 |
ShanghaiJune 15, 2026 /PRNewswire/ — Recently, XtalPi (2228.HK), a globally leading AI + robotics drug and new materials R&D platform, announced that the “Intelligent Autonomous Workstation for Physical/Chemical Adsorption Analysis,” jointly developed with Sinopec (Shanghai) Petrochemical Research Institute Co., Ltd. and Beijing JWGB Instruments Co., Ltd., has officially commenced operations. This workstation leverages intelligent, automated material characterization to drive chemical R&D, creating a key physical carrier and embodied intelligence foundation for the “AI for Science” (AI4Science) material discovery engine. For the first time in an industrial-grade scenario, it fully integrates high-throughput data collection and autonomous experimental decision-making for material characterization into an intelligent system of “AI + Robotics + Multi-Agent,” marking a critical step toward Physical AI and laying the groundwork for a “perceivable, operable, and evolvable” intelligent autonomous R&D system for material development.
This achievement highlights three core technological hallmarks: fully automated, unmanned end-to-end experiments; native high-quality data closed loops; and a modular intelligent foundation integrating software and hardware. This collaboration upgrades material characterization—a high-frequency, essential process—from an experience-driven, manual workshop operation to a data-driven, AI-decision-making industrial-grade intelligent system, achieving a quantum leap in characterization throughput, data accuracy, and experimental safety.
Powerful Collaboration Creates an AI+ Material Characterization Industry Benchmark
In trillion-dollar industries such as petrochemicals, new energy, and environmental protection, precise material characterization is a high-frequency, essential, and highly labor- and experience-intensive trial-and-error process in R&D workflows. Porous materials (e.g., molecular sieves, activated carbon, metal-organic frameworks) are the most widely used and highest-volume catalysts and adsorbent carriers in petrochemicals. Their properties—such as specific surface area, pore size distribution, and surface acidity—directly determine the efficiency and selectivity of core processes like catalytic cracking, hydrotreating, and gas separation, making them the “chips” of the petrochemical industry. Traditional characterization methods rely heavily on manual operation, resulting in low efficiency and throughput, as well as poor data consistency due to subjective experience and operational variability. This prevents vast amounts of experimental data from effectively feeding AI models, creating the biggest data bottleneck in intelligent new material R&D.
To address this challenge, XtalPi collaborated closely with Sinopec (Shanghai) Petrochemical Research Institute and JWGB Instruments to build a collaborative innovation ecosystem that spans from defining industrial problems and developing high-end instruments to fully closed-loop AI-driven autonomous experiments. This transforms traditionally intuition- and experience-based analysis into quantifiable, reproducible scientific methods, directly targeting core industry pain points.
In this collaboration, Sinopec (Shanghai) Petrochemical Research Institute, leveraging its extensive R&D expertise and deep understanding of petrochemical industry scenarios, precisely defined the core industrial requirements for high throughput, high precision, and high safety, while providing real, rigorous validation scenarios. JWGB Instruments, as a leading enterprise in domestic physical/chemical adsorption instruments, built the high-precision analytical instrument hardware base—the “precise senses”—for the workstation, ensuring the accuracy and reliability of AI-driven autonomous experimental data. XtalPi, as a benchmark enterprise in the AI for Science field, contributed the “AI brain” and robotic autonomous manipulation capabilities. Relying on its closed-loop autonomous intelligent system of “AI + Robotics + Multi-Agent,” XtalPi upgraded standalone instruments into “AI material characterization scientists” capable of autonomously planning workflows, analyzing data, and making decisions. Through deep, innovative collaboration among the three parties, a new intelligent benchmark for material characterization has been established for the industry.
AI-Driven Autonomous Experiments Reshape the Core Paradigm of Material Characterization
This workstation, with an AI-native core, integrates flexible and scalable robotic experimental stations with intelligent algorithms to unify experimental standards, forming a “software-hardware integrated” intelligent system. It achieves a fully automated, unmanned closed loop from sample processing to data analysis, building a “high-quality data foundation” for AI for Science to empower material science:
- High-Throughput Autonomous Experiments: The workstation supports intelligent expansion of multi-channel physical/chemical adsorption modules, autonomously assigning tasks under unified AI scheduling for 7×24 unmanned, continuous operation. Daily sample processing capacity achieves an order-of-magnitude increase, completely freeing researchers from repetitive labor.
- Native High-Quality Data Closed Loop: Robotic operations standardize experimental procedures, fundamentally eliminating human error. The system integrates core intelligent algorithms, ensuring ultra-high data consistency and reproducibility, providing high-quality data support for AI model training, and making every data point traceable and reusable.
- Intrinsic Safety and Intelligent Analysis: Unmanned operation significantly reduces risks such as liquid nitrogen exposure in traditional experiments, enhancing laboratory intrinsic safety. The system also automatically performs data analysis, result normalization, and trend modeling, laying the foundation for the digital and intelligent transformation of material R&D.
This system is developed based on XtalPi’s mature, customizable AI autonomous experiment platform, which features over 30 functional modules that can be flexibly combined and has been recognized by over 300 top global enterprises and research institutions.
Building a Data Foundation to Drive Industry Toward Physical AI
The “Intelligent Autonomous Workstation for Physical/Chemical Adsorption Analysis,” through full-process digitalization and autonomous operation, achieves, for the first time, complete capture and structured deposition of experimental data, transforming previously scattered, fleeting personal experience into accumulable, reusable data assets. Its significance extends beyond point-specific efficiency gains; it provides high-quality “data fuel” for building AI models capable of understanding and acting upon the physical world. This enables rational material design to truly discover structure-property relationships from massive experimental data, forming a closed-loop evolutionary capability of “experiment → data → model → prediction.”
A relevant business leader from Sinopec (Shanghai) Petrochemical Research Institute Co., Ltd. stated: “This intelligent workstation introduces AI and autonomous experiment technology into the core process of catalyst R&D. It not only achieves leaps in efficiency and data accuracy but also provides a new research paradigm for exploring high-performance, low-energy catalysts, supporting the green and low-carbon transformation of the industry under the ‘dual carbon’ goals. It is a benchmark practice in the intelligent transformation of chemical R&D.”
The head of XtalPi’s Automation Innovation Business stated: “This is a significant breakthrough for AI for Science in the petrochemical field. We are building an R&D infrastructure that enables AI to continuously generate, digest high-quality data, and drive self-iteration. Starting from this point, this model will expand from adsorption characterization to broader material R&D scenarios, driving material R&D from ‘experience-driven’ to ‘data-driven and intelligence-driven,’ empowering source innovation across more industries.”
A relevant leader from Beijing JWGB Instruments Co., Ltd. stated: “This collaboration is a model of integrating domestic instruments with AI autonomous experiment technology. We will continue to enhance the intelligence level of our products, providing global users with more complete digital and intelligent solutions for material characterization.”
Looking ahead, XtalPi will continue to deepen its AI for Science platform technology, driving material R&D from empirical exploration toward deeper mechanistic understanding and rational design. In industrial scenarios, it will persistently refine the R&D flywheel centered on vertical AI models, large-scale robotic laboratories, and Multi-Agent systems, accelerating the comprehensive intelligent upgrade of China’s material R&D field and injecting sustained momentum into serving the national strategy of becoming a science and technology powerhouse and promoting high-quality industrial development.
About Sinopec (Shanghai) Petrochemical Research Institute Co., Ltd.
Sinopec (Shanghai) Petrochemical Research Institute is a comprehensive petrochemical research institution directly under China Petrochemical Corporation (Sinopec Group). It is dedicated to technology R&D and industrial application in fields such as petrochemicals, synthetic resins, synthetic fibers, and catalysts, providing core support for Sinopec’s technological progress and industrial upgrading.
About JWGB Instruments
Founded in 2004, JWGB Instruments is a scientific instrument manufacturer with its headquarters and R&D center in Beijing, a production base in Tianjin, and subsidiaries in the United States and Germany, serving the global market. The company’s products cover key areas including adsorption instruments, thermal analysis instruments, X-ray diffractometers, and reaction devices. As an innovation driver in the global material analysis instrument field, JWGB consistently upholds its mission to “provide high-quality, user-friendly, and cost-effective advanced measurement instruments for the research and manufacturing of new materials,” continuously exploring cutting-edge material characterization technologies, accelerating technological iteration, and offering diversified products and service solutions to global customers.
About XtalPi
XtalPi (“XtalPi Holdings Limited,” stock abbreviation: XtalPi Holdings, XTALPI, stock code: 2228.HK) was founded in 2015 by three physicists from the Massachusetts Institute of Technology. It is an innovative R&D platform based on quantum physics, empowered by artificial intelligence and driven by robotics. The company combines quantum physics-based first-principles calculations, artificial intelligence, high-performance cloud computing, and scalable, standardized robotic automation to provide drug and material science R&D solutions and services to global and domestic companies in the pharmaceutical and material science industries (including agricultural technology, energy, new chemicals, and cosmetics).