AGIBOT WORLD CHALLENGE 2026 Advances Embodied AI Competition from Simulation to Real-Robot Testing at ICRA 2026

VIENNA, June 5, 2026 /PRNewswire/ -- AGIBOT, a leading embodied AI company, hosted AGIBOT WORLD CHALLENGE 2026 alongside ICRA 2026 in Vienna, bringing together 526 research and enterprise teams from 27 countries to compete across two embodied AI tracks: Reasoning to Action and World Model. The competition highlighted a key shift in embodied AI evaluation, moving beyond simulation scores toward closed-loop testing on real robots, real tasks, and standardized benchmarks.

Dual Tracks Focus on Reasoning to Action and World Modeling
AGIBOT WORLD CHALLENGE 2026 featured two tracks designed around core capabilities in embodied AI. The Reasoning to Action (R2A) track evaluated how robots understand tasks, plan actions, and execute them in physical environments. The World Model (WM) track focused on how AI systems predict physical-world changes and model interactions based on robot actions and sensor inputs. Together, the two tracks reflected the broader evolution of embodied AI from task execution toward understanding, prediction, and decision-making.

This challenge drew research and industry teams from leading institutions and companies, including the Chinese Academy of Sciences, Tsinghua University, the University of Science and Technology of China, the University of California San Diego, Russia's Sber Robotics Center, Alibaba, Amap, and vivo. More than 100 teams surpassed the official baseline, reflecting strong participation from universities, research institutes, technology companies, startups, and individual developers across academia and industry.

The competition adopted a benchmark-driven format that combined online automated evaluation with an offline real-robot final in Vienna. Leveraging AGIBOT's EWMBench and Genie Sim Benchmark, the format enabled automated testing, standardized metrics, and reproducible results, offering a more consistent framework for evaluating embodied AI systems across simulation and real-world execution.

During the offline final, finalist teams completed tasks using the AGIBOT G2 humanoid robot in real-world scenarios. By incorporating real-robot validation into the evaluation process, the competition placed robot stability, physical-world adaptability, and long-horizon task reliability at the center of the scoring system, aligning technical evaluation more closely with practical deployment needs.

The Reasoning to Action (R2A) track, upgraded from the 2025 Manipulation track, expanded the evaluation from action execution to the full process of environment understanding, task planning, and physical execution. Teams trained reasoning-and-manipulation models using the AGIBOT WORLD open-source dataset and evaluated them through Genie Sim 3.0, with the benchmark covering language understanding, spatial reasoning, atomic skills, disturbance adaptation, and zero-shot transfer. In the final ranking, PrismBot from vivo won the championship, followed by Shanghai RoboParty's RP-VLA and GreenVLA.

Alongside the competition, AGIBOT and Dexmal launched a real-supermarket benchmark track focused on end-to-end decision-making and whole-body control. Set in a highly realistic retail environment, the track required models to complete the full mobile manipulation process, from autonomous navigation and item picking to item transport and placement, under real physical constraints such as shelf height limits and randomized item placement. Through API-based remote control, participants' algorithms directly controlled real robots, creating a practical benchmark for evaluating embodied intelligence in deployment-oriented scenarios.

In the World Model (WM) track, NeoVerse-ABot, a joint team from the Institute of Automation of the Chinese Academy of Sciences, and Amap CV Lab, won first place. The PAI@IAII team from the Institute of Industrial Artificial Intelligence, Chinese Academy of Sciences, ranked second, while the Loop team from the University of Science and Technology of China placed third. This track incorporated non-ideal physical interactions, including object drops and grasping failures, to better reflect the complexity of real-world interaction and provide a more practical evaluation framework for world model research.

Full-Stack Toolchain Supports Standardized Real-Robot Validation
Beyond the competition itself, AGIBOT opened a full-stack toolchain covering real-world data, simulation evaluation, and real-robot testing. The toolchain included the AGIBOT WORLD open-source dataset, Genie Sim 3.0, and the AGIBOT G2 robot platform, helping developers validate models across the path from training to simulation and physical deployment.

By combining dual-track evaluation, automated benchmarking, and real-robot testing, AGIBOT WORLD CHALLENGE 2026 contributed to a more practical and reproducible evaluation framework for embodied AI. EWMBench and Genie Sim Benchmark supported standardized metrics, automated evaluation, and comparable results across simulation and physical testing, addressing common challenges such as inconsistent evaluation criteria and the gap between simulated performance and real-world deployment.

The competition also moved beyond a narrow focus on simulation scores by placing real-robot stability, physical consistency, and long-horizon task reliability at the center of evaluation. This approach encouraged teams to develop models not only for benchmark performance, but also for deployability, generalization, and robustness in real-world environments.

The technical and ecosystem resources developed through the competition will be integrated into AGIBOT's ongoing benchmark development and open-source ecosystem. Moving forward, AGIBOT plans to launch an online simulation leaderboard, introduce more test tasks and diversified benchmarks, and support more comprehensive quantitative evaluation of model capabilities. The company will also continue to refine its benchmarks and full-stack toolchain, working with global research institutions, developers, and industry partners to help embodied intelligence progress from individual algorithmic advances toward systems that can be deployed and scaled in real-world settings.

For more information, please visit the AGIBOT website at AGIBOT.com, and follow AGIBOT on:
https://x.com/AGIBOTofficial
https://www.linkedin.com/company/agibot/
https://www.youtube.com/@AGIBOTofficial
https://www.instagram.com/agibotofficial/
https://www.tiktok.com/@agibot_
https://www.facebook.com/AGIBOTofficial/

About AGIBOT
AGIBOT is an Embodied AI foundation model company developing both the intelligence layer and the corresponding robotic embodiments needed to bring general intelligence into the physical world. AGIBOT's "Three Intelligences in One" architecture integrates Locomotion Intelligence, Interaction Intelligence, and Manipulation Intelligence into a unified embodied system. Its portfolio spans humanoid robots, quadrupeds, dexterous systems, and commercial cleaning solutions. In March 2026, AGIBOT announced that its 10,000th robot had rolled off the production line.

** This press release is distributed by PR Newswire through automated distribution system, for which the client assumes full responsibility. **

AGIBOT WORLD CHALLENGE 2026 Advances Embodied AI Competition from Simulation to Real-Robot Testing at ICRA 2026

AGIBOT WORLD CHALLENGE 2026 Advances Embodied AI Competition from Simulation to Real-Robot Testing at ICRA 2026

AGIBOT WORLD CHALLENGE 2026 Advances Embodied AI Competition from Simulation to Real-Robot Testing at ICRA 2026

AGIBOT WORLD CHALLENGE 2026 Advances Embodied AI Competition from Simulation to Real-Robot Testing at ICRA 2026

AGIBOT WORLD CHALLENGE 2026 Advances Embodied AI Competition from Simulation to Real-Robot Testing at ICRA 2026

TAIPEI, June 5, 2026 /PRNewswire/ -- Innodisk, a leading global AI solution provider, showcases its complete edge AI ecosystem at COMPUTEX 2026, demonstrating how enterprises and industrial customers can accelerate AI deployment for production-ready applications. Built across five essential layers—compute, memory, storage, sensing and communication, and software—the portfolio brings together AI platforms, industrial modules, and real-world application demos to support secure, scalable AI adoption.

At the center of this year's showcase are Innodisk's on-premises AI solutions for secure enterprise AI deployment. AccelBrain, powered by the APEX-X200, enables fully on-premises deployment of open-source LLMs with 100% data sovereignty. Complementing it, AccelTune provides a no-code LLM fine-tuning experience, demonstrated on the APEX-S100 featuring Intel® Xeon® 6700-series processors and supporting dual NVIDIA RTX PRO GPU. Together, these solutions help enterprises build secure, application-specific LLM workflows without relying on public cloud infrastructure.

Beyond enterprise AI, Innodisk demonstrates how edge AI can be deployed in demanding industrial environments. A heavy machinery safety solution showcases eight ruggedized GMSL2 camera modules rated IP67 and IP69K, delivering AI-driven surround-view stitching, Driver Monitoring System (DMS), and Blind Spot Detection (BSD) to enhance operator awareness and safety in harsh field applications.

Innodisk, an Intel Gold Partner, also presents the APEX-E400 edge AI system, powered by Intel® Core™ Ultra Series 3 processors. Built on a heterogeneous CPU-GPU-NPU architecture, the system supports up to 16 simultaneous streams with parallel AI model inference. A live Intel OpenVINO™ demo highlights adaptive workload distribution across the tri-engine architecture for optimized edge AI performance.

In collaboration with Qualcomm Technologies, Inc., Innodisk continues to expand its AI on Qualcomm Dragonwing™ series for compact, power-efficient edge inference, showcasing the latest Dragonwing processors, across the IQ9, IQ10 and IQ-X Series, in the Innodisk booth. Powered by the Dragonwing IQ-9075 processor-based COM-HPC Mini platform, there are live demos showcasing AI screw thread inspection and multi-stream vision processing, while an AMR demonstration further integrates GMSL and depth cameras for spatial awareness, ROI safety zone detection, and PWM-triggered automatic emergency braking.

Software enablement is another key layer of the ecosystem. Innodisk integrates Edge Impulse's end-to-end edge AI machine learning operations (MLOps) platform with iCAP, Innodisk's intelligent cloud management platform, to demonstrate Agentic AI capabilities for automated remote model updates and deployment.

Supporting these AI systems is Innodisk's industrial-grade memory, storage, connectivity, and sensing portfolio. The company showcases next-generation DDR5 8000 RDIMM, CUDIMM, and CSODIMM, along with industry-leading 12800 MRDIMM and a new CXL Add-in Card (AIC). Storage highlights include Data center SSDs in EDSFF and U.2 form factors, as well as 218-layer 3D TLC SSDs. In connectivity, Innodisk debuts the ELPL-82F1 SFP28 25GbE LAN card, alongside the award-winning EGPL-T2F1—honored at Embedded World 2026 as the world's first SFP+ LAN card in M.2 form factor. The booth also features ruggedized camera solutions across GMSL2, MIPI, and USB interfaces, complemented by an interactive OCR container identification demo running on an integrated edge system.

Together, these demonstrations show how Innodisk brings together its complete five-layer AI ecosystem, helping customers deploy AI securely, reliably, and at scale across enterprise and industrial environments.

 

** This press release is distributed by PR Newswire through automated distribution system, for which the client assumes full responsibility. **

Innodisk Showcases Its Five-Layer Edge AI Ecosystem at COMPUTEX 2026