Human-Centered Physical AI and Trustworthy Autonomous Systems - College of Engineering - Purdue University

Project Description

Future autonomous systems must operate safely and naturally alongside humans in complex, dynamic environments. This project aims to develop next-generation Physical AI by integrating model-based control and optimization with foundation models and generative AI to enable trustworthy autonomy. The research will investigate new algorithms for motion planning, decision making, and human-autonomy teaming that simultaneously satisfy hard safety and dynamic constraints while producing human-compatible behaviors. The resulting framework will be validated on real robotic and autonomous vehicle platforms and generalized across multiple embodied AI domains, including autonomous driving, collaborative robotics, and intelligent manufacturing. The project combines rigorous control theory with modern AI to advance deployable Physical AI systems that are safe, adaptive, and explainable.

Start Date

January 1, 2027

Postdoc Qualifications

Candidates should hold a Ph.D. in Robotics, Computer Science, Electrical Engineering, Mechanical Engineering, Civil Engineering, or a closely related field by the start of the appointment. The ideal candidate will have demonstrated expertise in robotics, autonomous systems, motion planning, control, optimization, machine learning, or foundation models, with a strong publication record in leading conferences and journals. Experience with generative AI, world models, reinforcement learning, human-autonomy teaming, ROS/ROS2, or real-world robotic systems is highly desirable. Applicants should be excited to conduct interdisciplinary research at the intersection of Physical AI, robotics, and human-centered autonomous systems, and to collaborate across multiple research groups. This description aligns well with Sixu's background in combining model-based control, optimization, and learning for trustworthy autonomous systems. 

Co-advisors

Ziran Wang, ziran@purdue.edu, Lyles School of Civil and Construction Engineering, https://ziranw.github.io/.

Aniket Bera, aniketbera@purdue.edu, Department of Computer Science, https://www.cs.purdue.edu/homes/ab/.

Bibliography

Cui, C., Ma, Y., Ye, W., & Wang, Z. Drive as You Speak: Enabling Human-Like Interaction with Large Language Models in Autonomous Vehicles. IEEE/CVF WACV, 2024.

Ma, Y., et al. LaMPilot: An Open Benchmark Dataset for Autonomous Driving with Language Model Programs. CVPR, 2024.

Cui, C., et al. On-board Vision-Language Models for Personalized Autonomous Vehicle Motion Control: System Design and Real-World Validation. arXiv, 2024.

Daiya, D., Conover, D., & Bera, A. COLLAGE: Collaborative Human-Agent Interaction Generation using Hierarchical Latent Diffusion and Language Models. IEEE International Conference on Robotics and Automation (ICRA), 2025. IDEAS Lab

Gupta, P., Verma, S., Grama, A., & Bera, A. Unified Multi-Modal Interactive and Reactive 3D Motion Generation via Rectified Flow. International Conference on Learning Representations (ICLR), 2026.