Jiawei (Janna) Lin

I am a first-year Ph.D. student in Computer Science and Engineering at University of California, San Diego, where I work on safety and reliability in autonomous systems. I am co-advised by Prof. Sean/Sicun Gao in the Automation Algorithms Group and Prof. Sylvia Herbert in the Safe Autonomous Systems Group.

My research interests lie in algorithms, optimization, and control for reliable decision-making in dynamical systems. I am especially interested in mathematically grounded methods for safety verification, trajectory optimization, and control synthesis, with applications to physical and cyber-physical systems.

Prior to joining UCSD, I graduated with a Bachelor of Science in Computer Science with Honors in the College of Engineering at Cornell University. During my undergraduate studies, I've explored a wide range of topics in control. I was fortunate to work with Prof. Sarah Dean on model predictive control for high-altitude balloons (ICRA 2025), Prof. Hadas Kress-Gazit on specification-based control for heterogeneous electromechanical systems, and Prof. Tapomayukh Bhattacharjee on adaptive control methods for physical interaction studies (CoRL 2025).

jal214 at ucsd dot edu  /  GitHub  /  Google Scholar  /  LinkedIn

Research Interests

My research focuses on algorithms, optimization, and control theory for complex dynamical systems. I am interested in developing mathematically grounded methods for modeling, verification, and control, with particular emphasis on reliability, robustness, and computational tractability.

Current directions include optimal control, trajectory optimization, formal verification, Hamilton-Jacobi reachability, safety filters, and numerical methods for continuous and hybrid systems.

News

Research

I'm interested in the safety and reliability in autonomous systems with learning-based or optimization-based methods.

High-Altitude Balloon Station-Keeping with First Order Model Predictive Control

We study model-based control for station-keeping in atmospheric dynamical systems. We develop a first-order model-predictive control method and implement the wind and balloon dynamics as differentiable functions in JAX, enabling gradient-based trajectory optimization for online planning.

PrioriTouch: Adapting to User Contact Preferences for Whole-Arm Physical Human-Robot Interaction

We introduce PrioriTouch, a framework for adapting whole-arm physical interaction to user-specific contact preferences. The method combines preference learning with hierarchical operational-space control, translating high-level feedback into low-level pose and force-control policies for physical interaction tasks.

Continuous Execution of High-Level Collaborative Tasks for Heterogeneous Robot Teams

We propose a control-synthesis framework for coordinating heterogeneous electromechanical systems under high-level task specifications. The framework supports collaborative tasks with actions of varying duration and enables continuous execution across different hardware platforms.

Other Projects

Car Dynamics Correction with Random Fourier Ridge Regression and Fast Optimal Control via DLRA Scheme of Hamilton-Jacobi-Bellman Equation: a Comparative Study

Using the EU long-term dataset, we develop and compare three approaches: raw INS integration, an Extended Kalman Filter with Random Fourier Features (EKF-RFF) for state estimation, and a tensor- train-based Hamilton-Jacobi-Bellman (HJB) solver with Dynamical Low-Rank Approximation (DLRA) for optimal control synthesis.

Miscellaneous

Website last updated Jun 2026 Design and source code from Jon Barron's website