Postdoctoral Researcher, A²R Lab
The Accessible and Accelerated Robotics Lab (A²R Lab) at Barnard College, Columbia University is hiring a postdoctoral fellow with an ASAP start date, under the direction of Professor Brian Plancher. The postdoc will be playing a leading role in the associated research in our new NSF-funded project: "Accessible GPU-Accelerated Edge Optimal Control Library and Benchmarks." This (up-to) three-year project will be building on our prior work on GPU acceleration of numerical optimal control algorithms in the pursuit of whole body nonlinear model predictive control for locomotion which led to a number of open-source projects and ICRA/RA-L publications including our rigid body dynamics library, GRiD, and our recent trajectory optimization solver, MPCGPU. This research has also been integrated into the PI's Parallel Optimization for Robotics undergraduate course.
Our new effort is aimed at turning these proof-of-concept results into full-fledged, open-source software packages and supporting ecosystem for use by the optimal control and robotics communities broadly. This will require algorithmic research to generalize our existing approaches and novel re-designs to maintain performance while supporting broader classes of problems. This software will be paired with open-source benchmark problems and datasets and integrated into machine learning (ML) frameworks to enable fair evaluations of new algorithms and to enable broader participation in this interdisciplinary field. Finally, this project will build on the PIs existing courses and release an open-source integrated educational curriculum that provides background knowledge, enabling researchers and practitioners worldwide to learn about these topics, leverage this cyberinfrastructure to improve their systems, and contribute to the project.
Building on Professor Plancher's leadership of the IEEE RAS TC on Model Based Optimization for Robotics, we have already secured a number of global collaborators interested in helping co-develop these many efforts. These not only include research collaborations building on past award-winning collaborative work (e.g., TinyMPC), but also through additional grants including a RAS-TEP Grant to run an Optimization for Robotics Summer School in Greece in 2025. As such, this role will place the postdoctoral researcher at the center of the optimization for the robotics world.
Applications should be submitted electronically and should include a CV, Statement of Interest, along with any other relevant applicant material. Candidates must have a PhD, in progress or conferred, in Computer Science or related discipline.
Strong preference for C, C++, CUDA experience.
Applications will be reviewed until the position is filled.