Exhibitions & Posters

Details of corporate exhibitions, research exhibitions, and poster presentations at the 3rd AI Robot-Driven Science Symposium (December 5, 2025).

Corporate & Research Exhibitions

E-01

New Research Infrastructure Created by AI Material Exploration and Evidence Preservation

TOYOTA MOTOR CORPORATION

Toyota Motor Corporation is developing various new businesses. We will introduce two of them: the data analysis cloud service "WAVEBASE" and the data preservation service "PCE".
・WAVEBASE: Automatically analyzes experimental data and material composition/process data to support data-driven problem solving. It speeds up analysis and enables development efficiency.
・PCE: Utilizing blockchain technology, it can prove the originality of data globally over the long term. It strengthens evidence of technical information and enhances response capabilities for disputes and litigation related to improper handling of information and intellectual property rights.

E-02

Advanced and Efficient Omics Data Analysis with Hitachi's Proprietary AI "B3"

Hitachi, Ltd.

Hitachi has developed "B3," a technology that can analyze small-sample, high-dimensional data with high generalization performance and prediction accuracy, contributing to data-driven efficiency in exploration work and new discoveries. There are analysis cases for metabolite data, RNA-Seq data, etc., which are used for exploring important genes, multi-biomarkers, and risk factors. We will introduce case studies of "B3" and "B3 Analytics" available as a cloud service. We will also introduce examples of how we are utilizing generative AI in the drug discovery process.

E-03

Automation Solution for Laser Diffraction/Scattering Particle Size Distribution Analyzer

HORIBA, Ltd.

HORIBA's particle size distribution measurement devices can be equipped with automatic sample transport mechanisms using robot arms. Automating from sample loading to measurement enables continuous multi-sample measurement, reducing operator burden and preventing human error. The precise and highly reproducible operation by the robot arm achieves both improved efficiency in research and quality control and enhanced measurement reliability. Through such automated analysis solutions and the data management system STARS Enterprise, HORIBA supports customers' cutting-edge research.

E-04

Liquid Handling Robot System with Transport Function

Kojiro Narazaki (Tsubame Lab Inc.)

We exhibit an open-source liquid handling robot equipped with a plate transport mechanism. In addition to dispensing and transport operations, it enables recording via camera images and log management on the cloud. AI automatically generates control code from natural language input, enabling experiment automation without programming knowledge. With a flexible configuration that can link with other robots and devices, we aim to build a low-cost, highly reproducible research automation environment.

E-05

Robot Utilization and Smart Lab System Development for High-Performance Material Development

Kazuma Kurihara (AIST Manufacturing Technology Research Division)

We are developing high-performance materials that can control light and wettability using microstructures. In R&D activities, efficiency improvement is necessary, and we are developing automation of sample preparation and measurement using collaborative robots, as well as a smart lab system that integrates process condition input using smartphones and lab management functions. By utilizing these DX systems, we are building functions that allow the system to discover data that would be overlooked in normal research activities, developing high-performance materials and accumulating process know-how. The exhibition will introduce developed materials and laboratory DX.

E-06

ROPES First Generation

Tetsumasa Ura (The University of Tokyo, Nagato Laboratory)

We exhibit the first prototype of ROPES (Robotic Objective Process Exploration System) created as a result of the 2019 JST MIRAI Program "Data-Driven Process Informatics for High-Throughput Powder Film Formation Process Research." This device actually performed automated experiments and autonomous exploration of the drying process of catalyst ink for fuel cells, but for safety, the demonstration will use sumi ink.

E-07

Automation of Powder Experiments in Glove Box Using Collaborative Robot

Yuki Yamaguchi (AIST) / Yoshiyasu Nishiyama (Aichi Institute of Technology) et al.

We have built an experimental system utilizing collaborative robots to automate powder experiments inside a glove box. We will introduce karakuri jigs that enable many experiments with a small number of collaborative robots.

E-08

Science Pioneering through Creative Co-evolution of Humans and AI Robots

Kanako Harada (Graduate School of Medicine, The University of Tokyo)

We will introduce the project overview and results. As an exhibition, we will demonstrate remote operation of the robot system from the exhibition venue. The operator wears a VR headset and remotely operates while checking the digital twin of the robot system at a remote location (The University of Tokyo) through mixed reality (MR) (DOI: 10.1109/VRW66409.2025.00102). It is used for remote robot operation and collecting training datasets for AI in environments where humans cannot easily enter, such as biohazard environments and clean environments.

E-09

Powder Grinding with Controlled Particle Size Using Robot Arm

Ryusei Takamoto (The University of Osaka, Graduate School of Engineering, Ono Laboratory)

We will present a poster on a system that grinds powder to obtain the desired particle size using a robot. In this system, the robot arm grinds powder while estimating the particle size from the vibration of the mortar, allowing grinding to stop when the desired particle size is reached. In the demo space, we will demonstrate the robot arm performing powder grinding using a pestle and mortar with Cobotta (DENSO WAVE), a collaborative robot.

E-10

Chemical Experiment Automation System by Dual Demonstration

Hikaru Sasaki (Assistant Professor, Nara Institute of Science and Technology)

In this study, we propose dual demonstration, where chemists themselves can simultaneously teach robot motion and jig operation, in order to flexibly extend chemical experiment automation systems. By integrating a teaching device in the shape of a robot hand, jigs, and a mobile manipulator, we achieved automated experiments based on chemist demonstrations. We demonstrated motion reproduction in simulated polymer synthesis experiments, showing that robot experiment automation can be built intuitively without requiring expertise in robotics.

E-11

Exploration of Milk Crown Formation Conditions Using NIMO

Shigeki Yoshikawa (Institute of Integrated Research, Institute of Science Tokyo)

When a drop of liquid is dropped onto a thin layer of milk, a crown-shaped structure called a milk crown may form depending on conditions such as the collision velocity of the droplet and the thickness of the liquid layer. In this exhibition, we will demonstrate efficient exploration of milk crown formation conditions using NIMO, general-purpose software for autonomous automated experiments, and two robot arms.

E-12

AI-Equipped Automated Experiment System Brought to Life by NIMO

Ryo Tamura / Shoichi Matsuda (NIMS)

We are developing "NIMO," an open-source software for realizing automated autonomous experiments, and advancing the development of automated autonomous experimental equipment utilizing it. By introducing NIMO into automated experimental equipment, we have achieved a closed loop of automatic selection of optimal experimental conditions and material synthesis/evaluation by automated experimental equipment based on them. This enables efficient experiment progress without human intervention. In the equipment exhibition, we will introduce the parallel electrochemical cells used in the NIMS Electrochemical Automated Experiment Robot (NAREE).

E-13

Leaf Sampling Using a Robotic Manipulator

Rui Tsuneya / Weiwei Wan (Osaka Univ./RIKEN) / Nobuyuki Tanaka / Ryoichi Sato / Miki Fujita (RIKEN) / Kensuke Harada (Osaka Univ.)

This work is about automated leaf cutting and collection for lab purposes. We propose a single-arm method, using a customized end-effector to hold and cut the leaf. The pose of the leaf is determined via learning-based method and the final position of interaction is obtained after closed-loop iterative refinement.

Poster Presentations

P-01

Introduction to Autonomous Lab: Autonomous Experimental System

Taichi Tomono (SHIMADZU CORPORATION)

This is an overview introduction of Autonomous Lab, an autonomous experimental system that aims to automatically run the Design→Build→Test→Learn experimental cycle at Shimadzu Corporation. We will introduce the contents of the prototype targeting biomanufacturing as an initial target.

P-02

Automated Exploration of Novel Quantum Chemistry Methods Using Large Language Models

Masaya Hagai (TOYOTA MOTOR CORPORATION)

While quantum chemical calculations enable molecular-level simulations, the introduction of approximation methods to reduce computational costs is essential for handling large molecular systems in realistic time. However, creating useful approximation methods faces barriers such as interdisciplinary knowledge spanning physics, chemistry, mathematics, and information science, difficulty predicting execution costs, and high implementation costs. In this study, we propose a method that automates the conception, implementation, and verification of new quantum chemistry methods using large language models, enabling automated exploration of promising approximation methods by quickly trying diverse interdisciplinary ideas.

P-03

Development of Domain-Specific Foundation Models for AI-for-Science

Yuna Oikawa (The University of Tokyo, Tsuda Laboratory)

We propose two large-scale models in the AI-for-Science domain: (1) GPepT, a foundation peptide language model for peptide mimetics design incorporating non-natural amino acids, and (2) aLLoyM, a large language model specialized for phase diagram prediction of metallic materials, integrating knowledge acquisition, generation, and prediction capabilities in each scientific domain.

P-04

Development of Crystal Structure Generation Framework Based on Natural Language Instructions

Yusei Ito (The University of Osaka)

Designing crystal structures that achieve desired properties is an important challenge in materials exploration. Existing methods using generative models such as MatterGen have shown effectiveness in structure generation conditioned on numerical property values, but since they assume explicit quantitative information, they have limitations in flexibly handling complex and multifaceted design goals. In this study, we propose a text-conditioned structure generation framework that enables direct generation of crystal structures from natural language instructions.

P-05

Object-Centric World Model and Policy Learning Considering Influence Relations

Haruhiro Nishimoto (The University of Osaka)

Deep reinforcement learning agents have extremely low sample efficiency, making real-world application difficult. To address this problem, many model-based reinforcement learning methods that learn world models have been proposed, achieving some success. However, in complex environments with multiple objects, it remains challenging for reinforcement learning agents to acquire world models. In this study, we propose a reinforcement learning agent where the world model, policy function, and value function are all composed of Transformers that handle object-centric representations, confirming its effectiveness in multiple benchmarks.

P-06

Development of Tailor-Made Experiment Automation Tools for Cell Culture

Atsushi Shibai (RIKEN Special Postdoctoral Researcher)

Targeting microbial culture experiments, we develop tailor-made automation tools that combine GUI wrappers with low-cost robot transport while leveraging existing culture and measurement equipment, verifying utility and versatility in drug resistance evolution experiments and stress tolerance acquisition experiments.

P-07

Flexible Control of Conditional Generative Models

Kuniaki Saito (OMRON SINIC X Corporation)

Models that generate data such as language and compound structures are expected to obtain desired outputs from various conditions. In this poster, we present findings on conditional generative models, focusing on Vision-Language Models that generate captions from images. Note that the results in this poster have been presented at ICCV2025.

P-08

ROS2/PLC Integration for Automating Existing Experimental Equipment and Construction of Automated Arc Furnace

Kensei Terashima (NIMS)

Many existing experimental devices still have technical barriers to plug-and-play automation. We built a framework using ROS2 and PLC, where LAN-communicable devices are handled via ROS2, and those that cannot are handled via PLC as ROS2 nodes, enabling experimental equipment to operate independently and in parallel, coordinating as needed. We created an automated solid bulk material synthesis system using an arc furnace.

P-09

Discovering New Theorems via LLMs with In-Context Proof Learning in Lean

Kazumi Kasaura (Research Engineer, OMRON SINIC X Corporation)

This study focuses on LLMs' ability to discover new theorems. We propose a "conjecture-proof loop" pipeline that automatically generates mathematical conjectures and proves them in Lean 4 format, a type of theorem proving assistant. The key feature of this method is that it generates and proves further conjectures using context that includes previously generated theorems and their proofs. This enables generation of more difficult proofs through in-context learning of proof strategies without changing the LLM's parameters.

P-10

Modeling Coupled Systems and Multi-Physics Using Deep Learning

Khosrobian Lazmik Arman (The University of Osaka, Graduate School of Engineering Science, Master's 2nd year)

Deep learning has achieved great success in modeling dynamical systems with unknown governing equations. However, application of existing methods has been mainly limited to mechanical systems, and they cannot directly model coupled systems because they treat systems as a whole. We propose a deep learning model using Dirac structures that can uniformly represent systems spanning multiple domains such as mechanical systems and electrical circuits, as well as the interactions and constraints of each element. Experimental results show that the proposed method appropriately learns interactions between elements and has better long-term prediction performance than existing methods.

P-11

Development of Next-Generation Experimental Robot for Distributed Development

Takaaki Horinouchi (Engineer, RIKEN Center for Biosystems Dynamics Research)

Toward the development of AI robot-driven science, we aim to provide robot labs and system infrastructure that enable learning and generation of diverse scientific research data as technology that autonomously and actively learns. To this end, we are developing Ardea, a next-generation experimental robot system compatible with distributed development of life science experiments, and LabCode, an experiment description language. In the life science field, diverse experimental protocols exist, and distributed development and resulting network effects are considered important elements for efficient implementation. We will introduce the development status toward its demonstration.

P-12

A Minimal Open-Access Platform for Laboratory Automation Training

Daiki Noguchi (Visiting Researcher, RIKEN Takahashi Laboratory)

In this study, we developed a low-cost, highly reproducible laboratory automation (LA) education system and created DIY-LA equipment based on open source that links the OT-2 liquid handler and Absorbance-96 plate reader. This system enables easy learning of the basic elements of LA - "sample preparation," "measurement," and "experimental design" - both individually and as an integrated experimental system. High educational effectiveness was confirmed in Bayesian optimization training for undergraduate students at Keio University.

P-13

NIMO: Software Supporting Automated Autonomous Experiments

Shoji Yamaguchi (NIMS Center for Energy and Environmental Materials)

We developed NIMO, a general-purpose software to easily form closed loops for automated autonomous experiments, and released it as open-source software. In NIMO, robot experimental equipment and exploration AI are treated as independent modules, designed to enable various automated autonomous experiments by flexibly selecting combinations of robot experimental equipment and AI algorithms. In particular, multiple options for exploration AI algorithms are implemented, allowing various types of exploration to be conducted with a single robot experimental device.

P-14

Introduction to JST PRESTO "Research and Development Process Innovation"

Ichiro Takeuchi (Professor, Nagoya University)

This poster introduces the JST PRESTO area "Infrastructure Construction and Practical Application for R&D Process Innovation through AI/Robots (Research and Development Process Innovation)." (Display only)