Design Safe and Efficient Algorithms for AI-Embodiments
Let’s make robots work safely for us!
Project is Not Currently Available
This project has reached full capacity for the current term. Please check back next semester for updates.
Project description
Fueled by artificial intelligence (AI) algorithms, various AI embodiments, such as autonomous vehicles, robotic manipulators, and humanoid robots, have made significant advances yet remain far from maturity. One of the button-necks has been the lack of safety guarantees of AI algorithms.
In this project, students will use emerging rigorous theories in dynamic and control to formally design safe and efficient algorithms that guarantee safety for these AI-embodiments. Students will join a group of graduate students at the UB Safe and efficient autonomous system (SEAS) Lab, master theories, and apply them to real-world AI-embodiments in simulation and on real-world hardware.
Project outcome
- Experience rigorous training on theory-oriented research: conduct literature reviews, read and critique papers, communicate results clearly through academic writing, illustrations, and presentations. The student will work closely with the PI and a graduate mentor and collaborate with colleagues at UB and beyond.
- Get hands-on experiences in dynamic and control tools in applications to real-world problems. The student will work closely with simulation and hardware to implement and validate the theoretical design.
- Develop an enriched portfolio that bolsters graduate-school and/or job applications: (when results warrant) presentation at UB symposia or national conferences, paper co-authored, GitHub repository, poster and videos, strong reference letters, etc.
Project details
| Length of commitment | Year-long (10-12 months) |
| Start time | Spring (January 2026) |
| In-person, remote, or hybrid? | In-Person Project |
| Level of collaboration | Individual student project, mentored directly by the faculty member, but will work with colleagues at SEAS Lab |
| Benefits | Stipend Potential academic credit |
| Who is eligible | Junior student with a solid background in applied mathematics, dynamics, and control (e.g., MAE 340, MAE 341, MAE 376). Student should be comfortable with conducting mathematical derivation and proofs.
Any prior experience working with Python/C++, ROS2, Git/GitHub, and on hardware such as robots, drones, sensor hardware/software, and embedded systems (Arduino, Raspberry Pi, etc.) is a plus. |
Project mentor
Chaozhe He
Assistant Professor
Mechanical and Engineering Department
Phone: (716) 645-1432
Email: chaozheh@buffalo.edu
Start the project
- Email the project mentor using the contact information above to express your interest and get approval to work on the project. (Here are helpful tips on how to contact a project mentor.)
- After you receive approval from the mentor to start this project, click the button to start the digital badge. (Learn more about ELN's digital badge options.)
Preparation activities
Once you begin the digital badge series, you will have access to all the necessary activities and instructions. Your mentor has indicated they would like you to also complete the specific preparation activities below. Please reference this when you get to Step 2 of the Preparation Phase.
- Review the lab's research page to familiarize yourself with the topics of interest and current activities in the lab
- Read these two papers to get to know some of the algorithms and tools that will be used.
- Contact Professor Chaozhe He via email (chaozheh@buffalo.edu) with CV and transcript. Get ready for a quick knowledge check on dynamic & control, and assessment of coding level (Python or MATLAB), etc., during the interview.
Keywords
robotics, AI, programming, Mechanical and Aerospace Engineering, Computer Science and Engineering, Electrical Engineering, Python/C, ROS,