Chase Murray


Associate Professor
Industrial & Systems Engineering
University at Buffalo

E-mail: cmurray3@buffalo.edu
Phone:  (716) 645-4716
Office: 309 Bell Hall

Director of SOAR Drone Facility
Director of Optimator Lab

My research program leverages operations research and systems engineering to tackle real-world challenges through innovative applications of autonomous systems. As director of the Structure for Outdoor Autonomy Research (SOAR) — one of the nation’s most advanced enclosed drone test facilities — I lead cutting-edge work spanning drone routing algorithms, hardware design, and flight control systems. My work ranges from revolutionizing last-mile delivery logistics to developing military ISR capabilities, and even creating drone light shows. Most recently, my lab has pioneered an emerging research domain using AI to compare and classify mathematical optimization models. With nearly $7.3M in funded research from agencies including DARPA, ONR, AFOSR, and NSF, my lab is pushing the boundaries of what’s possible with drones and operations research. I’m also an FAA-certified drone pilot and faculty advisor to the UB Drone Club.

Recent test flights at UB’s SOAR drone test facility. Here, we are trying to launch/land drones on a ground rover. Photo: Douglas Levere

The Optimator Lab, housed in Bell Hall, features an immersive drone simulator. The lab serves as a remote command center for SOAR.

Student Research Opportunities (Spring 2026)

(more info coming soon)
  • Warehouse Inventory Tracking Drone

    In this project, two students will work to develop a drone-based system for tracking inventory inside a warehouse. In the first phase of the project (“Design”), one student will focus on hardware development (primarily the design of the drone), while the other student will focus on software development (primarly the algorithms for identifying products using the drone’s onboard cameras). Both students will need to coordinate their efforts to ensure that the system works properly. In the second phase, “Integration”, the students will work together to combine the hardware and software components and test the system inside our mock warehouse (the ISE manufacturing lab in 427 Bell). The system should be able to track barcode-marked items in the warehouse.

    The final deliverables include documentation of the system, a brief conference paper, and a video showing a demonstration of the video, which the students will be able to use to promote their work to future employers or graduate schools.

    Visit the UB ELN website for more information

  • Drone Light Show

    I will be looking for enthusiastic student volunteers to join the Drone Light Show team this spring.

  • Drone Data Collection

    Watch this space for details on an upcoming position related to data collection for machine learning research.

Featured Research Areas

Drone Light Shows

We have been at work for the past year designing 150+ drones for an upcoming drone light show. Watch this space for more info in spring 2026.

First light show drone prototypes.

Custom power distribution and LED board designed by one of our undergrad team members.

Drone Data Collection

We are amassing quite a collection of data on our drones. These data will be used to refine our simulation models, and are going towards our work on counter-UAS research.


A view of our workstation in SOAR, collecting some audio data on one of our drones.

My lab has a large and growing inventory of drones, ground rovers, and sensors.

Drones:
  • 2x DJI Avata 2
  • 1x DJI Mavic 4
  • 2x ModalAI s500
  • 1x ModalAI seeker
  • 4x 3DR Iris+ (heavily modified)
  • 1x Holybro x500
  • 1x Parrot Bebop 2
  • 1x Coex Clover
  • 2x prototype light show drones
  • 150x light show drones (by Q1 2026)
UGVs:
  • 1x Clearpath Husky
  • 5x racing cars
Sensors:
  • Weather Station
  • RTK-GPS base station and rovers
  • Software Defined Radios (Kraken, HackRF One, RTL-SDR)
  • Spectrum Analyzer
  • Analog Devices Phased Array Radar (CN0566)
  • Microphones
  • SiK Lidar
  • Cameras
    • FLIR BOSON 320, OpenMV Event Camera, OpenMV Global Shutter, Stereo Cameras, Intel RealSense Depth Camera
    Prototyping Hardware:
    • Prusa XL 3D Printer
    • CNC router

    A small collection of our drones and rovers, collecting data under the sunshade at SOAR.

    A Graph-Based Approach for Relating Integer Programs:

    Pleased to announce a recent paper in INFORMS Journal on Computing with co-authors Zachary Steever, Kyle Hunt, Mark Karwan, and Junsong Yuan.

    Abstract. This paper presents a framework for classifying and comparing instances of integer linear programs (ILPs) based on their mathematical structure. It has long been observed that the structure of ILPs can play an important role in determining the effectiveness of certain solution techniques; those that work well for one class of ILPs are often found to be effective in solving similarly structured problems. In this work, the structure of a given ILP instance is captured via a graph-based representation, where decision variables and constraints are described by nodes, and edges denote the presence of decision variables in certain constraints. Using machine learning techniques for graph-structured data, we introduce two approaches for leveraging the graph representations for relating ILPs. In the first approach, a graph convolutional network (GCN) is used to classify ILP graphs as having come from one of a known number of problem classes. The second approach makes use of latent features learned by the GCN to compare ILP graphs to one another directly. As part of the latter approach, we introduce a formal measure of graph-based structural similarity. A series of empirical studies indicate strong performance for both the classification and comparison procedures. Additional properties of ILP graphs, namely, losslessness and permutation invariance, are also explored via computational experiments.

    bin packing problem with item fragmentation
    capacitated vehicle routing problem
    lot sizing problem
    generalized assignment problem

    Integer linear programming graphs for instances from four different problem classes. These instances were downloaded from strIPlib. Graph visualizations were generated using the Python package networkx. The paper shows how these graphs of integer programs can be used to compare/relate different problem formulations.

    Swarm Simulation Demo

    The clip below shows a small-scale drone swarm simulation. My research lab is working on the software to plan and execute swarm operations.

    Drone Ground Control Station

    The gallery below shows some screenshots of our ground control station.

    Simulated trailer and real photo
    Front gates
    Mission and weather forecast
    Chat and mission planning
    Simulated video feed
    Looking thru the trees

    Key Features:

    • Supports a mix of real and virtual (simulated) vehicles, including drones and UGVs.
    • Provides voice-activated functionality for controlling drones (“move forward 2 meters”) and for obtaining information about the system (“what’s 107’s altitude?”) and surroundings (“what’s the weather?”).
    • Includes a detailed 3D digital twin of the SOAR drone testing facility
    • Supports PX4 calibration.
    • Includes a photo/video gallery
    • Camera controls for aruco tags
    • Supports multiple users and text- or voice-based “chat”
    • Integration with social media accounts
    • 3D mission planning and geofencing capabilities
    • Generates 3D maps of WiFi signal strength
    • Import 3D models to test, for example, infrastructure inspection operations

    Web-based Robot Control

    The open-source ub_web repository contains code for a ROS-enabled webpage. This isn’t nearly as feature-rich as the ground control station; it’s designed to provide some starter code to highlight these types of interactivity:

    • “Touchpad” controls on mobile devices. These can be used, for example, to control drones.
    • “Direction Pad” controls (on mobile and desktop). These are discrete buttons, like “move forward” or “stop”.
    • Support for gamepads (like XBox or PS5 controllers). Connect your gamepad to your phone/computer and press a button. The gamepad should be instantly recognized.
    • Support for speech-to-text via the Whisper API. This has been successfully tested on Android and Ubuntu devices. It fails to work on Mac/iOS devices. I don’t use Windows.
    • Video streams from ROS compressed image topics, or mjpg streams.
    • A “console” to display messages. The system can be run on a network with multiple users in “chat” mode.

    VeRoViz Vehicle Routing Visualization

    This open-source software package, for Python and with web-based components, is designed to help vehicle routing researchers easily create test problems, generate time and distance matrices, and visualize solutions with dynamic 3D movies. Visit veroviz.org for installation instructions, documentation, and examples.

    tex2solver

    tex2solver makes it easy to transfer LaTeX-typeset optimization models to programming code for use in a solver. Simply copy-and-paste your LaTeX code (or take a screenshot of your model), then choose your desired solver and programming language. tex2solver will generate the code you need to be able to solve instances of your model. With tex2solver, it’s easy to keep your math model and solver code in sync.

    Visit tex2solver.com to get started for free.

    Featured Research Area: Drone Delivery

    My lab has been working on drone-assisted last-mile delivery for over a decade, starting with The Flying Sidekick Traveling Salesman Problem (2015). Co-author Amanda Chu and I proposed two new extensions to the traveling salesman problem (TSP). The resulting problems pair traditional delivery trucks with unmanned aerial vehicles (UAVs, also known as drones).

    mFSTSP – In 2020, the “multiple flying sidekicks traveling salesman problem” was published in Transportation Research Part C. This paper features models and algorithms for problems involving a single delivery truck an multiple delivery drones.

    mFSTSP with Variable Drone Speeds – Fly Slower to Reduce Drone Delivery Times? Another 2020 paper with Ritwik Raj revealed that flying drones at slower speeds can actually lead to a significant reduction in overall delivery times.

    Truck/Drone deliveries with road traffic – The 3rd paper from Ritwik Raj’s Ph.D. dissertation involved “The Time-Dependent Multiple Flying Sidekicks Traveling Salesman Problem”. Dr. Raj’s research examines the impacts of road network congestion in a last-mile delivery system consisting of a truck and multiple drones. Existing literature in this area assumes that the truck travel time between two nodes is fixed. However, this assumption may be dangerous considering that unmanned aerial vehicles (UAVs, or drones) have limited endurance, as congestion may delay the truck’s arrival at retrieval locations, potentially causing crashes. This work introduces the time-dependent multiple flying sidekicks traveling salesman problem, in which truck travel times on each road segment may vary throughout the day. A mixed integer linear programing formulation is provided for small-scale problems, while an ant-pair colony system heuristic is proposed for problems of realistic scale. Results indicate significant improvement in terms of feasibility and time savings over the case in which schedules are generated by neglecting congestion. Furthermore, the analysis demonstrates the ability of the proposed model to increase the utilization of UAVs and smaller roads during high congestion to minimize overall delivery time.

    Drone Scheduling with Weather Considerations – The first paper from Dr. Lan Peng’s dissertation, entitled “Parallel Drone Scheduling Traveling Salesman Problem with Weather Impacts” provides a model for scheduling drone and truck operations when inclement weather (e.g., rain, wind, low visibility) restricts flights. A mixed integer linear programming formulation is presented, as well as an efficient heuristic for solving problems of practical size.