The 1st Workshop @ IROS on

Embodied AI and Robotics for Future Scientific Discovery

📅

Date

October 24, 2025

🕐

Time

9:00 AM - 1:00 PM (GMT+8)

📍

Location

210A

🔗

Join Zoom Meeting

Click to Join Meeting

Meeting ID: 953 5652 9482 | Passcode: 249906



The accelerating pace of scientific research demands more efficient, accurate, and comprehensive methodologies that can transcend the limitations of traditional research approaches. Current scientific practices face significant challenges: manual experimentation is time-consuming and resource-intensive, while multidisciplinary research requires integration of knowledge that often exceeds individual researchers' expertise. This workshop explores a transformative vision: the development of embodied AI systems capable of conducting end-to-end scientific research across multiple disciplines. Recent advances in embodied AI and robotics present unprecedented opportunities to evolve from purely virtual AI scientists to embodied robotic researchers that can actively engage in a complete research lifecycle. This workshop brings together experts from robotics, AI, and various scientific domains to discuss the development of systems that can autonomously perform the scientific research lifecycle, literature reviews, generate hypotheses, conduct physical experiments, and synthesize findings into scholarly manuscripts.

Organizers

UoT iit Harvard GeorTech ZJU TU


The workshop will chart a transformative path: from traditional human-led research to collaborative AI scientists and Robot scientists working alongside humans, and ultimately to fully autonomous AI and Robot scientists with capabilities. This developmental roadmap will help identify key technological barriers and research opportunities in creating embodied AI and Robotic systems capable of revolutionary scientific breakthroughs.

What is Embodied AI and Robotic for future scientifc discovery ?

see this table below:


Content

Topics

The workshop aims to address critical challenges and implications, including technological limitations, ethical considerations, and the changing landscape of scientific training. By fostering dialogue between researchers and practitioners, we aim to establish a roadmap for developing truly autonomous generalist scientist that can help address complex global challenges.

  • Advanced AI agents and algorithms for each stage of autonomous scientific research, including:
  • Operating system agents with advanced computing capabilities for scientific research automation
  • Domain-specific robotic systems designed for autonomous experimentation in targeted scientific fields
  • Embodied AI systems with dexterous manipulation capabilities, incorporating:
    • Foundation models for perception and reasoning
    • Advanced robotic hardware for precise manipulation
    • Multi-modal sensing and interaction
    • Real-world adaptation and learning
  • Comprehensive datasets and benchmarks for:
    • AI-driven scientific discovery
    • Robotic manipulation in laboratory settings
  • Performance evaluation frameworks for AI agent and robot-based autonomous scientific systems
  • Broader impacts and ethical considerations


The workshop will also address critical challenges and implications, including technological limitations, ethical considerations, and the changing landscape of scientific training. By fostering dialogue between researchers and practitioners, we aim to establish a roadmap for developing truly autonomous generalist scientist that can help address complex global challenges.

Schedule [PDF]


Time Zone: GMT+08

Time Activity Comments
09:00 - 09:10 Opening remarks and introduction Introduction
09:10 - 09:25 Invited Talk 1 Dr. Pulkit Agrawal and Dr. Hong
09:25 - 09:40 Invited Talk 2 Dr. James Zou
09:40 - 10:00 Invited Talk 3 Dr. Markus J. Buehler
10:00 - 10:15 Invited Talk 4 CEO Wang Xingxing
10:15 - 10:30 Invited Talk 5 Dr. Yuquan Wang
10:30 - 10:50 Invited Talk 6 Dr. Hirotaka Sugiura
10:50 - 11:15 Coffee break & Poster session Open discussion & Networking
11:15 - 11:35 Invited Talk 7 Dr. Kanako Harada
11:35 - 11:50 Perspective Talk 8 Dr. David Scott Lewis
11:50 - 12:05 Perspective Talk 9 VC Kedi Cui
12:05 - 12:25 Invited Talk 10 Dr. Josie Hughes
12:25 - 12:40 Invited Talk 11 Dr. Di Fu
12:40 - 12:50 Awards ceremony Best paper awards
12:50 - 13:00 Closing remarks Summary, Thanks

Call for papers

Topic of Interest

  • AI Scientists and Robot Scientists
  • Al for Science: Nature, Formal, Social, Applied, Interdisciplinary Science
  • AI automates regearch: literature review, idea proposal coding, analysis, etc.
  • Embodied AI and robotic manipulation enhancing laboratory automation
  • SOTA algorithms for each scientific research stage
  • Foundation models for Science, robotic manipulation
  • Dataset, Evaluation or Benchmark
  • Broader impacts and ethical considerations
  • Submission

  • We will use openreview.net on Venues IEEE IROS 2025 Workshop AIR4S
  • Full paper (4-8 pages)
  • Short paper (3-4 pages)
  • Abstract [1 page], Extended Abstract [2 pages]
  • Poster [Affiliated on final submission, single pdf file]
  • IROS double column format
  • Submission link: https://openreview.net/group?id=IEEE.org/IROS/2025/Workshop/AIR4S
  • AI Review: AI-generated review comments are provided for authors' reference only
    and did not participate in the decision-making process.
  • Important dates:

  • Submission Open: 10.Jun.2025 AOE
  • Submission Deadline (Extended Deadline): 07.Oct.2025 AOE
  • Notification date: 10.Oct.2025 AOE
  • Workshop date: 24.Oct.2025 Beijing Time
  • Invited Speakers


    _______________________________________________________________________________________________

    Wang Xingxing

    Wang Xingxing

    Founder and CEO of robotics company Unitree
    Hangzhou, China

    Talk title: Unitree's Latest Advances and Future Perspectives



    Pulkit Agrawal

    Pulkit Agrawal

    Associate Professor
    MIT, USA
    Dr. Hong

    Dr. Hong

    PhD
    MIT, USA

    Joint Talk: Robot Scientists for Scientific Discovery.


    Josie Hughes

    Josie Hughes

    Assistant Professor
    EPFL, Switzerland

    Talk title: Leveraging Embodied Intelligence for Environmentally Rich Interactions for Robotic Scientific Discovery.


    Yuquan Wang

    Yuquan Wang

    Principal Researcher
    Tencent Robotics X, China

    Talk title: TAIROS: An Embodied AI Platform for Robotics Applications.


    Kedi Cui

    Kedi Cui

    Vice President of Investments
    Baidu Ventures, China

    Talk title: Medical Laboratory Robot Professionals: The Dawn of Conquering All Diseases.


    Hirotaka Sugiura

    Hirotaka Sugiura

    Lecturer
    The University of Tokyo, Japan

    Talk title: Micromanipulation Technologies for AI Robot to Promote Unexplored Scientific Research.


    Di Fu

    Di Fu

    Assistant Professor
    University of Surrey, UK

    Talk title: Embodied AI in Multimodal Human-Robot Social Interaction.


    Kanako Harada

    Kanako Harada

    Professor
    University of Tokyo, Japan

    Talk title: Co-evolution of Human and AI-Robots to Expand Science Frontiers.


    James Zou

    James Zou

    Associate Professor
    Stanford University, USA

    Talk title: AI Agents for Scientific Discovery.


    Markus J. Buehler

    Markus J. Buehler

    Professor
    Massachusetts Institute of Technology, USA

    Talk title: Discovery superintelligence for science, engineering and creativity.


    David Scott Lewis

    David Scott Lewis

    Co-Founder & CEO (Maestro)
    AIXC

    Talk title: Building a Robot Scientist: From Reasoning Models to Autonomous Discovery.




    Organizers

    Pengsong Zhang

    Pengsong Zhang

    University of Toronto

    Heng Zhang

    Heng Zhang

    Istituto Italiano di Tecnologia (IIT)

    Cong Wang

    Cong Wang

    Harvard University

    Jin Wang

    Jin Wang

    Istituto Italiano di Tecnologia (IIT)

    Animesh Garg

    Animesh Garg

    Georgia Tech

    Renjun Xu

    Renjun Xu

    Zhejiang University

    Huazhe Xu

    Huazhe Xu

    Tsinghua University

    Xinyu Liu

    Xinyu Liu

    University of Toronto

    Arash Ajoudani

    Arash Ajoudani

    Istituto Italiano di Tecnologia (IIT)

    Sponsors



    Sponsor 1
    Sponsor 2
    Partner 1 Partner 2

    YOU

    Contact


    If you have any questions please contact:
    pengsong.zhang AT mail.utoronto.ca
    or: heng.zhang AT iit DOT it