
Andrea Bajcsy
Assistant Professor · Robotics Institute — Faculty · Carnegie Mellon University
At Prof Rod’s reading desk
Questions to explore
- What assumptions does a safety claim make about the person interacting with the system?
- Which safety checks remain useful when the system includes a generative model?
Research interests
Andrea Bajcsy studies how autonomous systems interact safely with people. Her work connects control, learning and human behavior.
- Human-robot interaction
- Robot safety
- Control and learning
Explore the work
Prof Rod’s reading notes
Start with a paper
arXiv preprint · 2024
Human-AI Safety: A Descendant of Generative AI and Control Systems Safety
Prof Rod’s reading note: Compare the safety concepts inherited from control systems with the risks of generative AI. Treat this as a perspective paper, not a proof that a deployed system is safe.
Bring a question of your own
Turn reading into research
Choose a human-agent interaction. State the unsafe outcome, the uncertainty about the person and the boundary of any proposed safety claim.
Keep exploring
More at Carnegie Mellon University
- Aaron Steinfeld
Robotics
- Abhinav Gupta
Machine learning · Computer vision
- Cameron Riviere
Robotics
- Changliu Liu
Robotics
Improve this page
Suggest a correction, share a paper to start with, or point readers to a group page or opening.