Clinton Enwerem ECE Doctoral Candidate | Policy Learning for Safe & Robust Poly-Articulated Dexterous Robotic Manipulation

I am on track to complete my PhD this Fall and am seeking full-time roles in robot learning, robotics research engineering, and planning and control, with availability from January 2027.

I am an Electrical & Computer Engineering (ECE) Ph.D. candidate at the University of Maryland (UMD), College Park, MD, USA, working with Professor John S. Baras, Distinguished University Professor and Endowed Lockheed Martin Chair in Systems Engineering, and Professor Calin Belta, Brendan Iribe Endowed Professor of ECE and Computer Science. I work on contact-rich poly-articulated (humanoid, serial-chain, and fixed-base bimanual) dexterous grasping and manipulation under uncertainty, drawing on safe and risk-sensitive control, belief-space kinodynamic motion planning, and policy learning to make multifingered grasping and manipulation more reliable when object pose, friction, and contact modes are only partially known. At UMD, I am affiliated with the Institute for Systems Research, the EXplainable and Assured Control for AuTonomy (EXACT) lab, the Systems Engineering and Integration lab, and the Maryland Robotics Center (MRC). I have also received the Dean's Fellowship from UMD's Graduate School and the Microsoft Diversity in Robotics and Autonomy PhD Fellowship, awarded through a collaboration between Microsoft Corporation and MRC.

Prior to resuming doctoral studies at UMD, I was a robotics engineer at Kognitive Robotics, a local robotics engineering startup building turnkey mobile robot platforms for education and research. Before that, I completed a year-long stint as a robotics trainee at Nigeria's foremost robotics and AI research center — Robotics and Artificial Intelligence Nigeria (RAIN). At RAIN, I worked with Dr. Olusola Ayoola on varied projects spanning robot navigation, visual SLAM, and robot control. Before RAIN, in affiliation with the Electrical Engineering Department at my alma mater, I collaborated with Engr. Ihechiluru Okoro on research topics at the intersection of robust control, observer-based compensator design, and feedback control of time-delayed dynamical systems.

I earned my undergraduate degree in Electrical Engineering (with highest honors) from the University of Nigeria, working under the supervision of Dr. Udoka Nwaneto. My bachelor's thesis focused on model-based controller design for speed regulation in electric drives.

profile photo

Contact Info

4448 A.V. Williams Bldg.

8223 Paint Branch Dr

College Park, MD 20740

Email LinkedIn
Research

I study contact-rich dexterous grasping and manipulation under uncertain object pose, friction, and contact conditions. My work combines control barrier functions, risk-sensitive planning, belief estimation, and policy learning to account for these uncertainties and for forces and torques induced by robot motion and external disturbances. I evaluate these methods in MuJoCo, Drake, and Isaac Sim, and through hardware experiments on the platforms listed on the Robots page.

SE(3)-Equivariant, Reach-Aware Grasp Synthesis · EquiDexFlow Project Page
Grasp Distance Fields · Project Page
GDF supports autonomous dexterous grasp execution with dynamic obstacle avoidance and grasp-quality preservation.
Belief-Informed vs. Reference Tracking · Bimanual Part Assembly · Drake Simulation
VR-assisted dexterous teleoperation for demonstration collection, with workspace-boundary enforcement and collision avoidance.
Bimanual Hardware Video
Demonstration-Augmented Reinforcement Learning for Dexterous Relocation · Study Details
Behavior cloning initialization compared with a trained DAPG policy.
Imitation Learning Under Variation in Execution Timing · ParcelStow Project Page
We show that nominal task success does not establish preservation of expert performance under variation in execution timing.
Supervised fine-tuning (SFT) of VLAs for monitoring task progress and triggering recovery from visuo-tactile feedback.

Publications and more →

News

  • Preprint We introduced a CBF-CLF-based method for planner-free dexterous grasp execution, with safe-set forward invariance and grasp-quality preservation. Project page: Grasp Distance Fields.

  • Preprint In FIRMGrasp, we introduced a CVaR-based grasp-quality margin for uncertain friction. Among grasps that established contact, simulated lift-and-pull success at a friction coefficient of 0.2 was 70% for 27 grasps certified by our margin, compared with 25% for 24 grasps certified only by the nominal Ferrari–Canny margin.

  • Paper VNB-Grasp, our variational neural belief method for risk-sensitive dexterous grasping under visuo-tactile uncertainty, was accepted for presentation at IROS 2026. Links: arXiv, project page.

  • Model We introduced EquiDexFlow, an SE(3)-equivariant flow-matching model for joint prediction of wrist pose, hand joint configuration, fingertip contacts, contact normals, and contact forces from an object point cloud. We retargeted the predicted contacts to the LEAP Hand for hardware grasp-and-lift execution.

Older News

  • Paper Our paper on quantile-based distributional reinforcement learning for safe control was accepted for presentation at CDC 2025. Study summary.

  • Milestone I passed my research proposal exam and advanced to doctoral candidacy.