REx Sample Return Capsule Reentry

  The Planetary Science Journal · 2024-09-01 · 25 citations

  articleOpen access

  Abstract Sample return capsules (SRCs) entering Earth’s atmosphere at hypervelocity from interplanetary space are a valuable resource for studying meteor phenomena. The 2023 September 24 arrival of the Origins, Spectral Interpretation, Resource Identification, and Security-Regolith Explorer SRC provided an unprecedented chance for geophysical observations of a well-characterized source with known parameters, including timing and trajectory. A collaborative effort involving researchers from 16 institutions executed a carefully planned geophysical observational campaign at strategically chosen locations, deploying over 400 ground-based sensors encompassing infrasound, seismic, distributed acoustic sensing, and Global Positioning System technologies. Additionally, balloons equipped with infrasound sensors were launched to capture signals at higher altitudes. This campaign (the largest of its kind so far) yielded a wealth of invaluable data anticipated to fuel scientific inquiry for years to come. The success of the observational campaign is evidenced by the near-universal detection of signals across instruments, both proximal and distal. This paper presents a comprehensive overview of the collective scientific effort, field deployment, and preliminary findings. The early findings have the potential to inform future space missions and terrestrial campaigns, contributing to our understanding of meteoroid interactions with planetary atmospheres. Furthermore, the data set collected during this campaign will improve entry and propagation models and augment the study of atmospheric dynamics and shock phenomena generated by meteoroids and similar sources.

  PublisherDOI

• Few-shot Scooping Under Domain Shift via Simulated Maximal Deployment Gaps

  arXiv (Cornell University) · 2024-08-06

  preprintOpen access

  Autonomous lander missions on extraterrestrial bodies need to sample granular materials while coping with domain shifts, even when sampling strategies are extensively tuned on Earth. To tackle this challenge, this paper studies the few-shot scooping problem and proposes a vision-based adaptive scooping strategy that uses the deep kernel Gaussian process method trained with a novel meta-training strategy to learn online from very limited experience on out-of-distribution target terrains. Our Deep Kernel Calibration with Maximal Deployment Gaps (kCMD) strategy explicitly trains a deep kernel model to adapt to large domain shifts by creating simulated maximal deployment gaps from an offline training dataset and training models to overcome these deployment gaps during training. Employed in a Bayesian Optimization sequential decision-making framework, the proposed method allows the robot to perform high-quality scooping actions on out-of-distribution terrains after a few attempts, significantly outperforming non-adaptive methods proposed in the excavation literature as well as other state-of-the-art meta-learning methods. The proposed method also demonstrates zero-shot transfer capability, successfully adapting to the NASA OWLAT platform, which serves as a state-of-the-art simulator for potential future planetary missions. These results demonstrate the potential of training deep models with simulated deployment gaps for more generalizable meta-learning in high-capacity models. Furthermore, they highlight the promise of our method in autonomous lander sampling missions by enabling landers to overcome the deployment gap between Earth and extraterrestrial bodies.

  PublisherOA PDFDOI

• Learning and Autonomy for Extraterrestrial Terrain Sampling: An Experience Report from OWLAT Deployment

  2024-01-04 · 1 citations

  article

  Extraterrestrial autonomous lander missions increasingly demand adaptive capabilities to handle the unpredictable and diverse nature of the terrain. This paper discusses the deployment of a Deep Meta-Learning with Controlled Deployment Gaps (CoDeGa) trained model for terrain scooping tasks in Ocean Worlds Lander Autonomy Testbed (OWLAT) at NASA Jet Propulsion Laboratory. The CoDeGa-powered scooping strategy is designed to adapt to novel terrains, selecting scooping actions based on the available RGB-D image data and limited experience. The paper presents our experiences with transferring the scooping framework with CoDeGa-trained model from a low-fidelity testbed to the high-fidelity OWLAT testbed. Additionally, it validates the method’s performance in novel, realistic environments, and shares the lessons learned from deploying learning-based autonomy algorithms for space exploration. Experimental results from OWLAT substantiate the efficacy of CoDeGa in rapidly adapting to unfamiliar terrains and effectively making autonomous decisions under considerable domain shifts, thereby endorsing its potential utility in future extraterrestrial missions.

  PublisherDOI

• First Results of Airborne GNSS Radio Occultation Sounding From Airbus Commercial Aircraft

  Geophysical Research Letters · 2024-08-30 · 1 citations

  articleOpen access

  Abstract The lack of high vertical resolution atmospheric thermodynamic structure observations inside or near major weather events impedes our understanding of physical processes and their predictability in numerical weather prediction (NWP) models. Airborne Global Navigation Satellite System (GNSS) radio occultation (airborne radio occultation [ARO]) has proven to be a viable remote sensing option to offer dense soundings near flight tracks. The global fleet of commercial aircraft already equipped with GNSS receivers could be leveraged to produce an unprecedented number of ARO soundings along global flight paths. Eleven cases of atmospheric bending angle and refractivity profiles were successfully retrieved and compared with the colocated European Center for Medium‐Range Weather Forecasting global reanalysis data. Good quality measurements are obtained with median refractivity differences less than 1% in the middle and upper troposphere, between 5.5 and 11.5 km. Given the use of aircraft data (e.g., Aircraft Meteorological DAta Relay) for data assimilation, incorporating ARO profiles would be a valuable addition, further enhancing the accuracy of aviation and weather forecasts.

  PublisherOA PDFDOI

Recent grants

• DC: Small: The Use of Ternary Associative Memories in Data Intensive Computing

  NSF · $430k · 2009–2013

• CAREER: Algorithms for Services - Oriented Communications Networks

  NSF · $280k · 2003–2008

• BIGDATA: F: DKA: Collaborative Research: Dealing Efficiently with Big Social Network Data

  NSF · $300k · 2014–2018

• III: Medium: Collaborative Research: Optimization with Sparse Priors -- Algorithms, Indices, and Economic Incentives

  NSF · $698k · 2009–2014

• AitF: Collaborative Research: Fair and Efficient Societal Decision Making via Collaborative Convex Optimization

  NSF · $475k · 2016–2019

Frequent coauthors

• Sudipto Guha

  University of Pennsylvania

  33 shared

• Moses Charikar

  Stanford University

  32 shared

• Sanjeev Khanna

  30 shared

• Amit Chakrabarti

  Centre for Mental Health

  27 shared

• Pascal Koiran

  25 shared

• Gruia Călinescu

  25 shared

• Howard Karloff

  New York Proton Center

  25 shared

• Nicolas Schabanel

  École Normale Supérieure de Lyon

  25 shared

Education

• Ph.D., Computer Science

  Stanford University

  1990

• M.S., Computer Science

  Stanford University

  1987

• B.S., Electrical Engineering and Computer Science

  Massachusetts Institute of Technology (MIT)

  1983

Awards & honors

• ACM Fellow (2025)