Projects | HUMAN-ORIENTED ROBOTICS AND CONTROL LAB

Human-Robot Interaction & Control Interfaces

Mon, 01 Jan 0001 00:00:00 +0000

Project Goal

This project advances human-multi-agent interaction by creating intuitive, responsive control frameworks at the intersection of neuroscience, robotics, and machine learning. We integrate physiological intent decoding with distributed control to build scalable, low-cognitive-load interfaces for supervising complex multi-agent systems. Additionally, we apply adversarial machine learning using probing agents to actively discover and identify leader agents within dynamic multi-agent topologies.

Key Contributions

EEG-Based Trust Quantification: Utilized electroencephalography (EEG) signals to decode, quantify, and model real-time human trust levels during human-multi-agent interaction.
Brain-Machine Interface (BMI) Control: Formulated novel control methodologies leveraging brain-machine interfaces (BMI) for intuitive, direct human supervision of multi-agent systems.
Adversarial Leader Identification: Developed the first learning-based framework for automatic leader identification, using deep reinforcement learning to train a physically interactive probing agent within partially observable multi-agent environments.

Media & Experimental Demos

Selected Publications

(see for a complete list)

Extracting Human Levels of Trust in Human-Swarm Interaction using EEG signals
Jesus Orozco and Panagiotis Artemiadis
IEEE Transactions on Human-Machine Systems, vol. 54, no. 2, pp. 182–191, April 2024.
[ ]
Inferring imagined speech using EEG signals: a new approach using Riemannian manifold features
Chuong H. Nguyen, George K. Karavas, and Panagiotis Artemiadis
Journal of Neural Engineering, vol. 15, no. 1, 016002, 2018.
[ ] [ ]
Learning Adversarial Policies for Swarm Leader Identification using a Probing Agent
Stergios Bachoumas and Panagiotis Artemiadis
IEEE International Conference on Robotics and Automation (ICRA), Atlanta, GA, 2025.
[ ]

Funding & Acknowledgments

This work has been supported by the following grants:

DARPA: D14AP00068
AFOSR: FA9550-14-1-0149, FA9550-18-1-0221, FA9550-18-1-0464
NSF: 2014264
Any opinions, findings, and conclusions expressed are those of the authors.

Robot-assisted Gait Rehabilitation using the Variable Stiffness Treadmill

Mon, 01 Jan 0001 00:00:00 +0000

Project Goal

This project develops a novel post-stroke rehabilitation platform using the Variable Stiffness Treadmill (VST) to deliver targeted unilateral surface perturbations, evoking therapeutic motor responses in the impaired leg to increase step length and reduce drop-foot in mobility impaired individuals.

Key Contributions

Demonstration of Lasting Motor Aftereffects: Proved that robot-assisted surface stiffness perturbations induce persistent sensorimotor adaptations, facilitating neural plasticity and improving inter-leg coordination post-stroke.
Patient-Specific Rehabilitation Personalization: Established a framework for real-time, dynamic stiffness adjustment to tailor mechanical perturbations to an individual’s unique gait deficits and training needs.
Mechanistic Insights into Mechanical Interventions: Advanced fundamental understanding of how targeted physical/mechanical perturbations engage neural pathways to correct post-stroke motor impairments.
Translational Clinical Impact: Demonstrated a viable robotic intervention to improve functional mobility, step symmetry, and gait mechanics for hemiparetic patients.

Media & Experimental Demos

Selected Publications

(see for a complete list)

The Variable Stiffness Treadmill (VST) 2: Development and Validation of a Unique Tool to Investigate Locomotion on Compliant Terrain
Vaughn Chambers, Bradley Hobbs, William Gaither, Zachary The, Anthony Zhou, Chrysostomos Karakasis, Panagiotis Artemiadis
J. Mechanisms Robotics, 2025.
[ ]
Using robot-assisted stiffness perturbations to evoke aftereffects useful to post-stroke gait rehabilitation
Vaughn Chambers and Panagiotis Artemiadis
Frontiers in Robotics and AI, 9, 2023. [ ]
Variable Stiffness Treadmill (VST): System Development, Characterization and Preliminary Experiments
Jeffrey Skidmore, Andrew Barkan and Panagiotis Artemiadis
IEEE/ASME Transactions on Mechatronics, vol. 20, issue 4, pp. 1717-1724, 2015. [ ]

Funding & Acknowledgments

This work has been supported by the following grants:

NSF: 2020009, 2015786, 2025797, 201890, 2415093
NIH: NIH 1R01HD111071-01
Any opinions, findings, and conclusions expressed are those of the authors.

Advanced Controllers for Lower-limb Prostheses Enhancing Agility

Mon, 01 Jan 0001 00:00:00 +0000

Project Goal

This project develops human-in-the-loop adaptive control systems for prosthetic devices that enhance user mobility and stability across varied terrains.

Key Contributions

Dynamic Adaptive Control Design: Developed intelligent prosthetic controllers that dynamically adapt parameters in real time to suit changing surface conditions and individual user needs.
Predictive Surface Transitioning: Formulated predictive models using neural and kinematic signals to anticipate transitions to compliant terrains during gait, ensuring smooth, uninterrupted locomotion.
Terrain-Adaptive Stiffness Modulation: Implemented real-time ankle-foot stiffness tuning to enhance user balance, stability, and agility over soft, uneven, or compliant surfaces.

Media & Experimental Demos

Selected Publications

(see for a complete list)

On Predicting Transitions to Compliant Surfaces in Human Gait via Neural and Kinematic Signals
Charikleia Angelidou and Panagiotis Artemiadis IEEE Transactions on Neural Systems and Rehabilitation Engineering, 31:2214-2223, 2023. [ ]
Adjusting the Quasi-Stiffness of an Ankle-Foot Prosthesis Improves Walking Stability during Locomotion over Compliant Terrain
Chrysostomos Karakasis, Robert Salati and Panagiotis Artemiadis In the Proc. of the 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Detroit, MI, USA, pp. 2140-2145, 2023 [ ]
On the Effects of Visual Anticipation of Floor Compliance Changes on Human Gait: Towards Model-based Robot-Assisted Rehabilitation
Michael Drolet, Emiliano Quinones Yumbla, Bradley Hobbs and Panagiotis Artemiadis
In the Proc. of the 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 9072-9078, 2020. [ ]

Funding & Acknowledgments

This work has been supported by the following grants:

NSF: 2020009, 2015786, 2025797, 201890
Any opinions, findings, and conclusions expressed are those of the authors.

Controllers for Compliant, Efficient and Safe Human-Humanoid Collaboration

Mon, 01 Jan 0001 00:00:00 +0000

Project Goal

This project develops advanced control frameworks for humanoid robots that enable safe, compliant, and intuitive physical collaboration with humans during shared tasks such as joint object transportation and manipulation.

Key Contributions

Novel I-LIP Modeling & MPC: Formulated the Interaction Linear Inverted Pendulum (I-LIP) model to generate adaptive footstep patterns for physical co-manipulation tasks.
Hybrid MPC & Admittance Control Framework: Integrated Model Predictive Control with an admittance control model to dynamically adapt bipedal behavior in response to real-time interaction forces.
Coupled Stability and Compliance: Designed an object-aware Whole Body Controller for the high-level plans of the Digit Humanoid to achieve simultaneous bipedal balance and compliant behavior during physical human-robot collaboration.
Quantitative Collaboration Metric: Established an efficiency metric to jointly evaluate task performance and inter-agent coordination during dyadic transport.
Full-Scale Experimental Validation: Demonstrated real-world execution on the Digit humanoid robot, proving that passive compliance enabled diverse dynamic maneuvers (forward motion, lateral shifts, turning) without prior knowledge of the human’s trajectory.

Media & Experimental Demos

Selected Publications

(see for a complete list)

MPC-QP-based Control Framework for Compliant Behavior of Humanoid Robots in Physical Collaboration with Humans
Shubham Kumbhar and Panagiotis Artemiadis
IEEE International Conference on Robotics and Automation (ICRA), Atlanta, GA, 2025
[ ]
Toward Seamless Physical Human-Humanoid Interaction: Insights from Control, Intent, and Modeling with a Vision for What Comes Next
Gustavo A. Cardona, Shubham S. Kumbhar, and Panagiotis Artemiadis
Journal of Intelligent & Robotic Systems, 2026, [ ]

Funding & Acknowledgments

This work has been supported by the following grants:

NSF: 2020009, 2015786, 2025797, 201890, 2415093
NIH: NIH 1R01HD111071-01
Any opinions, findings, and conclusions expressed are those of the authors.

Neural Human-Robot Interfaces for Intuitive Collaboration

Mon, 01 Jan 0001 00:00:00 +0000

Project Goal

This project develops advanced human-robot interfaces that integrate neural signals and movement intent inference to enable seamless, intuitive physical collaboration during complex tasks.

Key Contributions

Movement Intent Inference Algorithms: Developed algorithms to infer intended movement directions based on human-human physical interaction paradigms, enabling more intuitive human-robot collaboration.
6-DOF Physical Interaction Control: Formulated control strategies capable of managing complex, full six-degrees-of-freedom (6-DOF) physical interactions during shared tasks.
Asymmetric Task Sharing & Role Allocation: Designed adaptive control frameworks that accommodate varying and unequal task contributions between human and robotic partners.

Selected Publications

(see for a complete list)

Communication and Inference of Intended Movement Direction during Human-Human Physical Interaction
Keivan Mojtahedi, Bryan Whitsell, Panagiotis Artemiadis and Marco Santello
Frontiers in Neurorobotics, vol. 11 (21), pp. 1-12, 2017. [ ]
Physical Human–Robot Interaction (pHRI) in 6 DOF With Asymmetric Cooperation
Bryan Whitsell and Panagiotis Artemiadis IEEE Access, vol. 5, pp. 10834-10845, 2017. [ ]
Effective Neural Representations for Brain-Mediated Human-Robot Interactions
Christopher A. Buneo, Stephen Helms Tillery, Marco Santello, Veronica J. Santos, and Panagiotis Artemiadis In Neuro-robotics: From brain machine interfaces to rehabilitation robotics, as part of the Springer series on Trends on Augmentation of Human Performance, Artemiadis, P., Ed., New York:Springer, 2014, Vol. 2., pp. 207-237. Springer Netherlands, 2014.

Neuromuscular Interface Development for Enhancing Human-Machine Collaboration

Mon, 01 Jan 0001 00:00:00 +0000

Project Goal

This project develops advanced neuromuscular control frameworks that decode electromyographic (EMG) signals in real time to achieve intuitive, high-precision control of prosthetic limbs and assistive robotic devices.

Key Contributions

High-Density EMG Systems for Multi-DoF Control: Developed high-density EMG frameworks that enable robust, long-term control of high-degree-of-freedom platforms (such as a 7-DoF robot arm) while enhancing motor skill learning and retention over extended periods.
Muscle Synergy-Based Control Architectures: Leveraged muscle synergy principles to design myoelectric control systems that improve overall performance, skill retainment, and generalization across diverse motor tasks.
Simultaneous Multifunction Decoding: Advanced simultaneous, multi-axis control algorithms to overcome traditional myoelectric limitations and enable seamless, intuitive human-machine interaction in complex scenarios.

Media & Experimental Demos

Selected Publications

(see for a complete list)

High-Density Electromyography and Motor Skill Learning for Robust Long-Term Control of a 7-DoF Robot Arm
Mark Ison, Ivan Vujaklija, Bryan Whitsell, Dario Farina and Panagiotis Artemiadis
IEEE Transactions on Neural Systems & Rehabilitation Engineering, vol. 24(4), pp. 424-433, 2016. [ ]
Proportional Myoelectric Control of Robots: Muscle Synergy Development drives Performance Enhancement, Retainment, and Generalization
Mark Ison and Panagiotis Artemiadis
IEEE Transactions on Robotics, vol. 31, issue 2, pp. 259-268, 2015. [ ]
The Role of Muscle Synergies in Myoelectric Control: Trends and Challenges for Simultaneous Multifunction Control
Mark Ison and Panagiotis Artemiadis
Journal of Neural Engineering, vol. 11(5), 2014. [ ]