Physical AI Safety

Physical AI systems such as robots and humanoids are increasingly capable, yet deploying them safely around humans remains an open challenge. This raises the following question.

How do we train physical AI to safely adapt to new environments?

Problems

  • Safe Reinforcement Learning
  • Sim-to-Real Adaptation

10 Related Publications

Online Conformal Abstention Under Adversarial Bandit Feedback
Minjae Lee*, Yoonjae Jung*, Sangdon Park
The Fortieth Annual Conference on Neural Information Processing Systems, 2026
NeurIPS 🏆 Best Paper Finalist from CKAIA ICLR'26 Reliable Autonomy Workshop
SOUNDBOOST: Effective RCA and Attack Detection for UAV via Acoustic Side-Channel
Haoran Wang, Zheng Yang, Sangdon Park, Yibin Yang, Seulbae Kim, Willian Lunardi, Martin Andreoni, Taesoo Kim, Wenke Lee
International Conference on Dependable Systems and Networks, 2025
DSN
MedBN: Robust Test Time Adaptation against Malicious Test Samples
Hyejin Park*, Jeongyeon Hwang*, Sunung Mun, Sangdon Park, Jungseul Ok
Computer Vision and Pattern Recognition, 2024
CVPR
Angelic Patches for Improving Third-Party Object Detector Performance
Wenwen Si, Shuo Li, Sangdon Park, Insup Lee, Osbert Bastani
Computer Vision and Pattern Recognition, 2023
CVPR
CODiT: Conformal Out-of-Distribution Detection in Time-Series Data for Cyber-Physical Systems
Ramneet Kaur, Kaustubh Sridhar, Sangdon Park, Yahan Yang, Susmit Jha, Anirban Roy, Oleg Sokolsky, Insup Lee
International Conference on Cyber-Physical Systems, 2023
ICCPS 🏆 ICCPS'23 Best Paper Award Finalist
Sequential Covariate Shift Detection Using Classifier Two-Sample Tests
Sooyong Jang, Sangdon Park, Insup Lee, Osbert Bastani
International Conference on Machine Learning, 2022
ICML
Towards PAC Multi-Object Detection and Tracking
Shuo Li, Sangdon Park, Xiayan Ji, Insup Lee, Osbert Bastani
2022
iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection
Ramneet Kaur, Susmit Jha, Anirban Roy, Sangdon Park, Edgar Dobriban, Oleg Sokolsky, Insup Lee
Association for the Advancement of Artificial Intelligence, 2021
AAAI
Integrated intelligence for human-robot teams
Jean Oh, Thomas M Howard, Matthew R Walter, Daniel Barber, Menglong Zhu, Sangdon Park, Arne Suppe, Luis Navarro-Serment, Felix Duvallet, Abdeslam Boularias, others
International Symposium on Experimental Robotics, 2016
ISER
Abnormal object detection by canonical scene-based contextual model
Sangdon Park, Wonsik Kim, Kyoung Mu Lee
European Conference on Computer Vision, 2012
ECCV 🏆 Distinguished MS Dissertation Award