Publications

Peer-reviewed conference and journal papers

Kaiqu Liang, Haimin Hu, Ryan Liu, Thomas L. Griffiths, Jaime Fernández Fisac

RLHS: Mitigating Misalignment in RLHF with Hindsight Simulation

Findings of the Association for Computational Linguistics (ACL), 2026

[paper] [homepage] [code] [poster]

Ravi Pandya, Madison Bland, Duy P. Nguyen, Changliu Liu, Jaime Fernández Fisac, Andrea Bajcsy

From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails

International Association for Safe & Ethical AI (IASEAI), 2026

[paper]

Donggeon David Oh*, Duy P. Nguyen*, Haimin Hu, Jaime Fernández Fisac

Provably Optimal Reinforcement Learning under Safety Filtering

International Association for Safe & Ethical AI (IASEAI), 2026

[paper]

Donggeon David Oh*, Justin Lidard*, Haimin Hu, Himani Sinhmar, Elle Lazarski, Deepak Gopinath, Emily S. Sumner, Jonathan A. DeCastro, Guy Rosman, Naomi Ehrich Leonard, Jaime Fernández Fisac

Safety with Agency: Human-Centered Safety Filter with Application to AI-Assisted Motorsports

Robotics: Science and Systems (RSS), 2025

[paper] [homepage] [video] [talk]

Haimin Hu, Jaime Fernández Fisac, Naomi Ehrich Leonard, Deepak Gopinath, Jonathan DeCastro, Guy Rosman

Think Deep and Fast: Learning Neural Nonlinear Opinion Dynamics from Inverse Dynamic Games for Split-Second Interactions

IEEE International Conference on Robotics and Automation (ICRA), 2025

[paper] [poster]

Kaiqu Liang, Zixu Zhang, Jaime F. Fisac

Introspective Planning: Aligning Robots' Uncertainty with Inherent Task Ambiguity

Neural Information Processing Systems (NeurIPS), 2024

[paper] [code] [homepage]

Justin Wang, Haimin Hu, Duy P. Nguyen, Jaime F. Fisac

MAGICS: Adversarial RL with Minimax Actors Guided by Implicit Critic Stackelberg for Convergent Neural Synthesis of Robot Safety

Workshop on the Algorithmic Foundations of Robotics (WAFR), 2024

[paper] [video]

Duy P. Nguyen*, Kai-Chieh Hsu*, Wenhao Yu, Jie Tan, Jaime Fernández Fisac

Gameplay Filters: Robust Zero-Shot Safety through Adversarial Imagination

Conference on Robot Learning (CoRL), 2024

[paper] [homepage] [code] [poster]

Haimin Hu*, Gabriele Dragotto*, Zixu Zhang, Kaiqu Liang, Bartolomeo Stellato, Jaime Fernández Fisac

Who Plays First? Optimizing the Order of Play in Stackelberg Games with Many Robots

Robotics: Science and Systems (RSS), 2024

[paper] [homepage] [code]

Justin Lidard*, Haimin Hu*, Asher Hancock, Zixu Zhang, Albert Gimó Contreras, Vikash Modi, Jonathan DeCastro, Deepak Gopinath, Guy Rosman, Naomi Ehrich Leonard, María Santos, Jaime Fernández Fisac

Blending Data-Driven Priors in Dynamic Games

Robotics: Science and Systems (RSS), 2024

[paper] [homepage] [code]

Kai-Chieh Hsu, Haimin Hu, Jaime F. Fisac

The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systems

Annual Review of Control, Robotics, and Autonomous Systems, 2024

[paper]

Haimin Hu, David Isele, Sangjae Bae, Jaime F. Fisac

Active Uncertainty Reduction for Safe and Efficient Interaction Planning: A Shielding-Aware Dual Control Approach

The International Journal of Robotics Research (IJRR), 2023

[paper] [homepage]

Haimin Hu*, Zixu Zhang*, Kensuke Nakamura, Andrea Bajcsy, and Jaime F. Fisac

Deception Game: Closing the Safety-Learning Loop in Interactive Robot Autonomy

Conference on Robot Learning (CoRL), 2023

[paper] [code] [homepage]

Athindran Ramesh Kumar, Kai-Chieh Hsu, Peter J. Ramadge, and Jaime F. Fisac

Fast, Smooth, and Safe: Implicit Control Barrier Functions Through Reach-Avoid Differential Dynamic Programming

IEEE Control Systems Letters, 2023

[paper] [code] [homepage]

Haimin Hu, Kensuke Nakamura, Kai-Chieh Hsu, Naomi Ehrich Leonard, and Jaime F. Fisac

Emergent Coordination through Game-Induced Nonlinear Opinion Dynamics

IEEE Conference on Decision and Control (CDC), 2023

[paper] [code] [homepage]

Kai-Chieh Hsu, Karen Leung, Yuxiao Chen, Jaime F. Fisac, and Marco Pavone

Interpretable Trajectory Prediction for Autonomous Vehicles via Counterfactual Responsibility

IEEE/RSJ Int. Conf. on Intelligent Robots & Systems, 2023

[paper] [homepage]

Kai-Chieh Hsu, Duy P. Nguyen, and Jaime F. Fisac

ISAACS: Iterative Soft Adversarial Actor Critic for Safety

The 5th Conference on Learning for Dynamics and Control (L4DC), 2023

[paper] [code] [homepage]

Kai-Chieh Hsu, Allen Z. Ren, Duy P. Nguyen, Anirudha Majumdar, and Jaime F. Fisac

Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guarantees

Artificial Intelligence Journal (AIJ), 2022

[paper] [code] [poster] [homepage]

Haimin Hu and Jaime F. Fisac

Active Uncertainty Reduction for Human-Robot Interaction: An Implicit Dual Control Approach

Algorithmic Foundations of Robotics XV (WAFR), 2022.

[paper] [talk] [code] [homepage]

Haimin Hu, Kensuke Nakamura and Jaime F. Fisac

SHARP: Shielding-Aware Robust Planning for Safe and Efficient Human-Robot Interaction

IEEE Robotics and Automation Letters (RA-L), 2022.

[paper] [talk] [code] [poster] [homepage]

Kai-Chieh Hsu*, Vicenç Rubies-Royo*, Claire J. Tomlin and Jaime F. Fisac

Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learning

Robotics: Science and Systems (RSS), 2021

[paper] [talk] [code] [poster] [homepage]

Zixu Zhang and Jaime F. Fisac

Safe Occlusion-aware Autonomous Driving via Game-Theoretic Active Perception

Robotics: Science and Systems (RSS), 2021

[paper] [talk] [code] [homepage]