Safe Robotics Lab

Research lab at @Princeton working on Robot and AI Safety around people. Opinions are our own.

[Safe Robotics Lab @SafeRoboticsLab]

Can AI keep you safe at 200 mph? We pushed the limits on the world-class racing sim @AC_assettocorsa🏁 When danger strikes, our AI copilot smoothly adjusts your steering, gas & brakes faster than you blink, keeping you on track, in control and crash-free🛡️✨ See it in action!👇🧵

[Safe Robotics Lab @SafeRoboticsLab]

Finally, a shout-out to the awesome humans who came together to make this happen 👇

@Princeton:
@donggeonoh1999, @justinlidard, @HaiminHu, @HimaniSinhmar, @eglazarski, Naomi Leonard, @jaime_fisac

@ToyotaResearch:
@gopinath_deepak, @EmilySSumner, Jon DeCastro, Guy Rosman

[Safe Robotics Lab @SafeRoboticsLab]

Can AI keep you safe at 200 mph? We pushed the limits on the world-class racing sim @AC_assettocorsa🏁 When danger strikes, our AI copilot smoothly adjusts your steering, gas & brakes faster than you blink, keeping you on track, in control and crash-free🛡️✨ See it in action!👇🧵

[Safe Robotics Lab @SafeRoboticsLab]

🔗 Want to learn more? Check out our paper & more videos: https://t.co/1pQ0dXiGfA

🛠️ Open-source code coming soon—stay tuned if you want to play!

[Safe Robotics Lab @SafeRoboticsLab]

Our lab is in Atlanta for #ICRA2025 this week! Reach out if you’re interested in chatting about robot safety—we’d love to connect.

[Safe Robotics Lab @SafeRoboticsLab]

@OpenAI rolled back GPT-4o citing sycophancy—just as our research predicted. Short-term feedback teaches AI to sound nice... and systematically misaligns it!

Our solution: RLHS, training AI with simulated hindsight feedback for long-term alignment!

👉 https://t.co/howxfhPRvd

[OpenAI @OpenAI]

We’ve rolled back last week's GPT-4o update in ChatGPT because it was overly flattering and agreeable. You now have access to an earlier version with more balanced behavior.

More on what happened, why it matters, and how we’re addressing sycophancy: https://t.co/LOhOU7i7DC

[Safe Robotics Lab @SafeRoboticsLab]

✨ We look forward to seeing you in Atlanta!
Organizing Team: @HaiminHu, @kaiqu_liang, @zzx9636, @andrea_bajcsy, @jaime_fisac

[Safe Robotics Lab @SafeRoboticsLab]

📢 Excited to announce the 1st ICRA Workshop on Public Trust in Autonomous Systems!

🚗 Join us for a focused day-long discussion on what it’ll take to lay the foundations of trust in robotics and AI #ICRA2025

📅 Submit your papers by Apr 18! ⏰

👉 https://t.co/bCinesIi10 (1/5)

[Safe Robotics Lab @SafeRoboticsLab]

We're bringing together leading roboticists and policy experts for a day-long deep dive, generating new insights to lay rigorous foundations for public trust in robotics and AI. 🤝📚 (5/5)

[Safe Robotics Lab @SafeRoboticsLab]

Meet our team!

Prof. @jaime_fisac
@HaiminHu
@zzx9636
@duyphgnguyen
@maddie_bland_31
@kaiqu_liang
Justin Wang
@donggeonoh1999
Jarod Wille

[Safe Robotics Lab @SafeRoboticsLab]

🚀 We are the Safe Robotics Lab at Princeton. We work on making robots and AI safe around people. 🤖🤝👥 #SafeRobotics #TrustworthyAI #HumanRobotInteraction

🎬Check us out in < 1 min! ⬆️🔊🎶

Discover more: https://t.co/hyh8Bb42hL
(1/3)

[Safe Robotics Lab @SafeRoboticsLab]

Our research brings together control systems, game theory, and artificial intelligence to unlock rigorous safety guarantees that are transparent, trustworthy, and easy to understand. 💡🔐 (3/3)