Recent News

[9/6/24] I was awarded an NSF CSSI Grant to build an Accessible GPU-Accelerated Edge Optimal Control Library and Benchmarks!

[7/16/24] My lab’s MPCGPU paper won the Best Poster Award at the IEEE-RAS TC on Model-Based Optimization for Robotics Virtual Poster Session!

[6/7/24] My international collaborators and I were awarded an IEEE-RAS Technical Education Program Grant to run an “Optimization for Robotics Summer School” to be held in Summer 2025!

[5/16/24] My lab’s collaborative TinyMPC paper won the Best Paper in Automation and was a finalist for Best Conference Paper and Best Student Paper at the 2024 IEEE International Conference on Robotics and Automation (ICRA)!

Featured Publications

Best Poster Award at the 2024 IEEE TC on Model Based Optimization for Robotics Virtual Poster Session
We introduce MPCGPU, a GPU-accelerated, real-time NMPC solver that leverages an accelerated preconditioned conjugate gradient (PCG) linear system solver at its core. We show that MPCGPU increases the scalability and real-time performance of NMPC, solving larger problems, at faster rates. In particular, for tracking tasks using the Kuka IIWA manipulator, MPCGPU is able to scale to kilohertz control rates with trajectories as long as 512 knot points. This is driven by a custom PCG solver which outperforms state-of-the-art, CPU-based, linear system solvers by at least 10x for a majority of solves and 3.6x on average.
PDF Code Poster Slides DOI

Best Paper in Automation at IEEE ICRA 2024
Finalist for Best Conference Paper at IEEE ICRA 2024
Finalist for Best Student Paper at IEEE ICRA 2024
Model-predictive control (MPC) is a powerful tool for controlling highly dynamic robotic systems subject to complex constraints. However, MPC is computationally demanding, and is often impractical to implement on small, resource-constrained robotic platforms. We present TinyMPC, a high-speed MPC solver with a low memory footprint targeting the microcontrollers common on small robots. Our approach is based on the alternating direction method of multipliers (ADMM) and leverages the structure of the MPC problem for efficiency. We demonstrate TinyMPC both by benchmarking against the state-of-the-art solver OSQP, achieving nearly an order of magnitude speed increase, as well as through hardware experiments on a 27 g quadrotor, demonstrating high-speed trajectory tracking and dynamic obstacle avoidance.
PDF Code Poster Video DOI Website

Computer science (CS) and engineering research both have large and well documented gender diversity gaps. In fact, previous studies have reported that the overall CS Female Author Ratio (FAR) is only in the range of 16-26% and varies significantly between CS subfields ranging from as high as 42% in CS Education to as low as 8% in Theory and Algorithms. To understand the current state of gender diversity of robotics, we recently collected and analyzed the gender of paper authors from all IEEE RAS fully sponsored conferences (ARSO, CASE, HAPTICS, Humanoids, ICRA, ISAM, MEMS, RoboSoft, SIMPAR, SSRR) as well as IROS and RA-L from 2019-2021. Overall, we find that robotics has a long way to go to reach gender parity, with an overall FAR of only 11-12%. We hope this analysis helps the robotics community to continue to emphasize the importance of working to improve our diversity.
DOI

We introduce and release GRiD, an open-source, GPU-accelerated library for computing rigid body dynamics with analytical gradients. GRiD was designed to accelerate nonlinear trajectory optimization through optimized code generation, GRiD provides as much as a 7.2x speedup over a state-of-the-art, multi-threaded CPU implementation and maintains as much as a 2.5x speedup when accounting for I/O overhead.
PDF Code Poster Slides Video DOI Benchmark Experiments

Featured Courses

Instructor of Record
Many stages of state-of-the-art robotics pipelines rely on the solutions of underlying optimization algorithms. Unfortunately, many of these approaches rely on simplifications and conservative approximations in order to reduce their computational complexity and support online operation. At the same time, parallelism has been used to significantly increase the throughput of computationally expensive algorithms across the field of computer science. And, with the widespread adoption of parallel computing platforms such as GPUs, it is natural to consider whether these architectures can benefit robotics researchers interested in solving computationally constrained problems online. This course will provide students with an introduction to both parallel programming on GPUs as well as numerical optimization. It will then dive into the intersection of those fields through case studies of recent state-of-the-art research and culminate in a team-based final project.
Draft Syllabus

Instructor of Record
This course is designed as a companion to mentored research and industry projects in computer science that enable students to apply their learning in real-world contexts. While the course staff can provide general support for projects, they may not have the technical expertise to support all projects in depth. Therefore, for Spring 2024, students are expected to have arranged for a mentored project during the course registration period and will need to present their project topic in the first class. For example, a student could be working on a research project mentored by a professor or helping a local company develop a web interface to their product mentored by a company software engineer. Mentors must commit to meeting with students at least every other week. The course will be run through a mix of lecture and group work led by the course instructor as well as guest instructors from both industry and academia. Lectures cover a variety of applied computing topics designed to complement student projects and engage students with often underexplored considerations for effective and sustainable real-world projects. Students are evaluated both by their mentor on their project progress as well as by the course staff and peers on written deliverables and presentations.
Draft Syllabus

Instructor of Record
Robots are cyber-physical systems – leveraging computational intelligence to sense and interact with the real world. As such, robotics is a very diverse, cross-disciplinary field. This introductory course exposes learners to the vast opportunities and challenges posed by the interdisciplinary nature of robotics. While grounded and focused in computation this course also explores hands-on electromechanical and ethical topics that are an integral part of a real-world robotic system. Topics will include: a survey of the algorithmic robotics pipeline (perception, mapping, localization, planning, control, and learning), an introduction to cyber-physical system design, and responsible AI. The course will culminate in a team-based final project.