![[Annotated] Two of four quadrants of the task environment to study referring behaviors for linguistic HRI. Two rule cards are placed on each table, with learners' on the left hand side and instructors' (dashed box) on the right hand side (solid box). Objects are intentionally placed at the intersections of a 3×3 grid to encourage use of different referring forms whose use varies according to distance. Instructors teach learners to construct buildings whose constituents blocks are distributed across the visible and non-visible quadrants.](https://i0.wp.com/zhaohanphd.com/uploads/2022/01/Two-of-four-quadrants-of-the-task-environment-to-study-referring-behaviors-for-linguistic-HRI-annotated.jpg?resize=750%2C563&ssl=1 "Two of four quadrants of the task environment to study referring behaviors for linguistic HRI annotated")
Dr. Zhao Han’s research interests lie in human-robot interaction (HRI), augmented reality (AR), robotics, and artificial intelligence (AI). His goal is to develop capable and understandable robotic systems and interactions with humans.
For advancing this work, Dr. Han and his collaborators design, implement and experiment with proactive interactions, causal and preferred robot explanations, explanation generation using interpretable behavior trees, mobile manipulation (perception, manipulation, and navigation) algorithms, multimodal communications, headset-free projection mapping augmented reality (AR), behavioral and cognitive insights from psychology, and more.
These novel interactions and prototypes are evaluated in different domains and contexts with rigorous quantitative and qualitative human-subjects studies, including integrated mobile manipulation, human-robot handovers, teleoperation (mental workload), assistive robotics, as well as during robot failures and with ethical considerations.
Previously in his M.S. thesis, he investigated frequent itemset mining for non-experts using cloud computing and novel visualization, a subfield of data mining.
Contents
Expertise
- Robot explanation, explainable AI (XAI) (AI-HRI ’19, ICRA ’20 WS, THRI ’21a, THRI ’21b, Ph.D. Dissertation, AAAI-SSS ’22, WYSD ’22, THRI ’22b)
- Preferences (THRI ’21b), generation algorithms (THRI ’21a), survey (AI-HRI ’19)
- Mobile manipulation, research testbed (ICRA ’19 FetchIt Competition, ICRA ’20)
- Augmented reality (AR)
- Projector-based AR, projection mapping (AI-HRI ’20, THRI ’21a, Paladyn ’21, HRI ’22b, AI-HRI ’22)
- Head-worn AR (VAM-HRI ’22, THRI ’22a, HRI ’23a)
- Natural language generation — referring form selection (HRI ’22 LBR, INLG ’22, IROS ’22)
- Robot failures (ICRA ’20 WS, THRI ’21a, THRI ’21b, WYSD ’22)
- Assistive robotics
- Human-robot handovers (HRI ’19, ICRA ’20 WS, THRI ’21b)
- Proactive release (HRI ’19), handover failures (ICRA ’20 WS, THRI ’21b)
- Robotic wheelchair (Paladyn ’21)
- Human-robot handovers (HRI ’19, ICRA ’20 WS, THRI ’21b)
- Robot competition (ICRA ’19 FetchIt Competition, Panasonic Challenge ’20, ICRA ’20)
- Robot task representation — behavior trees (BTs) (THRI ’21a, WYSD ’22)
- Robot ethics (HRI ’22a, HRI ’23b)
- Mental workload — teleoperation (ICRA ’21)
- Cognitive architecture (IROS ’20)
- Open science — code (AI-HRI ’20, HRI ’22b)
- Data visualization, visual analytics (WI ’16)
- Data mining — frequent itemset mining (KES ’15, BigDAS ’15, M.S. Thesis)
Human-Robot Interaction (HRI)
Developing understandable robot interactions with humans
HRI
Robotics
Developing capable robotic systems in human environments
Robotics
Artificial Intelligence (AI)
Developing human-centered AI algorithms to facilitate HRI
AI
Augmented Reality (AR)
Developing salable projected AR without headsets
AR
Robot Competitions
Dr. Han has a deep software development background, especially ROS, and is skilled at project management.
During his Ph.D., he has proposed, budgeted, and led three teams of students, researchers, and engineers to win
- first place in the Panasonic Prototype 3D LiDAR Challenge (detect and grasp small objects from sparse 3D LiDAR data),
- second place in the FetchIt Mobile Manipulation Challenge at ICRA (autonomous navigation and manipulation to build assemblies from irregular objects),
- and selected as a finalist to secure seed funding in the ADI Real-Time Sensor Fusion Challenge (human-aware projection mapping to externalize robot intent).
ADI Real-Time Sensor Fusion Challenge
In this challenge, we proposed an augmented reality (AR) project titled “Human-Aware Projection Mapping for Robot Intention”. Leading a team of three, we were awarded $2,500 seed funding and this project led to two scientific publications. Competition Proposal Robots are now increasingly deployed in areas ranging from factories and warehouses to private homes. Externalizing a……
Panasonic Prototype 3D LiDAR Challenge
Competition Proposal In a factory or warehouse, if a mechanical part (e.g., a small gear) is accidentally left on the floor — or a robot dropped an item while operating — it may end up in the path of another robot (e.g., autonomous mobile robot, or AMR, delivering items). The robot may not be able……
FetchIt Mobile Manipulation Challenge at ICRA 2019
In the competition, a Fetch mobile manipulator robot autonomously navigates to stations in a narrow work cell to pick parts in irregular shape (screws, gears, gearbox parts) and machine large gears by inserting into a narrow chuck, transport and place them into a human-friendly caddy, and drop off the caddy on a specified region at……
Organizers and sponsors
