About

Alexander Ihler is a Professor in the Department of Computer Science at the University of California, Irvine. He received his Ph.D. in Electrical Engineering and Computer Science from MIT in 2005 and holds a B.S. with honors from Caltech, earned in 1998. His research focuses on machine learning, graphical models, and algorithms for both exact and approximate inference. His work has applications in sensor networks, computer vision, data mining, and computational biology. Professor Ihler has been recognized with an NSF CAREER award and has received several best paper awards at conferences including NIPS, IPSN, and AISTATS.

Research topics

• Computer Science
• Artificial Intelligence
• Computer network
• Machine Learning
• Data Mining
• Distributed computing
• Transport engineering
• Engineering

Selected publications

• A Hybrid Reactive Routing Protocol for Decentralized UAV Networks

  IEEE Transactions on Aerospace and Electronic Systems · 2025-05-14 · 2 citations

  article

  Wireless networks consisting of low SWaP (size, weight, and power), fixed-wing UAVs (unmanned aerial vehicles) are used in many applications, such as monitoring, search, and surveillance of inaccessible areas. A decentralized and autonomous approach ensures robustness to failures; the UAVs explore and sense within the area and forward their information, in a multihop manner, to nearby aerial gateway nodes. However, the unpredictable nature of the events, relatively high speed of the UAVs and dynamic trajectories cause the network topology to change significantly over time, resulting in frequent route breaks. A holistic routing approach is needed to support multiple traffic flows in these networks to provide mobility- and congestion-aware, high-quality routes when needed, with low control and computational overhead, using the information collected in a distributed manner. Existing routing schemes do not address all the mentioned issues. This paper presents a hybrid reactive routing protocol for decentralized UAV networks called Hyd-AODV. It searches routes on-demand (using a multi-metric route selection), monitors a region around the selected route (the “pipe”), and proactively switches to an alternative route before the current route's quality degrades below a threshold. The impact of pipe width is empirically and theoretically evaluated to find alternate high-quality routes within the pipe and the overhead required to maintain the pipe. A queue management scheme is also incorporated to prioritize packet transmissions based on their age of information (AoI). Compared to existing reactive routing schemes, the proposed approach achieves higher throughput and reduces the number of route discoveries, overhead, and resulting flow interruptions at different traffic loads, node density, and speeds. Despite having limited network topology information and low overhead and route computation complexity, the proposed scheme achieves a superior throughput to proactive optimized link state routing (OLSR) scheme for different network and traffic settings. The relative performance of reactive and proactive routing schemes is also studied.

  PublisherDOI

• Pipe Routing with Topology Control for Decentralized and Autonomous UAV Networks

  Drones · 2025-02-13 · 2 citations

  articleOpen access

  This paper considers a decentralized and autonomous wireless network of low SWaP (size, weight, and power) fixed-wing UAVs (unmanned aerial vehicles) used for remote exploration and monitoring of targets in an inaccessible area lacking communication infrastructure. Here, the UAVs collaborate to find target(s) and use routing protocols to forward the sensed data of target(s) to an aerial base station (BS) in real-time through multihop communication, which can then transmit the data to a control center. However, the unpredictability of target locations and the highly dynamic nature of autonomous, decentralized UAV networks result in frequent route breaks or traffic disruptions. Traditional routing schemes cannot quickly adapt to dynamic UAV networks and can incur large control overhead and delays. In addition, their performance suffers from poor network connectivity in sparse networks with multiple objectives (exploration and monitoring of targets), which results in frequent route unavailability. To address these challenges, we propose two routing schemes: Pipe routing and TC-Pipe routing. Pipe routing is a mobility-, congestion-, and energy-aware scheme that discovers routes to the BS on-demand and proactively switches to alternate high-quality routes within a limited region around the routes (referred to as the “pipe”) when needed. TC-Pipe routing extends this approach by incorporating a decentralized topology control mechanism to help maintain robust connectivity in the pipe region around the routes, resulting in improved route stability and availability. The proposed schemes adopt a novel approach by integrating the topology control with routing protocol and mobility model, and rely only on local information in a distributed manner. Comprehensive evaluations under diverse network and traffic conditions—including UAV density and speed, number of targets, and fault tolerance—show that the proposed schemes improve throughput by reducing flow interruptions and packet drops caused by mobility, congestion, and node failures. At the same time, the impact on coverage performance (measured in terms of coverage and coverage fairness) is minimal, even with multiple targets. Additionally, the performance of both schemes degrades gracefully as the percentage of UAV failures in the network increases. Compared to schemes that use dedicated UAVs as relay nodes to establish a route to the BS when the UAV density is low, Pipe and TC-Pipe routing offer better coverage and connectivity trade-offs, with the TC-Pipe providing the best trade-off.

  PublisherOA PDFDOI

• Pipe Routing with Topology Control for UAV Networks

  arXiv (Cornell University) · 2024-05-07 · 1 citations

  preprintOpen access

  Routing protocols help in transmitting the sensed data from UAVs monitoring the targets (called target UAVs) to the BS. However, the highly dynamic nature of an autonomous, decentralized UAV network leads to frequent route breaks or traffic disruptions. Traditional routing schemes cannot quickly adapt to dynamic UAV networks and/or incur large control overhead and delays. To establish stable, high-quality routes from target UAVs to the BS, we design a hybrid reactive routing scheme called pipe routing that is mobility, congestion, and energy-aware. The pipe routing scheme discovers routes on-demand and proactively switches to alternate high-quality routes within a limited region around the active routes (called the pipe) when needed, reducing the number of route breaks and increasing data throughput. We then design a novel topology control-based pipe routing scheme to maintain robust connectivity in the pipe region around the active routes, leading to improved route stability and increased throughput with minimal impact on the coverage performance of the UAV network.

  PublisherOA PDFDOI

• Graph-based Complexity for Causal Effect by Empirical Plug-in

  arXiv (Cornell University) · 2024-11-15

  preprintOpen access

  This paper focuses on the computational complexity of computing empirical plug-in estimates for causal effect queries. Given a causal graph and observational data, any identifiable causal query can be estimated from an expression over the observed variables, called the estimand. The estimand can then be evaluated by plugging in probabilities computed empirically from data. In contrast to conventional wisdom, which assumes that high dimensional probabilistic functions will lead to exponential evaluation time of the estimand. We show that computation can be done efficiently, potentially in time linear in the data size, depending on the estimand's hypergraph. In particular, we show that both the treewidth and hypertree width of the estimand's structure bound the evaluation complexity of the plug-in estimands, analogous to their role in the complexity of probabilistic inference in graphical models. Often, the hypertree width provides a more effective bound, since the empirical distributions are sparse.

  PublisherOA PDFDOI

• Estimating Causal Effects from Learned Causal Networks

  Frontiers in artificial intelligence and applications · 2024-10-16

  book-chapterOpen access

  The standard approach to answering an identifiable causal-effect query (e.g., P(Y|do(X)) given a causal diagram and observational data is to first generate an estimand, or probabilistic expression over the observable variables, which is then evaluated using the observational data. In this paper, we propose an alternative paradigm for answering causal-effect queries over discrete observable variables. We propose to instead learn the causal Bayesian network and its confounding latent variables directly from the observational data. Then, efficient probabilistic graphical model (PGM) algorithms can be applied to the learned model to answer queries. Perhaps surprisingly, we show that this model completion learning approach can be more effective than estimand approaches, particularly for larger models in which the estimand expressions become computationally difficult. We illustrate our method’s potential using a benchmark collection of Bayesian networks and synthetically generated causal models.

  PublisherDOI

• A Deep-$Q$-Learning-Based Base-Station-Connectivity-Aware Decentralized Pheromone Mobility Model for Autonomous UAV Networks

  IEEE Transactions on Aerospace and Electronic Systems · 2024-07-29 · 6 citations

  article

  Wireless networks consisting of low size, weight, and power, fixed-wing unmanned aerial vehicles (UAVs) are used in many applications, such as search, monitoring, and information gathering of inaccessible areas, in which UAVs sense within an area and forward the information, in a multihop manner, to an aerial base station (BS). Robustly performing these tasks requires the UAV network to be decentralized, autonomous, and scalable. An important tradeoff is between area coverage and connectivity: fast area coverage is needed to quickly identify objects of interest, while connectivity must be maintained for coordination and to transmit sensed information to the BS in real time. These factors must be balanced by the mobility model, which for each UAV has access only to locally available information. While Adam (2019, 2020) attempts to balance these factors using flocking behavior, this only encourages the UAVs to spread, rather than using knowledge of what areas have already been covered. In this article, we develop a neighborhood- and BS-connectivity-aware distributed pheromone mobility model to autonomously coordinate the UAV movements in a decentralized network. By using a pheromone map, we directly incorporate recent coverage information for the area. We then extend our approach to a deep $Q$-learning policy variant to further tune and improve the balance between coverage and connectivity. These mobility models are fully distributed and rely only on information from neighboring UAVs. Our simulations demonstrate that both the models achieve efficient area coverage and improved connectivity (both locally and to the BS), providing significant improvements over existing approaches.

  PublisherDOI

• A Hybrid Reactive Routing Protocol for Decentralized UAV Networks

  arXiv (Cornell University) · 2024-07-03

  preprintOpen access

  Wireless networks consisting of low SWaP, FW-UAVs are used in many applications, such as monitoring, search and surveillance of inaccessible areas. A decentralized and autonomous approach ensures robustness to failures; the UAVs explore and sense within the area and forward their information, in a multihop manner, to nearby aerial gateway nodes. However, the unpredictable nature of the events, relatively high speed of UAVs, and dynamic UAV trajectories cause the network topology to change significantly over time, resulting in frequent route breaks. A holistic routing approach is needed to support multiple traffic flows in these networks to provide mobility- and congestion-aware, high-quality routes when needed, with low control and computational overheads, using the information collected in a distributed manner. Existing routing schemes do not address all the mentioned issues. We present a hybrid reactive routing protocol for decentralized UAV networks. Our scheme searches routes on-demand, monitors a region around the selected route (the pipe), and proactively switches to an alternative route before the current route's quality degrades below a threshold. We empirically evaluate the impact of pipe width and node density on our ability to find alternate high-quality routes within the pipe and the overhead required to maintain the pipe. Compared to existing reactive routing schemes, our approach achieves higher throughput and reduces the number of route discoveries, overhead, and resulting flow interruptions at different traffic loads, node densities and speeds. Despite having limited network topology information, and low overhead and route computation complexity, our proposed scheme achieves superior throughput to proactive optimized link state routing scheme at different network and traffic settings. We also evaluate the relative performance of reactive and proactive routing schemes.

  PublisherOA PDFDOI

• Estimating Causal Effects from Learned Causal Networks

  arXiv (Cornell University) · 2024-08-26

  preprintOpen access

  The standard approach to answering an identifiable causal-effect query (e.g., $P(Y|do(X)$) when given a causal diagram and observational data is to first generate an estimand, or probabilistic expression over the observable variables, which is then evaluated using the observational data. In this paper, we propose an alternative paradigm for answering causal-effect queries over discrete observable variables. We propose to instead learn the causal Bayesian network and its confounding latent variables directly from the observational data. Then, efficient probabilistic graphical model (PGM) algorithms can be applied to the learned model to answer queries. Perhaps surprisingly, we show that this \emph{model completion} learning approach can be more effective than estimand approaches, particularly for larger models in which the estimand expressions become computationally difficult. We illustrate our method's potential using a benchmark collection of Bayesian networks and synthetically generated causal models.

  PublisherOA PDFDOI

• A Connectivity-Aware Pheromone Mobility Model for Autonomous UAV Networks

  2023 · 14 citations

  • Computer Science
  • Computer Science
  • Computer network

  UAV networks consisting of reduced size, weight, and power (low SWaP) fixed-wing UAVs are used for various applications such as search and rescue, surveillance, and tracking. To carry out these operations efficiently, there is a need to develop scalable, decentralized autonomous UAV network architectures with high network connectivity. However, the area coverage and the network connectivity requirements exhibit a trade-off. In this paper, a connectivity-aware pheromone mobility (CAP) model is designed for search and rescue operations, which is capable of maintaining connectivity among UAVs in the network. We use stigmergy-based digital pheromone maps along with distance-based local connectivity information to autonomously coordinate the UAV movements, in order to improve its map coverage efficiency while maintaining high network connectivity.

  PublisherDOI

• A Deep Q-Learning based, Base-Station Connectivity-Aware, Decentralized Pheromone Mobility Model for Autonomous UAV Networks

  arXiv (Cornell University) · 2023-11-28

  preprintOpen access

  UAV networks consisting of low SWaP (size, weight, and power), fixed-wing UAVs are used in many applications, including area monitoring, search and rescue, surveillance, and tracking. Performing these operations efficiently requires a scalable, decentralized, autonomous UAV network architecture with high network connectivity. Whereas fast area coverage is needed for quickly sensing the area, strong node degree and base station (BS) connectivity are needed for UAV control and coordination and for transmitting sensed information to the BS in real time. However, the area coverage and connectivity exhibit a fundamental trade-off: maintaining connectivity restricts the UAVs' ability to explore. In this paper, we first present a node degree and BS connectivity-aware distributed pheromone (BS-CAP) mobility model to autonomously coordinate the UAV movements in a decentralized UAV network. This model maintains a desired connectivity among 1-hop neighbors and to the BS while achieving fast area coverage. Next, we propose a deep Q-learning policy based BS-CAP model (BSCAP-DQN) to further tune and improve the coverage and connectivity trade-off. Since it is not practical to know the complete topology of such a network in real time, the proposed mobility models work online, are fully distributed, and rely on neighborhood information. Our simulations demonstrate that both proposed models achieve efficient area coverage and desired node degree and BS connectivity, improving significantly over existing schemes.

  PublisherOA PDFDOI

Recent grants

• CAREER: Estimation and Decisions in Graphical Models

  NSF · $442k · 2013–2019

Frequent coauthors

• Rina Dechter

  33 shared

• Alan S. Willsky

  23 shared

• John W. Fisher

  Massachusetts Institute of Technology

  22 shared

• Padhraic Smyth

  22 shared

• Radu Marinescu

  17 shared

• Junkyu Lee

  University of Essex

  14 shared

• Julian Yarkony

  10 shared

• Sunil Kumar

  10 shared

Education

• PhD, EECS

  Massachusetts Institute of Technology

  2005

• BS, EE & Mathematics

  California Institute of Technology

  1998

Awards & honors

• NSF CAREER Award