George J. Pappas UPenn Pappas
Current Projects    |    Former Projects  


Distributed and Collaborative Intelligent Systems and Technology (ARL CRA DCIST)


The Distributed and Collaborative Intelligent Systems and Technology Collaborative Research Alliance (CRA) will create Autonomous, Resilient, Cognitive, Heterogeneous Swarms that can enable humans to participate in wide range of missions in dynamically changing, harsh and contested environments. These include search and rescue of hostages, information gathering after terrorist attacks or natural disasters, and humanitarian missions. Swarms of humans and robots will operate as a cohesive team with robots preventing humans from coming in harms way (Force Protection) and extending and amplifying their reach to allow 1 human to do the work of 10 humans (Force Multiplication). Our research will create swarms that will provide on-demand services in these missions.  The team is led by the University of Pennsylvania and includes collaborators from Penn and the U.S. Army Research Laboratory, the Massachusetts Institute of Technology, Georgia Institute of Technology, University of California and University of Southern California.

Safe AI-enabled Autonomy (DARPA Assured Autonomy)

Safe AI

We are in the midst of a foundational shift. From self-driving cars and voice assistants to smart thermostats and recommendation engines, Artificial Intelligence (AI) and machine learning are becoming an integral part of our daily lives. The emergence of these technologies opens up countless opportunities to transform any industry and to revolutionize traditional ways of thinking, operating, and solving problems. But…how do you know if you can trust AI? Our group is focused on working with existing AI-enabled autonomous systems, making them safer, and providing rigorous guarantees of their safety. Our approach uses ideas from robust control and robust optimization (broadly defined) in order to make machine learning more robust to perturbed data or distributional shifts in the data. Quantifying the uncertainty of machine learning components is also critical as it allows systems designs that compensate for the uncertainty induce my machine learning components. Our efforts can be applied to more classical perception based tasks (classification) or in the safety and stability analysis of deep reinforcement learning of autonomous systems with machine learning components in the feedback loop.

Machine Learning and Control (

Over the next decade, the biggest generator of data is expected to be IoT devices which sense and control the physical world. This explosion of data that is emerging from the physical world requires new ways for making sense of the data as well as making data-driven decisions. These challenges will require a rapprochement of areas such as machine learning and control theory,that have evolved independently over the past couple of decades. This project aims at connecting these two intellectually distant communities by an interdisciplinary approach that spans and connects the forefronts of robust control, deep learning, dynamical systems, nonlinear control theory, system identification, statistical learning, (deep) reinforcement learning, and convex optimization. A major thrust of our proposed research will create the foundation for statistical learning for dynamical and control system identification, approximation and abstraction, which will result in providing rigorous modeling guarantees using finite amount of data. Another major thrust focuses on rethinking nonlinear control analysis and stability from model driven to data driven, enabling machine learning to scale nonlinear control towards large scale, unknown models. Finally, the last major thrust focuses on rethinking robust control for providing robustness guarantees for deep learning components as well as in deep learning the context of feedback control loops. Recently, we also started a new conference on this exciting topic (

Perception-based safe planning in unknown environments (AFOSR Assured Autonomy)

perception based safe planning in unknown environments

The majority of motion or mission planning algorithms for autonomous systems assume robots with known dynamics operating in known environments. As a result, these methods cannot be safely applied to scenarios where the environment is initially unknown but but is continuously perceived and mapped using recent advances in machine learning. To address these challenges, we are pursuing developing perception-based complex mission planning algorithm for multi-robot systems with known dynamics that operate in uncertain environments. Specifically, the uncertain environment is modeled using probabilistic semantic maps and/or occupancy grid maps while mission. Safety specifications are rigorously expressed in suitable temporal logic formalisms. Our approaches generate reactive control policies that adapt to the continuously learned map of the environment that is updated machine learning-based perception systems. The proposed method scales well with the number of robots and the size of workspace. We are also developing learning-based approaches for temporal logic mission planning for robots with unknown dynamics operating in uncertain environments.

Estimation and Control over 5G networks (NSF CPS), Intel Science and Technology Center

Estimation and Control over 5G networks

The internet-of-things (IoT) revolution is bringing millions of physical devices online (e.g. cars, UAVs, homes, medical devices), enabling them to connect to each other in real-time, as well as to cloud services. Beyond 5G wireless communication will be critical in providing IoT connectivity. Our project focuses on low-latency and ultra-reliable communications and networking that is critical for latency-sensitive, closed-loop control applications, like vehicle to vehicle communications, collaborative swam planning, and Industry 4.0 applications. In such latency sensitive applications, we do not know what is possible and what are the fundamental limits for control system design over low-latency, high-reliability communications. In this project, we will be rethinking the scientific foundations for ultra-reliable, low-latency wireless communications for latency sensitive control applications. We propose to achieve our scientific agenda by addressing three intellectual challenges: 1) Low-latency channel coding, where the goal is to focus on short packet codes for control loops 2) Control over low latency-aware communication channels, where the goal is to understand the what is the optimal tradeoff of latency to reliability for control loops and 3) Learning for Large Scale Wireless Control Networks, where machine learning will perform resource allocation for large numbers of control loops with competing latency/reliability requirements We intend to evaluate the proposed research agenda by leveraging our existing Intel Science and Technology Center (ISTC) on Wireless Autonomous Systems and demonstrate our ideas in future wireless protocols (IEEE 802.11ax) and experimentally demonstrate it in high-speed V2V and fast formation control with aerial swarms.

Resilience of Critical Networked Infrastructure (The Rockefeller Foundation)

Multi-agent networked systems are used to model a wide variety of systems, from robotic networks to power systems, to biological networks. The emergent dynamics of a network of dynamic agents can be strongly affected by the presence of network failures. The main of our research in this direction is to find computationally efficient methods to study the effects of link or node failures on networked infrastructure. We have provided several methods for detection and isolation of failures in a network of dynamic agents, based on the presence of discontinuities in the derivatives of the output responses of a subset of nodes.

Security and Privacy-Aware Cyber-Physical Systems (NSF, Intel) - (Project page)

The project aims to achieve a comprehensive understanding of CPS-specific security and privacy challenges. This understanding will enable us to (1) develop techniques to prevent security attacks to CPS and to detect and recover from malicious attacks to CPS; (2) develop techniques for security-aware control design by develop attack resilient state estimator; (3) ensure privacy of data collected and used by CPS, and (4) establish an evidence-based framework for CPS security and privacy assurance, taking into account the operating context of the system and human factors.