My research is broadly founded on exploring the interplay between control, data availability, and learning in order to design provably safe, successful, and efficient planning strategies for systems operating in complex or unknown environments. Inversely, I am interested in identifying control policies and agent intent from data, and communicating the findings to a human supervisor in an explainable manner. Some of my recent areas of interest are described below. If you want to learn more, please look at my recent publications or contact me.
Research Funding
My research is currently supported by the Air Force Young Investigator Program award with the Resilience and Guaranteed Task Completion for Partially Unknown Nonlinear Control Systems project, by the Office of Naval Research Young Investigator Program award with the Risk vs. Efficiency vs. Resources: AI-Assisted Planning for Expeditionary Tactical Operations in Denied Environments project, the Distributed Swarm Planning in Complex, Low-Communication Environments, Synthesizing Temporal Logic and Human Performance Models for Deception Mitigation and Long-Duration Autonomy via Optimal Resource-Aware Control Design projects funded by the Office of Naval Research, and the Fellowship Program for Educating and Training the Next Generation of Space Systems Engineers funded by the US Department of Education. I also recently learned that our project When Magic Goes Wrong: Identifying and Understanding Failures of Agentic AI Systems in Multi-Turn and Sequential Tasks has been selected for funding by the CapitalOne—Illinois Center on AI Safety and Knowledge Systems.
We concluded the Robust and Resilient Autonomy for Advanced Air Mobility, the DRILLAWAY: aDaptive, ResIllient Learning-enabLed oceAn World AutonomY and the Safety-Constrained and Efficient Learning for Resilient Autonomous Space Systems projects funded by NASA, the Optimal Infrastructure Assessment and Management Through Active Learning and Data-Driven Planning project funded by the United States Army Engineer Research and Development Center, the SCRIPTED-FM: Selective and Contractive Robotic Intelligence for Performant, Trustworthy, and Exploratory Decisions with Foundation Models and Seedling: Synthesis of Control Protocols for Integrated Mission Planning, Resource Management and Information Acquisition projects funded by DARPA, the System for Avoidance and Flight-path Execution based on Risk Reduction (SAFERR) project funded by the United States Air Force’s AFWERX program, the Learning of Time-Varying Dynamics project funded by Sandia National Laboratories, the Net Zero Transportation Infrastructure project funded by the Discovery Partners Institute, the Optimal Planning for Ag Systems funded by Corteva, the Enhancing Opportunities for Research and Training in Space Engineering project funded by the US Department of Education, and the intensive summer research project LEONA: Logic-Based Context-Aware Activity Interpreter for Geospatial Intelligence funded by the University of Illinois Urbana-Champaign’s New Frontiers Initiative, aligning with the mission and needs of the National Geospatial-Intelligence Agency.
Some Contributions
Certifiable Planning and Control for Systems with Unknown Dynamics
Faced with a mid-mission catastrophe or a significantly different environment from the one originally expected, it is often impossible for a system to complete its original task; hence, classical methods of adaptation and robustness — focused on adapting the system’s control capabilities to meet its original objective — will fail. My research develops methods that recognize whether the original task can be completed, choose an alternative task if it cannot, and ensure that the system completes the chosen task.
My group’s work introduced a guaranteed reachable set of a partially unknown system as the set of all states reachable for every system consistent with partial knowledge about new system dynamics. Underapproximating the guaranteed reachable set by exploiting the knowledge of the system’s reachable set prior to the adverse event and/or partial knowledge of the new system dynamics allows us to quickly determine tasks that the system can certifiably complete, even before we know how to complete them. After determining such a task, the remaining challenge is to perform online learning and adaptation to drive the system to succeed at its new mission.
In a scenario where the unknown dynamics are precipitated by partial failure or hostile takeover of actuators, the controller needs to adapt to undesirable actuator inputs in real time to keep the system progressing towards completing its task. The video below, made by a graduated LEADCAT member Jean-Baptiste Bouvier to illustrate joint work with Robyn Woollands‘ group at the University of Illinois, illustrates the resilience of a spacecraft to adversarial inputs in successful completion of an orbital inspection mission.
In a scenario of completely unknown dynamics, the system must continually relearn its interactions with the environment while determining a feasible path towards completing its long-term objective. The following video, made by LEADCAT member Zhiquan Zhang, shows a simulation of a wheeled robot operating on uncertain, varying terrain, controlled using a hybrid combination of high-level graph planning and low-level system identification through myopic control and predicted reachability.
Frugal Planning
Controlling a system in a partially unknown environment inevitably requires learning about the environment and the system’s interaction with it. Collecting the information needed to learn consumes both time and resources. My group’s work uses structural knowledge about the system’s sensing and actuation capabilities, as well as known information about the environment, to learn quicker and subsequently plan better.
Our work in this area spans across domains: a recent line of work seeks to use just enough sensing to complete a mission in a dynamic environment, understanding the heterogeneous utility and energy consumption of different sensors. The video below illustrates this collaborative work of LEADCAT members Gokul Puthumanaillam and Manav Vora with members of Jane Shin‘s group at the University of Florida and Leonardo Bobadilla‘s group at Florida International University. The video was produced by Florida International University members using the equipment and grounds of their campus.
Another effort focuses on the cost of communication between members in a large team. The animation below, made by Manav Vora and Gokul Puthumanaillam from LEADCAT in collaboration with and using resources of Hiroyasu Tsukamoto‘s group at the University of Illinois, illustrates a 100 vs. 100 battle of agent teams with limited communication between attacking team members.
Another effort focuses on fast planning for an extraterrestrial lander based on prior testing on Earth and real-time sensor data. The video below, made by LEADCAT’s member Pranay Thangeda in collaboration with and using the equipment of Kris Hauser‘s research group, illustrates our recent hardware experiment at learning to scoop in an extraterrestrial environment.
Behavior Inference, Supervision, and Deception
To ensure success in a hostile environment, an agent being observed may want to hide its true intentions from the observer for as long as possible. Inversely, an agent observing an adversary needs to infer its important behavioral features and uncover possible deception. My current work deals with both sides of this coin. On one hand, I have been exploring methods that agents can use to seem as unpredictable as possible while ultimately satisfying their objective or, alternatively, seem to follow a particular “decoy” policy as closely as possible while also proceeding to their objective. The resulting algorithms often match the human intuition of deceptive behaviors, and have been shown to successfully fool autonomous adversaries about the agent’s intention. The video below, produced in the Aerospace Engineering drone lab and illustrating the effort led by LEADCAT’s Gokul Puthumanaillam and Ram Padmanabhan in collaboration with seven other members of LEADCAT and Leonardo Bobadilla‘s group at Florida International University, describes a method of optimal deception through exploiting supervisor intermittent inattention.
Along with work on (counter)deceptive policies, we introduced the notion of counterdeceptive environment design, i.e., placement of environmental features in a way that makes it easy to uncover the adversary’s true intentions. Investigating optimal environment design spawns interesting optimization questions: motivated by a geometry-inspired simplification, our recent papers interpret the challenge as a classical p-dispersion optimization problem.