About

Dr. Luis Antonio Garcia is an Assistant Professor at The University of Utah Kahlert School of Computing, focusing on the security and safety of learning-enabled Cyber-physical Systems (CPS) and Internet-of-Things (IoT). His research develops methods to ensure trustworthy and resilient autonomous systems that interact with humans, particularly in safety-critical contexts. His work aims to enable mutual assurances between deep-learning-enabled cyber-physical systems and humans by leveraging semantics to retrofit security and resiliency, integrating human logic and deep learning for trustworthy autonomous design, and ensuring secure, private, and useful ubiquitous sensing. He has a rich academic background, having previously served as a Research Assistant Professor at USC's Department of Computer Science and a Research Lead at the USC Information Sciences Institute. Dr. Garcia also held a postdoctoral appointment at UCLA's Networked & Embedded Systems Laboratory, collaborating with Dr. Mani Srivastava. He earned his PhD in Computer Engineering with a cybersecurity focus from Rutgers University, where his dissertation was titled “Physics for the Sake of Security, Security for the Sake of Physics.” His prior experience includes an internship at Carnegie Mellon University’s Logical Systems Lab, working on the verification of programmable logic controllers in cyber-physical systems, and an internship at Siemens Corporate Research focusing on PLC security. His research interests are driven by real-world stakeholders, aiming to enhance safety, security, and trustworthiness in cyber-physical and IoT systems.

Research topics

• Computer Science
• Artificial Intelligence
• Engineering
• Automotive engineering
• Mathematical optimization
• Business
• Electrical engineering
• Risk analysis (engineering)
• Reliability engineering
• Systems engineering
• Mathematics

Selected publications

• Hierarchical Combination of Deep Reinforcement Learning and Quadratic Programming for Distribution System Restoration

  IEEE Transactions on Sustainable Energy · 2023 · 31 citations

  • Computer Science
  • Computer Science
  • Artificial Intelligence

  This paper proposes a model for hierarchical combination of deep reinforcement learning (DRL) with quadratic programming for distribution system restoration after major outages. In the proposed model, optimal power dispatch of a collection of distributed energy resources, called integrated hybrid resources (IHRs), is determined by a DRL-trained controller, while a grid-level quadratic programming problem checks grid constraints and performs critical restoration operation. DRL is implemented using Soft Actor-Critic (SAC) algorithm, which is shown to outperform the common Deep Deterministic Policy Gradient in continuous action spaces. The numerical studies, performed on the 123-bus test distribution system, demonstrates that the hierarchical combination of DRL and quadratic programming not only speeds up the local operation of multiple IHRs, but also ensures that the network constraints are satisfied during the restoration operation.

  DOI

• Coordinated operation of pumped-storage hydropower with power and water distribution systems

  International Journal of Electrical Power & Energy Systems · 2022 · 29 citations

  • Computer Science
  • Engineering
  • Automotive engineering
  DOI

• Integrated water-power system resiliency quantification, challenge and opportunity

  Energy Strategy Reviews · 2021 · 23 citations

  • Computer Science
  • Risk analysis (engineering)
  • Computer Science

  Resiliency has been studied in the power and water systems separately. Often the resiliency study is not so comprehensive as to understand interdependent, integrated water and power systems. This research outlines the relevant factors necessary to understand and advance quantification of such integrated systems. It also presents a review of integrated water-power systems resiliency. Based on literature survey and identification of challenges, the authors present quantification and computational steps needed to understand integrated water-power systems resiliency. A conceptual framework is proposed to quantify integrated water-power system resiliency. Finally, the authors presented an opportunity for improved water and power system resilience.

  DOI

• UWHear

  2020 · 57 citations

  • Computer Science
  • Computer Science
  • Acoustics

  An ability to detect, classify, and locate complex acoustic events can be a powerful tool to help smart systems build context-awareness, e.g., to make rich inferences about human behaviors in physical spaces. Conventional methods to measure acoustic signals employ microphones as sensors. As signals from multiple acoustic sources are blended during propagation to a sensor, such methods impose a dual challenge of separating the signal for an acoustic event from background noise and from other acoustic events of interest. Recent research has proposed using radio-frequency (RF) signals, e.g., Wi-Fi and millimeter-wave (mmWave), to sense sound directly from source vibrations. Whereas these works allow separating an acoustic event from background noise, they cannot monitor multiple sound sources simultaneously. In this paper, we present UWHear, a system that simultaneously recovers and separates sounds from multiple sources. Unlike previous works using continuous-wave RF, UWHear employs Impulse Radio Ultra-Wideband (IR-UWB) technology, in order to construct an enhanced audio sensing system tackling the above challenges. Further, IR-UWB radios can penetrate light building materials, which enables UWHear to operate in some non-line-of-sight (NLOS) conditions. In addition to providing a theoretical guarantee for audio recovery using RF pulses, we also implement an audio sensing prototype exploiting a commercial-off-the-shelf IR-UWB radar. Our experiments show that UWHear can effectively separate the content of two speakers that are placed only 25cm apart. UWHear can also capture and separate multiple sounds and vibrations of household appliances while being immune to non-target noise coming from other directions.

  DOI

• How Can I Explain This to You? An Empirical Study of Deep Neural Network Explanation Methods

  Neural Information Processing Systems · 2020 · 96 citations

  • Computer Science
  • Computer Science
  • Artificial Intelligence

Frequent coauthors

• Masood Parvania

  University of Utah

  11 shared

• Sandra Pérez‐Londoño

  Technological University of Pereira

  10 shared

• Juan José Mora Flórez

  9 shared

• Majid Majidi

  University of Utah

  5 shared

• Thomas Mosier

  Idaho National Laboratory

  4 shared

• Mohammad Mehdi Hosseini

  University of Utah

  3 shared

• Leonardo F. Lozano-Valencia

  Technological University of Pereira

  2 shared

• Dídier Giraldo-Buitrago

  Technological University of Pereira

  2 shared

Education

• Ph.D. in Electrical and Computer Engineering, Electrical and Computer Engineering

  University of Utah

  2023

Similar researchers at University of Utah

• Teruo Okanoh-160
• Mario Capecchih-134
• Gerald J. Gleichh-119
• Michael Allen Pulsipherh-110
• Alfred K. Cheungh-106