Welcome to the Safe Robotics Laboratory at Princeton!

Our lab is pioneering rigorous safety frameworks with clear-cut guarantees to make robots and AI truly trustworthy partners in everyday life.

Making robots and AI safe around people.

 

Our group develops theory and algorithms empowering robots, autonomous cars, and AI assistants to actively ensure safety in dynamic, unpredictable human environments.

We believe safety means more than a low probability of failure—it means knowing that our systems will anticipate and avoid hazards before they can cause harm.

Our research brings together control systems, game theory, and artificial intelligence to unlock rigorous safety guarantees that we can all understand and trust.

Latest News

Jul 2026
Prof. Fisac was elected to the Council of the International Association for Safe & Ethical AI (IASEAI) for a 3-year term!
Jun 2026
Two papers were accepted to CDC 2026: "Synthesis and Deployment of Maximal Robust Control Barrier Functions through Adversarial Reinforcement Learning" (Oh, Nguyen, Hu, Fisac) and the "Handbook on Safety Certificates" (multi-lab collaboration)!
2026
"Viscosity CBFs" (Hirsch, Fisac, Herbert) was accepted to ACC 2026!
Jan 2026
Forbes covered Prof. Fisac's AI-safety remarks at IASEAI Paris!
Oct 2025
Prof. Fisac was featured in IEEE Spectrum's Researcher Spotlight!
2025
Prof. Fisac received Princeton's E. Lawrence Keyes, Jr./Emerson Electric Co. Faculty Advancement Award and was named in Stanford/Elsevier's World's Top 2% Scientists!
2025/26
Kaiqu Liang was named an Anthropic Research Fellow and Duy Nguyen received Princeton's Outstanding Teaching Assistant Award!
Apr 2026
Dr. Zixu Zhang successfully defended his PhD! Congrats :)
Apr 2026
Kaiqu Liang's work on Mitigating Misalignment in RLHF with Hindsight Simulation was accepted to ACL'26!
Dec 2025
Our latest work on Provably Optimal Reinforcement Learning under Safety Filtering and Control-Theoretic Approach to Generative AI Guardrails were accepted to IASEAI'26!
Aug 2025
Congratulations to Dr. Haimin Hu on successfully defending his PhD on Game-Theoretic Integration of Safety and Learning for Human-Centered Robotics!
Jun 2025
David Oh presented a paper and a live demo on Safety Filter-Assisted Car Racing at RSS 2025!
May 2025
Haimin Hu presented his paper on Learning Neural Nonlinear Opinion Dynamics at ICRA 2025!
Mar 2025
Safe Robotics Lab is organizing the Workshop on Public Trust in Autonomous Systems at ICRA 2025!
Feb 2025
Congratulations to Haimin Hu on being selected as an CPS Rising Star!
Oct 2024
New paper accepted to NeurIPS 2024! Kaiqu Liang, Zixu Zhang, Jaime F. Fisac. Introspective Planning: Aligning Robots' Uncertainty with Inherent Task Ambiguity.
May 2024
Big congratulations to Dr. Kai-Chieh Hsu on his successful defense of Scaling Full-Stack Safety for Learning-Enabled Robot Autonomy!
May 2024
Two papers accepted to RSS 2024! (1/2) Haimin Hu*, Gabriele Dragotto* et al., Who Plays First? Optimizing the Order of Play in Stackelberg Games with Many Robots. (2/2) Justin Lidard*, Haimin Hu* et al., Blending Data-Driven Priors in Dynamic Games.
May 2024
Haimin Hu and Zixu Zhang have been awarded the Outstanding Presentation Award at the Princeton Research Day for their work on Who Plays First? Using Game Theory to Coordinate Many Robots. Their presentation can be found here.
Dec 2023
Congratulations to Haimin Hu on being selected as an HRI Pioneer for his research on safe human-centered robot autonomy!
Dec 2023
Kai-Chieh Hsu presented our new Fast, Smooth, and Safe paper in collaboration with Peter Ramadge's group at CDC 2023. Our new method brings reach-avoid optimal control and CBFs under a unified lens to systematically construct minimally conservative CBFs at runtime. The best part: it works for arbitrary nonlinear systems without needing hand design.
Dec 2023
Kai-Chieh Hsu and Ken Nakamura presented our Game-Induced Opinion Dynamics paper in collaboration with Naomi Leonard at CDC 2023.
Nov 2023
Our safe-and-agile delivery robot concept has was featured at Celebrate Princeton Innovation. Check out the video here.
Nov 2023
A heartfelt thank you to the Survival and Flourishing Fund for supporting our continuing collaboration with BERI to help make AI technology safer and more beneficial to humanity.
Nov 2023
Congratulations to Promise Ekpo on receiving the Cadence Diversity in Tech Fellowship for her AI safety work!
Nov 2023
Haimin Hu, Zixu Zhang, and Ken Nakamura presented our Deception Game paper in collaboration with Andrea Bajcsy (CMU) at CoRL 2023.
Oct 2023
Kai-Chieh Hsu presented our recent Counterfactual Responsibility paper in collaboration with NVIDIA at IROS 2023.
Sep 2023
We got a fun paper on learning-aware safety accepted into CoRL'23!
Sep 2023
Prof. Fisac received the Sony Focused Research Award to work on safe mobile robot navigation.