Interview with Haimin Hu: Recreation-theoretic integration of security, interplay and studying for human-centered autonomy

On this interview sequence, we’re assembly a number of the AAAI/SIGAI Doctoral Consortium contributors to search out out extra about their analysis. On this newest interview, Haimin Hu tells us about his analysis on the algorithmic foundations of human-centered autonomy and his plans for future initiatives, and offers some recommendation for PhD college students trying to take the subsequent step of their profession.

May you give us an summary of the analysis you carried out throughout your PhD?

My PhD analysis, performed below the supervision of Professor Jaime Fernández Fisac within the Princeton Protected Robotics Lab, focuses on the algorithmic foundations of human-centered autonomy. By integrating dynamic sport principle with machine studying and safety-critical management, my work goals to make sure autonomous methods, from self-driving autos to drones and quadrupedal robots, are performant, verifiable, and reliable when deployed in human-populated house. The core precept of my PhD analysis is to plan robots’ movement within the joint house of each bodily and data states, actively making certain security as they navigate unsure, altering environments and work together with people. Its key contribution is a unified algorithmic framework—backed by sport principle—that enables robots to soundly work together with their human friends, adapt to human preferences and targets, and even assist people refine their expertise. Particularly, my PhD work contributes to the next areas in human-centered autonomy and multi-agent methods:

• Reliable human–robotic interplay: Planning protected and environment friendly robotic trajectories by closing the computation loop between bodily human-robot interplay and runtime studying that reduces the robotic’s uncertainty in regards to the human.
• Verifiable neural security evaluation for advanced robotic methods: Studying strong neural controllers for robots with high-dimensional dynamics; guaranteeing their training-time convergence and deployment-time security.
• Scalable interactive planning below uncertainty: Synthesizing game-theoretic management insurance policies for advanced and unsure human–robotic methods at scale.

Was there a challenge (or facet of your analysis) that was notably attention-grabbing?

Security in human-robot interplay is very tough to outline, as a result of it hinges on an, I’d say, virtually unanswerable query: How protected is protected sufficient when people may behave in arbitrary methods? To offer a concrete instance: Is it enough if an autonomous car can keep away from hitting a fallen bicycle owner 99.9% of the time? What if this price can solely be achieved by the car at all times stopping and ready for the human to maneuver out of the way in which?

I’d argue that, for reliable deployment of robots in human-populated house, we have to complement commonplace statistical strategies with clear-cut strong security assurances below a vetted set of operation circumstances as nicely established as these of bridges, energy crops, and elevators. We want runtime studying to reduce the robotic’s efficiency loss attributable to safety-enforcing maneuvers; this requires algorithms that may cut back the robotic’s inherent uncertainty induced by its human friends, for instance, their intent (does a human driver need to merge, lower behind, or keep within the lane?) or response (if the robotic comes nearer, how will the human react?). We have to shut the loop between the robotic’s studying and decision-making in order that it might optimize effectivity by anticipating how its ongoing interplay with the human might have an effect on the evolving uncertainty, and in the end, its long-term efficiency.

What made you need to examine AI, and the realm of human-centered robotic methods specifically?

I’ve been fascinated by robotics and clever methods since childhood, after I’d spend complete days watching sci-fi anime like Cellular Swimsuit Gundam, Neon Genesis Evangelion, or Future GPX Cyber System. What captivated me wasn’t simply the futuristic expertise, however the imaginative and prescient of AI as a real companion—augmenting human talents reasonably than changing them. Cyber System specifically planted the concept of human-AI co-evolution in my thoughts: an AI co-pilot that not solely helps a human driver navigate high-speed, high-stakes environments, but in addition adapts to the driving force’s fashion over time, in the end making the human a greater racer and deepening mutual belief alongside the way in which. Right now, throughout my collaboration with Toyota Analysis Institute (TRI), I work on human-centered robotics methods that embody this precept: designing AI methods that collaborate with folks in dynamic, safety-critical settings by quickly aligning with human intent by multimodal inputs, from bodily help to visible cues and language suggestions, bringing to life the very concepts that after lived in my childhood creativeness.

You’ve landed a college place at Johns Hopkins College (JHU) – congratulations! May you speak a bit in regards to the means of job looking, and maybe share some recommendation and insights for PhD college students who could also be at an identical stage of their profession?

The job search was positively intense but in addition deeply rewarding. My recommendation to PhD college students: begin pondering early in regards to the type of long-term affect you need to make, and act early in your software bundle and job speak. Additionally, be sure to speak to folks, particularly your senior colleagues and friends on the job market. I personally benefited rather a lot from the next sources:

Do you’ve an thought of the analysis initiatives you’ll be engaged on at JHU?

I want to assist create a future the place people can unquestionably embrace the presence of robots round them. In direction of this imaginative and prescient, my lab at JHU will examine the next subjects:

• Uncertainty-aware interactive movement planning: How can robots plan protected and environment friendly movement by accounting for his or her evolving uncertainty, in addition to their potential to cut back it by future interplay, sensing, communication, and studying?
• Human–AI co-evolution and co-adaptation: How can embodied AI methods study from human teammates whereas serving to them refine present expertise and purchase new ones in a protected, customized method?
• Protected human-compatible autonomy: How can autonomous methods guarantee prescribed security whereas remaining aligned with human values and attuned to human cognitive limitations?
• Scalable and generalizable strategic decision-making: How can multi-robot methods make protected, coordinated selections in dynamic, human-populated environments?

How was the expertise attending the AAAI Doctoral Consortium?

I had the privilege of attending the 2025 AAAI Doctoral Consortium, and it was an extremely beneficial expertise. I’m particularly grateful to the organizers for curating such a considerate and supportive atmosphere for early-career researchers. The spotlight for me was the mentoring session with Dr Ming Yin (postdoc at Princeton, now school at Georgia Tech CSE), whose insights on navigating the unsure and aggressive job market have been each encouraging and eye-opening.

May you inform us an attention-grabbing (non-AI associated) truth about you?

I’m obsessed with snowboarding. I realized to ski primarily by vision-based imitation studying from a chairlift, although I’m positively paying the value now for poor generalization! In the future, I hope to construct an exoskeleton that teaches me to ski higher whereas maintaining me protected on the double black diamonds.

About Haimin

Haimin Hu is an incoming Assistant Professor of Pc Science at Johns Hopkins College, the place he’s additionally a member of the Knowledge Science and AI Institute, the Institute for Assured Autonomy, and the Laboratory for Computational Sensing and Robotics. His analysis focuses on the algorithmic foundations of human-centered autonomy. He has acquired a number of awards and recognitions, together with a 2025 Robotics: Science and Techniques Pioneer, a 2025 Cyber-Bodily Techniques Rising Star, and a 2024 Human-Robotic Interplay Pioneer. Moreover, he has served as an Affiliate Editor for IEEE Robotics and Automation Letters since his fourth yr as a PhD scholar. He obtained a PhD in Electrical and Pc Engineering from Princeton College in 2025, an MSE in Electrical Engineering from the College of Pennsylvania in 2020, and a BE in Digital and Data Engineering from ShanghaiTech College in 2018.