Yantian was born in Nanjing, China. While Yantian started learning piano at three years old (and eventually obtained his 10-Level Piano Certificate), Yantian is committed to Robotics (which is one of Yantian’s childhood dreams). Yantian’s robotics journey truly set out when he was an undergrad, worked with Prof. Xudong Ma and Prof. Kun Qian at the Institute of Intelligent Robotics and Intelligent Control, Southeast University. After that, Yantian went to Arizona State University and had a delighted Ph.D. life with his advisor Prof. Subbarao Kambhampati (Rao) (as clearly seen from the title of Yantian’s Ph.D. Thesis). Recently, Yantian becomes a Postdoctoral Associate and Adjunct Lecturer, collaborating with Prof. Miao Yu, Prof. Bala Balachandran, Prof. Yiannis Aloimonos, Dr. Cornelia Fermüller, Prof. Ming Lin, and Prof. Tianyi Zhou at the University of Maryland, College Park.
Research Interest:
Yantian is interested in Cognitive Robot Learning – how different levels of cognitive functions like perception, acting, planning, and metacognition, can be tightly coupled to achieve human-level intelligence for robots.
Teaching:
2023 Spring: ENPM808Z Cognitive Robotics
2023 Fall: CMSC421 Introduction to Artificial Intelligence
2024 Spring: CMSC848J & ENPM808Z Cognitive Robotics
Please feel free to contact Yantian via ytzha at umd dot edu or LinkedIn. For students who contact me and look for my supervision, I promise to read your emails. I would appreciate it if you could mention which of my papers or research directions you are interested in; please also feel free to suggest any other research directions that you would like us to explore together.
News!
12/02/2024: Our paper “NatSGLD: A Dataset with Speech, Gestures, Logic, and Demonstrations for Robot Learning in Natural Human-Robot Interaction is accepted by HRI-25. Thanks to my collaborators!
08/22/24: I gave a faculty talk at the Maryland Research Day event
07/10/2024: Our paper “Task Success” is not Enough: Investigating the Use of Video-Language Models as Behavior Critics for Catching Undesirable Agent Behaviors is accepted by COLM-24. Thanks to my collaborators!
07/03/2024: I gave an invited talk at the Robotics Institute at Carnegie Mellon University: “Cognitively-Enhanced Robotic Manipulation across Sea, Air, and Land”
05/23/2024: I gave a faculty talk at Maryland Robotics Center Research Symposium 2024
12/09/2023: Our paper Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning is accepted by AAAI-24 Main Track. Thanks to my collaborators!
07/2023: Excited to announce our workshop Bridging the Gap between Cognitive Science and Robot Learning in the Real World: Progresses and New Directions at CoRL-23. Many thanks to my co-organizers!
04/2022: I am a recipient of the Maryland Robotics Center Postdoctoral Fellowship at the Institute for Systems Research (ISR), University of Maryland, 2022-2023.
06/30/2021: Our paper Contrastively Learning Visual Attention as Affordance Cues from Demonstrations for Robotic Grasping is accepted by IROS 2021. Thanks to my collaborators!
04/30/2021: I am awarded the CIDSE Doctoral Fellowship by ASU.
03/2020 - 08/2020: Worked as a robotics research intern at ABB, Raleigh advised by Dr. Jianjun Wang.
Publications
NatSGLD: A Dataset with Speech, Gestures, Logic, and Demonstrations for Robot Learning in Natural Human-Robot Interaction
Snehesh Shrestha, Yantian Zha, Ge Gao, Cornelia Fermuller, and Yiannis Aloimonos
IEEE/ACM International Conference on Human-Robot Interaction (Data Paper), 2025
Media: [Project]
Task Success is not Enough: Investigating the Use of VideoLanguage Models as Behavior Critics for Catching Undesirable Agent Behaviors
Lin Guan, Yifan Zhou, Denis Liu, Yantian Zha, Heni Ben Amor, Subbarao Kambhampati
Conference on Language Modeling 2024
Media: [Project]
Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning
Yantian Zha, Lin Guan, Subbarao Kambhampati
AAA-24 Main Track & AAAI-22 Workshop on Reinforcement Learning in Games 2022.
Media: [Website] [Slides]
Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systems
Subbarao Kambhampati, Sarath Sreedharan, Mudit Verma, Yantian Zha, Lin Guan
AAAI Blue Sky Paper (Senior Member Presentation Track) 2022.
Contrastively Learning Visual Attention as Affordance Cues from Demonstrations for Robotic Grasping
Yantian Zha, Siddhant Bhambri, and Lin Guan
The IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2021.
Media: [Project] [IROS_Talk] [Slides]
Plan-Recognition-Driven Attention Modeling for Visual Recognition
Yantian Zha, Yikang Li, Tianshu Yu, Subbarao Kambhampati and Baoxin Li
AAAI 2019 Workshop on Plan, Activity, and Intent Recognition (PAIR).
Recognizing plans by learning embeddings from observed action distributions
Yantian Zha, Yikang Li, Sriram Gopalakrishnan, Baoxin Li, and Subbarao Kambhampati
In Proceedings of International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2018.
Media: [Full Paper] [Code] [Slides] [Poster]
Discovering Underlying Plans Based on Shallow Models
Hankz Hankui Zhuo, Yantian Zha, Subbarao Kambhampati, and Xin Tian
In Proceedings of ACM Transactions on Intelligent Systems and Technology (ACM-TIST) 2019.
Media: [Code]
Explicability as Minimizing Distance from Expected Behavior
Anagha Kulkarni, Yantian Zha, Tathagata Chakraborti, Satya Gautam Vadlamudi, Yu Zhang and Subbarao Kambhampati
In Proceedings of International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2019.
Media: [Full Paper] [Demo Video]