People, Innovation, Excellence

Research Goal

Utilize the Theory-Computation-Experiment paradigm to research Low Cost Attritable Aircraft Technology (LCAAT) with autonomy to establish trust, providing a game changing capability that transforms the way manned and unmanned air, space, and ground systems are designed, controlled, and operated to effectively accomplish missions and tasks. VSCL is thus focused on synergistic strategies for the analysis, control, validation & verification of complex autonomous vehicle and sensor systems operating in challenging environments.

The Vehicle Systems & Control Laboratory is directed by Dr. John Valasek.

Graduate Research Assistant Positions Available

The Vehicle Systems & Control Laboratory (VSCL) has multiple fully funded Ph.D. positions in Aerospace Engineering that are available in Spring 2022, focused on the following areas:

Human-in-the-Loop Artificial Intelligence, which includes integrating multiple human interaction modalities to learning algorithms such as reinforcement learning; learning from human demonstrations, interventions and/or evaluations; unsupervised and/or weakly supervised segmentation of task demonstrations; human-agent teaming and task hierarchy discovery on multi-agent scenarios; and others.

Machine Learning and Artificial Intelligence for Coordinated Autonomous Unmanned Air Systems (UAS), which includes learning algorithms such as deep reinforcement learning; policy optimization and policy gradient methods; target tracking from computer vision; multi-agent teaming; human-agent teaming, task hierarchy on multi-agent scenarios; and others.

U.S. citizenship is required for some positions, but not all of them.

More information and details for applying can be found here.

UAS Research and Flight Testing by the Numbers

  • 21 Years of Fixed-Wing UAS Flight Testing under FAA Auspices
  • 26 Externally Funded UAS Research Programs (1999 – Present)
  • 400+ Flights with an operational tempo of 133 thermal IR and multi-spectral data collection flights in the field over 12 months (2015 – 2016)
  • 24 Certified UAS Flight Testers Currently on Staff
  • 3 Certified UAS Pilots Currently on Staff
  • 13 UAS Vehicles in Current Fleet

Research Project Spotlight

Project: System Identification for Unmanned Air Systems

Sponsor: National Science Foundation (NSF) Center for Autonomous Air Mobility & Sensing (CAAMS)

Purpose: System Identification is a process to develop a mathematical representation of the dynamics of a physical system from measured data. Accurate models enable prediction of performance and dynamics of a system.

Challenges: Models for sUAS are generally not available as manufacturers do not have models for commercial sUAS and models for military sUAS are not typically available. Modeling and control systems are often vehicle dependent and not easily portable across sUAS. Many commercial autopilots do not provide data needed for online system identification

Our Approach: Utilizing the Observer Kalman Filter Identification algorithm with the Developmental Flight Test Instrumentation 2 framework, full state space models can be identified in near-real time onboard the vehicle utilizing data from a variety of sensors.

Recent News

McQuinn Awarded the J. Malon Southerland ’65 Leadership Scholarship

Posted on by

VSCL graduate student Cassie-Kay McQuinn is the recipient of the J. Malon Southerland Aggie Leader Scholarship. The J. Malon Southerland Aggie Leader Scholarship program was created to recognize and reward students involvement at Texas A&M University. The scholarship was named in honor of J. Malon Southerland, former TAMU Vice President for Student Affairs. While a student at Texas A&M Cassie-Kay has been involved in leadership through membership of the Student Engineers’ Council (SEC), completion of the Zachry Leadership Program (ZLP), and has been Vice President then President of the Texas A&M chapter of Sigma Gamma Tau (SGT) the National Honor Society for Aerospace Engineering.

Cassie-Kay McQuinn Defends Masters Thesis

Posted on by

Cassie-Kay McQuinn (B.S. Aerospace Engineering, TAMU) successfully defended her Masters thesis titled “Online Near-Real Time Open-Loop System Identification from Closed-Loop Flight Test Data“.

Cassie-Kay’s thesis investigated identifying linear dynamic models onboard a vehicle in near-real time with and without an active controller. This is performed for a small Unmanned Air System (UAS) utilizing low cost, commercial-off-the-shelf components. Bare airframe longitudinal, lateral/directional and combined longitudinal lateral/directional models of the test vehicle are generated both onboard the vehicle during flight and offline during post-processing. The Developmental Flight Test Instrumentation 2 (DFTI2), utilizing the Robot Operating System (ROS), is extended to compute system models onboard the vehicle from both open-loop and closed-loop data. Additionally, a controller is implemented into the system, external to the primary flight controller, to generate and record controller inputs for the closed-loop system. The Observer/Kalman filter Identification (OKID) algorithm is used to generate locally linear models of the flight vehicle. Models are generated independent of actuator dynamics by mapping deflection angle to measured servo potentiometer readings. Orthogonal Schroeder sine sweep excitations are utilized to reduce potential control coupling while also exciting multiple frequencies. Identified models are presented and evaluated. Offline analysis of closed-loop flight data provides insight into the controller utilized in flight. Results presented in the thesis show the extended system can generate models suitable for describing the dynamics of the vehicle operating both with and without a controller implemented.

This work is sponsored by the National Science Foundation (NSF)  Center for Autonomous Air Mobility and Sensing (CAAMS). Conference and journal papers are being written on this work. Cassie-Kay’s is the 60th graduate degree earned by a VSCL graduate student.

Krpec and Valasek Publish “Vision-based Marker-less Landing of a UAS on Moving Ground Vehicle” in Journal of Aerospace Information Systems

Posted on by

VSCL Alumni Blake Krpec, Dr. John Valasek, and Dr. Stephen Nogar with the DEVCOM Army Research Lab published the paper “Vision-based Marker-less Landing of a UAS on Moving Ground Vehicle” in Journal of Aerospace Information Systems.

Current autonomous unmanned aerial systems (UAS) commonly use vision-based landing solutions that depend upon fiducial markers to localize a static or mobile landing target relative to the UAS. This paper develops and demonstrates an alternative method to fiducial markers with a combination of neural network-based object detection and camera intrinsic properties to localize an unmanned ground vehicle (UGV) and enable autonomous landing. Implementing this visual approach is challenging given the limited compute power on board the UAS, but is relevant for autonomous landings on targets for which affixing a fiducial marker a priori is not possible, or not practical. The position estimate of the UGV is used to formulate a landing trajectory that is then input to the flight controller. Algorithms are tailored towards low size, weight, and power constraints as all compute and sensing components weigh less than 100 g. Landings were successfully demonstrated in both simulation and experimentally on a UGV traveling in both a straight line and while turning. Simulation landings were successful at UGV speeds of up to 3.0 m/s, and experimental landings at speeds up to 1.0 m/s.

 

VSCL Hosts Texas Department of Transportation (TxDOT) and Texas A&M Transportation Institute (TTI)

Posted on by

VSCL hosts Texas Department of Transportation (TxDOT) and Texas A&M Transportation Institute (TTI) at the Texas A&M University UAS Flight Testing Facility at RELLIS Campus to discuss recent advances in UAS for infrastructure assessment. TxDOT members met with VSCL lab director Dr. Valasek and VSCL graduate students Jillian Bennett, Payton Clem, Hannah Lehman, Noah Luna, Cassie-Kay McQuinn, and Erin Swansen about the UAS research that VSCL conducts at the flight testing facility and toured the grounds.

McQuinn presents at IEEE Aerospace Conference in Big Sky, Montana

Posted on by

VSCL graduate student Cassie-Kay McQuinn presented “Run Time Assurance for Simultaneous Constraint Satisfaction During Spacecraft Attitude Maneuvering” at the 2024 IEEE Aerospace Conference this month. This work was completed as part of her internship with AFRL in summer 2023.

A fundamental capability for On-orbit Servicing, Assembly, and Manufacturing (OSAM) is inspection of the vehicle to be serviced, or the structure being assembled. The focus of this research is developing Active-Set Invariance Filtering (ASIF) Run Time Assurance (RTA) filters that monitor system behavior and the output of the primary controller to enforce attitude requirements pertinent for autonomous space operations. Slack variables are introduced into the ASIF controller to prioritize safety constraints when a solution to all safety constraints is infeasible. Monte Carlo simulation results as well as plots of example cases are shown and evaluated for a three degree of freedom spacecraft with reaction wheel attitude control. A preprint of the paper is available at: https://arxiv.org/abs/2402.14723

Bennett Receives Graduate Excellence Fellowship Award

Posted on by

 

VSCL Graduate Assistant Researcher, Jillian Bennett, is a recipient of the Graduate Excellence Fellowship Award for Spring 2024. This is a competitive, merit-based fellowship awarded to students by the Aerospace Engineering Graduate Committee. The fellowship includes a $1,000 supplemental award for Spring 2024.

Jillian is a Master of Science student, with a focus in Dynamics & Control. She is currently on the KAMS project, working on adaptive control for multiple time scale systems. She has been in the VSCL since Spring 2023, previously working on flight testing for the System Identification project. Jillian has an interest in flight testing, nonlinear control, and vehicle dynamics.

Two New Graduate Students Join VSCL in Spring 2024

Posted on by

VSCL is proud to welcome two new graduate research assistants:

Erin Swansen joins VSCL as a Ph.D. transfer student in the Aerospace Engineering department. Erin has over five years of experience in industry at Boeing as a guidance, navigation, and control engineer in the Advanced Autonomous Systems group. Her work involved guidance and control system development for a variety of aerial platforms including UAVs, high performance aircraft, and guided weapons. During graduate school, she has interned at NASA and Sandia National Laboratories doing flight control research and development. Her professional and research background includes significant work using robust and adaptive control to address challenges in flight, particularly for hypersonic vehicles. She has also conducted research sponsored by Sandia National Laboratories to develop a new methodology to improve performance of machine learning algorithms for sparse data sets. Her current research interests focus on implementable and verifiable algorithms that allow the safe use of machine learning in guidance and control architectures. Erin earned a B.S. in Systems Science and Engineering and an M.S. in Electrical Engineering from Washington University in St. Louis. With VSCL, Erin will be contributing towards the Center for Autonomous Air Mobility and Sensing (CAAMS) which is sponsored by the National Science Foundation (NSF).

 

Payton Clem is a Master of Science Student in the Aerospace Engineering department. She is graduating from Texas A&M with her Bachelor of Science in Aerospace Engineering with Minors in Mathematics and Astrophysics in Fall 2023. During her undergrad, she was involved in campus activities like working at the Memorial Student Center to provide support to her fellow Aggies, and was a member of P.S.U.N., an on campus organization that provides free programs and events to children with special needs. Finding an interest in research, she worked in Dr. Daniel Selva’s lab, SEAK, on a NASA SBIR project with Aureus Innovation to develop a new systems engineering language. This involved creating a satellite design from scratch using systems engineering diagrams with the SIMPL developing language. Within the SEAK lab she also assisted in developing a rule based planner that would be used in a space mission simulation for space mission design. She was also the project lead of her capstone design group, which provided a satellite constellation design, as well as mission planning software to aid in the solution of an on-orbit servicing problem for L3Harris. As she continued her research, Payton developed an interest into the applications of artificial intelligence within the aerospace engineering field. Payton became a member of VSCL in her senior year, applying her interest in AI by working on the Robust Threat Detection project, research she will continue during her Masters. Her work with VSCL will be primarily focused on Autonomous, Nonlinear Control of Air, Space and Ground Systems.

Lehman and Valasek Publish “Design, Selection, Evaluation of Reinforcement Learning Single Agents for Ground Target Tracking,” in Journal of Aerospace Information Systems

Posted on by

Ph.D. student Hannah Lehman and Dr. John Valasek of VSCL published the paper “Design, Selection, Evaluation of Reinforcement Learning Single Agents for Ground Target Tracking,” in Journal of Aerospace Information Systems.  

Previous approaches for small fixed-wing unmanned air systems that carry strapdown rather than gimbaled cameras achieved satisfactory ground object tracking performance using both standard and deep reinforcement learning algorithms. However, these approaches have significant restrictions and abstractions to the dynamics of the vehicle such as constant airspeed and constant altitude because the number of states and actions were necessarily limited.  Thus extensive tuning was required to obtain good tracking performance. The expansion from four state-action degrees-of-freedom to 15 enabled the agent to exploit previous reward functions which produced novel, yet undesirable emergent behavior. This paper investigates the causes of, and various potential solutions to, undesirable emergent behavior in the ground target tracking problem. A combination of changes to the environment, reward structure, action space simplification, command rate, and controller implementation provide insight into obtaining stable tracking results. Consideration is given to reward structure selection to mitigate undesirable emergent behavior. Results presented in the paper are on a simulated environment of a single unmanned air system tracking a randomly moving single ground object and show that a soft actor-critic algorithm can produce feasible tracking trajectories without limiting the state-space and action-space provided the environment is properly posed.

This publication is part of VSCL’s ongoing work in the area of Reinforcement Learning and Control.  The early access version of the article can be viewed at https://arc.aiaa.org/journal/jais

VSCL Alumnus Ryan Weisman Awarded Technical Fellow of KBR

Posted on by

VSCL alumnus Dr. Ryan Weisman ’12 has been inducted as a 2023 Fellow of KBR for his contributions in space situational awareness. Space superiority requires decision-making in ambiguous situations characterized by short timelines, reduced sensing, and conflicting information. Dr. Ryan Weisman’s work increases military space mission resilience to adversary parity, mission anomalies, and unforeseen situations by identifying and enabling operations under less explored, physically possible conditions beyond conventional, probable operating regimes. His operational tools provide warfighters proactive sensing recommendations, situation assessment, and solution confidence directly traceable to physics and data quality for navigation and vehicle safety without excessive data collection or exhaustive simulation.

Co-advised by Dr. John Valasek and Dr. Kyle T. Alfriend, Weisman was a recipient of the Science, Mathematics & Research for Transformation Fellowship (SMART) with the Air Force Research Laboratory, Albuquerque, NM, for which he was employed before joining KBR. KBR delivers science, technology and engineering solutions to governments and companies around the world

Texas A&M University Becomes Founding Partner of New NSF Center for Autonomous Air Mobility and Sensing

Posted on by

Texas A&M University is a founding partner of the National Science Foundation (NSF) Center for Autonomous Air Mobility and Sensing (CAAMS) along withUniversity of Colorado Boulder (CU), Brigham Young University (BYU), University of Michigan (UM), Penn State University (PSU), and Virginia Tech (VT). The center is organized under the NSF’s Industry-University Cooperative Research Centers program (IUCRC). CAAMS consists of three primary partners: academia, industry, and government. Academic faculty collaborate with industry and government members to promote long-term global competitive research and innovation. They create solutions to the most critical challenges faced in the autonomous industry. Dr. John Valasek serves as the Site Director for Texas A&M University. Texas A&M University faculty associated with CAAMS include: Dr. Moble Benedict, Dr. Manoranjan Majji, Dr. Sivakumar Rathinem, and Dr. Swaroop Darbha.

In conjunction with the CASS Lab at Penn State, directed by Dr. Puneet Singla, VSCL will be working on the project Integration of System Theory with Machine Learning Tools for Data Driven System Identification.  This project integrates system theory with machine learning tools for data driven system identification. The objective is to derive nonlinear dynamical models by employing a unique handshake between linear time varying subspace methods and sparse approximation tools from high fidelity flight simulations and flight experiments.