InterACT

Jump to: "Becoming a Member"

Faculty

Anca Dragan
Anca is an Assistant Professor in the EECS Department at UC Berkeley. She founded the InterACT lab, and helped found the Berkeley AI Research (BAIR) lab. She obtained her PhD from the Robotics Institute at Carnegie Mellon University.

PhD Students

	Jerry Zhi-Yang He Jerry is a PhD student in EECS. He wants to build household robots that interact with humans while perfoming a wide range of tasks. To that end, he is interested in algorithms that can learn from all forms of human inputs, including desmontrations, reward designs, vision as well as language feedbacks.
	Micah Carroll Micah Carroll is a PhD student in EECS co-advised with Stuart Russell. His research investigates what AI Alignment should entail when aligning to changing and influenceable humans. In particular, he has worked on formally characterizing manipulation, and on the effects algorithmic choices in recommender systems.
	Jessy Lin Jessy is a PhD student in EECS co-advised with Dan Klein. She is interested in building agents that can collaborate and interact with humans, and use language as a medium to do so.
	Cassidy Laidlaw Cassidy is a PhD student in EECS co-advised with Stuart Russell. Cassidy is interested in human-AI cooperation, machine learning safety and robustness, and bridging the theory-practice gap in reinforcement learning.
	Erik Jones Erik is a PhD student in EECS co-advised with Jacob Steinhardt. He works on developing automated ways to make generative machine learning systems more robust, reliable, and aligned, with a focus on large language models.
	Joey Hong Joey is a PhD student in EECS co-advised with Sergey Levine. Joey currently works on offline reinforcement learning.
	Vivek Myers Vivek is a PhD student in EECS co-advised with Sergey Levine. His research interests include robot learning, human-robot interaction, and reinforcement learning.
	Eli Bronstein Eli is a PhD student in EECS interested in creating AI systems that learn from and interact with people, leveraging machine learning, reinforcement learning, and optimization Previously, Eli was an undergraduate student in InterACT working on game-thoretic driving.

RAs

Davis Foote
Davis is a research assistant at the Center for Human-Compatible Artificial Intelligence (CHAI) and the Interactive Agents and Collaborative Technologies Laboratory (InterACT) at UC Berkeley. His research is focused on formally investigating model misspecification in reward learning systems (especially misspecified models of human preferences and decision-making), identifying specific failure modes that result, and developing algorithmic approaches to mitigate them.

Undergraduate Students

	Evan Ellis Evan is an undergraduate student in EECS.
	Owen Gozali Owen is an undergraduate student in EECS.
	Pruthvi Innamuri Pruthvi is an undergraduate student in EECS.
	Kishore Chidambaram Kishore is an undergraduate student in EECS.

Alumni (PhD/Postdoc):

	Dorsa Sadigh (prof. at Stanford) Dorsa worked on enabling robots to better coordinate with people by accounting for the influence they ahve on human actions. She is currently an Assistant Professor at Stanford University.
	Jaime Fisac (prof. at Princeton) Jaime completed his PhD in EECS in 2019. After spending a year as a Research Scientist at Waymo (formerly known as Google’s Self-Driving Car project), he is joining Princeton an Assistant Professor of Electrical Engineering. He’s interested in ensuring the safe operation of robots in complex and uncertain environments, especially around people.
	Sandy Huang (research scientist at DeepMind) Sandy worked on enabling robot transparency and helping users attain a good mental model of how the robot acts through informative behaviors. She is current a Research Scientist at Deep Mind.
	Dylan Hadfield-Menell (prof. at MIT) Dylan's research is on value alignment and enabling robots and AI agents to be robust to misspecified objectives Dylan is currently an Assistant Professor at MIT.
	Rohin Shah (research scientist at DeepMind) While Rohin's general interests in CS are very broad, including AI, machine learning, programming languages, complexity theory, algorithms, and security, he was convinced that it is really important for us to build safe, aligned AI. His research focuses on how to provide specifications of good behavior in ways other than reward functions, especially ones that do not require much human effort. He is currently a Research Scientist at DeepMind.
	Andrea Bajcsy (prof. at CMU) Andrea was a PhD student in EECS. She is broadly interested in the intersection of robotics, control theory, machine learning, and human-robot interaction. Much of her research focuses on combining data-driven human models and control theoretic-tools to develop robust human motion predictors and safe motion planners for robots operating in close physical proximity to people.
	Daniel Brown (prof. at Utah) Daniel was a postdoc at UC Berkeley, co-advised by Anca Dragan and Ken Goldberg. His research interests include imitation learning, reward inference, AI safety, and multi-agent systems. He recently received his Ph.D. in computer science from the University of Texas at Austin, where he worked with Scott Niekum on safe imitation learning. Prior to starting his PhD, Daniel worked for the Air Force Research Lab's Information Directorate where he studied bio-inspired swarms and multi-agent planning.
	Erdem Biyik (prof. at USC) Broadly, Erdem is interested in artificial intelligence for robotics. In his research, he uses tools from machine learning, artificial intelligence, optimization, game theory, robotics, information theory, and cognitive science.
	Andreea Bobu (prof. at MIT) Andreea is a PhD student in EECS. Her interests lie broadly at the intersection of machine learning, robotics, and human-robot interaction. Her research tackles ways in which autonomous systems’ models of the world and of other agents (e.g. humans) can go wrong, and improve them for enhanced interaction between people and robots.
	Kush Bhatia (postdoc at Stanford) Kush was a PhD student in EECS. He is interested in problems at the intersection of statistics, optimization and machine learning, in particular on aspects of aligning the objectives of the ML models with those of humans.
	Ellis Ratner (Waymo) Ellis was a PhD student in EECS. He researches planning and decision making algorithms for robotic systems. Recently, he has focused on developing algorithms for efficient planning under uncertainty using graph search methods.
	Smitha Milli (postdoc at Cornell Tech) Smitha was a PhD student in EECS. They are focused on making ML systems more reliable and robust. They are particularly interested in how to use interaction with humans to ensure that a system has learned the right objective or behavior.
	Sid Reddy (startup) Sid was a PhD student in EECS. His goal is to accelerate the advent of intelligent robotic assistants, like brain-computer interfaces for prosthetic limb control and guidance systems for visually-impaired users. His research develops machine learning algorithms for augmenting human control and inferring models of human beliefs, preferences, and behavior.
	Mariah Schrum (research scientist at TRI) Mariah was a postdoc working on applying reinforcement learning techniques to real-world settings, with a focus on reinforcement learning for deep brain stimulation.
	Lawrence Chan Lawrence is a PhD student in EECS. He focuses on learning human objectives despite systematic human biases. Lawrence is also an undergraduate alumn of the lab.

Alumni (undergrad/MS):

	Gokul Swamy (CMU) Gokul was an undergraduate and masters student in EECS. He is generally interested in systems, robotic or otherwise, that can learn effectively from data generated via interaction with people. He is especially excited about incorporating these sorts of systems in a scalable manner into personal robots. He is currently a PhD student at CMU RI.
	Ravi Pandya (CMU) Ravi was an undergraduate and masters student in InterACT working on how physical actions can communicate and gather information.
	Allan Zhou (Stanford) Allan was an undergraduate student in InterACT working on robot motion with style.
	Minae Kwon (Stanford) Minae was an undergraduate student in InterACT working on communicating incapability.
	Nick Landolfi (Stanford) Nick Landolfi was an undergraduate student in InterACT working on control for autonomous cars that interact with people and robot arms that infer human intent.
	Jason Zhang (CMU) Jason was an undergraduate student in InterACT working on learning from corrections.
	Hong Jun Jeon (Stanford) Hong was an undergraduate student in InterACT working on natural robot motion.
	Malayandi (Andy) Palaniappan (Stanford) Andy was an undergraduate student in InterACT working on human-robot collaboration.
	Dhruv Malik (Berkeley) Dhruv was an undergraduate student in InterACT working on human-robot collaboration.
	McKane Andrus (Partnership for AI) McKane was an undergraduate and masters student in InterACT working on the cooperative control of robots. He is a Research Associate at the Partnership for AI.
	Jensen Gao (Stanford) Jensen was an undergraduate student in EECS.

	Steven Wang (CHAI research engineer) Steven was an undergraduate student in InterACT working on detecting human model misspecification.
	Glen Chou (U Michigan) Glen was a part of the Interact Lab while an undergraduate student at UC Berkeley. He is currently a PhD student at the University of Michigan.
	Stephen Hansen (now at Freedom Robotics) Stephen obtained his Master's degree in EECS with the InterACT lab. He is now the head of robotics at Freedom Robotics.
	Xiaocheng Mesut Yang Mesut is a Master's student in EECS.
	Matthew Zurek Matthew was an undergraduate student in EECS.
	Sean Chen Sean was an undergraduate student in EECS.
	Nathan Miller Nathan was an undergraduate student in EECS.
	Avik Jain Avik was an undergraduate student in EECS.
	Arjun Sripathy Arjun was an undergraduate student in EECS.
	Sebastian Zhao Sebastian was an undergraduate student in EECS.
	Yike Wang Yike was an undergraduate student in EECS.
	Arvind Rajaraman Arvind was an undergraduate student in EECS.
	Michelle Pan Michelle was an undergraduate student in EECS.
	Jeremy Tien Jeremy was an undergraduate student in EECS.
	Sashrika Pandey Sashrika was a Master's student in EECS interested in developing AI systems tailored towards user interaction and experience.
	Shivam Singhal Shivam was a Master’s student in EECS interested in AI alignment and human-AI collaboration.

Collaborators:

Pieter Abbeel
Ken Goldberg
Stuart Russell
Shankar Sastry
Claire Tomlin
Sanjit Seshia
Ruzena Bajcsy
Tom Griffiths
Trevor Darrell
Peter Bartlett
Sergey Levine
Moritz Hardt

Becoming a Member:

Berkeley graduate students: Send email to Anca! Also, it will be useful to take the Algorithmic Human-Robot Interaction course.
Perspective graduate students: We would love to talk to you after you get admitted. Please apply to the CS (or EECS) PhD program under the AI (or CIR) areas.
Berkeley undergraduate students: Send email to Anca summarizing your project experience, what areas from our Research page you are interested in, and how much time you are able to commit. Attach you transcript and resume.
Non-Berkeley undergraduate students: Unfortunately, we do not offer internships to non-Berkeley undergraduates.