Nicholas Adrian

Education

B.S. Nanyang Technological University (2018)

Award

Technology-Environment-Energy-Water-Society Fellowship (Fall 2024)

Research

I joined the lab in Fall 2022 and have since been part of a collaborative research project to design, build, and control a highly dynamic humanoid robot called Dash. My initial work centered on developing a novel set of rigid-body dynamics algorithms capable of handling closed-chain sub-systems, which are increasingly prevalent in modern humanoids but have no straightforward solution. Traditionally, existing algorithms face a trade-off between accuracy and computational efficiency. Our approach, however, seeks to achieve both high accuracy and low computational time.

A second line of research addresses the demanding task of whole-body manipulation for humanoid robots that interact with heavy payloads. Heavy payload produces significant disturbance to the humanoid robot control and has become a major limitation in humanoid robots being able to alleviate humans in handling physically strenuous and dangerous tasks. My work incorporates the payload full dynamics into a model-based optimization strategy (MPC) and shows the Dash humanoid performing a heavy-lifting routine in simulation. The proposed methods will ultimately be validated on a real humanoid platform for which I am building the mechatronic systems.

The third project continues to challenge humanoid robots' limitation on working with heavy payload. My previous work assumes that we have full information about the payload (e.g., mass and inertial parameters) to include in the optimization formulation, and this work seeks to challenge that assumption. Much like how most humans can move bulky objects they have never seen before, we would like to replicate this capability by allowing the humanoid robot to infer the unseen payload's inertial properties through proprioception. Central to this is an inertial parameter estimation that leverages higher-order polynomials to characterize these inertial parameters.

Prior to graduate school, I received my B.S. in Mechanical Engineering from Nanyang Technological University, Singapore in 2018. Upon completing my undergraduate degree, I took up a full-time research position with Control Robotics Intelligence Group led by Assoc Prof Pham Quang Cuong. Most of my research work then revolved around industrial robotics manipulation in unstructured environment, and are done in collaboration with HP Inc as part of the HP-NTU Digital Manufacturing Corporate Lab.

Publication

Journal

• M. Chignoli, N. Adrian, S. Kim, and P. M. Wensing. A propagation perspective on recursive forward dynamics for systems with kinematic loops. IEEE Transactions on Robotics, 41:5584-5603, 2025. doi: 10.1109/TRO.2025.3593081, arXiv: 2311.13732.

Conference

• N. Fey, N. Adrian, P. M. Wensing, and M. Lemmon. A learning-based framework to adapt legged robots on-the-fly to unexpected disturbances. In 6th Annual Learning for Dynamics & Control Conference, volume 242, pages 1161–1173, 2024.
• Nguyen, Q. N., Adrian, N., & Pham, Q. C. (2023, May). Task-space clustering for mobile manipulator task sequencing. In 2023 IEEE International Conference on Robotics and Automation (ICRA) (pp. 3693-3699). IEEE.
• Adrian, N., Do, V. T., & Pham, Q. C. (2022, August). DFBVS: Deep feature-based visual servo. In 2022 IEEE 18th International Conference on Automation Science and Engineering (CASE) (pp. 1783-1789). IEEE.
• Nguyen, H., Adrian, N., Yan, J. L. X., Salfity, J. M., Allen, W., & Pham, Q. C. (2020, May). Development of a robotic system for automated decaking of 3D-printed parts. In 2020 IEEE International Conference on Robotics and Automation (ICRA)(pp. 8202-8208). IEEE.

Workshop

• M. Chignoli, N. Adrian, S. Kim, P. M. Wensing. Improving Contact-Rich Robotic Simulation with Generalized Rigid-Body Dynamics Algorithms. In ICRA 2023 Workshop: Embracing Contacts.
• Y. S. Lee, N. Vuong, N. Adrian, Q.-C. Pham. Integrating Force-based Manipulation Primitives with Deep Learning-based Visual Servoing for Robotic Assembly. In ICRA 2022 Workshop: Reinforcement Learning for Contact-Rich Manipulation.

Patent

• J. Salfity, W. Allen, H. Nguyen, N. Adrian , J. X. Y. Lim, Q.-C. Pham. 3D-printed object cleaning. US Patent 12,311,605. 2025.
• V.-T. Do, Q.-C. Pham, N. Adrian. Powder removal coverages. PCT App. PCT/US2022/046443

Life

I fill my week through a combination of: reading (especially books from the fantastic lines of authors that Notre Dame has been inviting), running, volunteering at the local bike garage, practising brazilian jiu-jitsu, keeping my sense of humor, and making sure that nobody is turning into paperclips.