Robora is expanding into academia. We’ve begun working with university researchers in robotics, bringing expertise in areas such as SLAM, multi-modal perception, and motion planning into our ecosystem. The progress can be tracked live on our Github Repo: github.com/RoboraDev/Vision_… More and more researchers are joining our initiative as we speak. Their research feeds directly into Robora’s decentralized infrastructure, where modules for detection, segmentation, and control can be deployed across autonomous systems. This collaboration accelerates our path from academic labs to large-scale deployment, building a foundation where robots can operate, learn, and coordinate through Robora. In the future, we’ll also create opportunities for the community to engage directly with these researchers as the collaboration deepens.

Live from the Inclusion Conference, @LarryHashpowerX shares an update with the Robora community. Bipedal robotics, global manufacturing, and the momentum we’re building were all in focus. We are already in active discussions with several major manufacturers, and the level of interest continues to grow. One of these discussions is moving toward a major partnership, which we look forward to announcing soon. Through these efforts, Robora is working to bring Web3 into the broader robotics space, creating new opportunities where decentralized infrastructure and physical AI converge.

Robora x Lemorele We are excited to announce the integration of the Robora P300 (R) model. An exclusive model developed in partnership with Lemorele, features a custom Robora-exclusive SKU and hardware configuration designed to support high-performance, wireless video streaming for AI training and perception. We will integrate this specialized unit into our VLA Module. The Robora P300 (R) enables seamless, real-time capture of high-definition HDMI video from external cameras, allowing users to wirelessly feed visual data directly into the VLA training pipeline. This enhances capabilities such as multi-view learning, remote annotation, and real-world AI fine-tuning, all without requiring tethered camera setups. While the full Robora robotics platform is still in development, users will be able to use the Robora P300 (R) hardware with their existing iOS or Android devices, enabling them to begin collecting and streaming visual data for VLA from mobile platforms. As part of our commitment to the Robora community, we will be offering exclusive giveaways of the Robora P300 (R) hardware to token holders, giving early supporters the opportunity to contribute directly to Robora’s growing AI training ecosystem and to gain early access to the tools that power the future of robotics and intelligent vision.

Introducing the Robora VLA SDK The Robora VLA SDK is a modular SDK built to integrate state-of-the-art Vision-Language-Action (VLA) models into modularized robotic systems. It facilitates easy fine-tuning, optimized inference, and deployment of open-weight VLA models like SmolVLA, Pi0, OpenVLA, and GR00T N1.5, supporting diverse robot platforms and applications. This SDK empowers researchers and engineers to build intelligent robotic applications that understand natural language commands and execute complex physical tasks with high efficiency and precision across various robot types. Robora VLA SDK Key functionalities includes : 1. Chassis/Frame Agnostic - modular design compatible with drones, quadrupeds, humanoids, and other custom robots. 2. Robust Fine-tuning - Allows developers to freeze VLM Backbone & fine-tune only the action heads or full fine-tuning to adapt models to new tasks or environments. 3. Inference - Action generation at high frequencies (upto 50Hz) with both autoregressive and flow-matching techniques. 4. Rich Simulation Environment - Integration with simulation environments like PyBullet and Gymnasium for training VLAs via imitation learning & RL. 5. Model management - Unified interface for seamless downloading and usage of pre-trained models from popular hubs. Check out our progress live on Github: github.com/RoboraDev/VLA_Mod…

Train. Configure. Calibrate. Your physical AI, verifiable on-chain. $RBR

They’re here. They’re learning. They’re changing the world. Robots are no longer sci-fi. With $RBR the future isn’t coming. The future is now.

Robots are no longer science fiction. They’ve stepped out of the lab. Into our offices. Into our cities. Into our lives. Fine-tune the future of robotics with $RBR.

Great way to start the week. We’ve officially surpassed 2,000 holders. Steady growth, strong community, and a foundation for what is next. $RBR

$RBR Liquidity has been locked for 5 years : team.finance/view-coin/0x2C4…

We’ve partnered with CryptoAutos. $RBR is now live in their marketplace for car purchases and rentals worldwide. This marks another step in real-world utility as mobility meets blockchain. Pay with $RBR. Drive anywhere.

As we look back on the past month, we’re proud of the progress we’ve made, and even more excited about what lies ahead. We’re incredibly thankful for every one of you who shares in our vision and aligns with the mission we're building together. Your support, energy, and belief in what we're creating makes all the difference. With every step forward, we’re proving what’s possible when a community moves with shared purpose. Here’s a look at what we’ve been working on the last month, in our latest Medium article and the video below 👇. Medium Article: robora.medium.com/monthly-re…

The Robora Vision Module (RVM) is a plug-and-play component for modular robotics, part of Robora’s Physical AI framework. Each module can operate independently or collaborate in orchestrated systems. The rvm Python package includes: rvm-detect: object detection and annotation (images, video, webcam) rvm-segment: image segmentation with SAM for ROI mask generation rvm-markers: fiducial marker and barcode detection for pose estimation and calibration rvm-eval-coco: optional benchmarking on COCO datasets with HTML reports Beyond CLI tools, RVM is extensible and allows developers to integrate or extend it for custom robotics projects. The RVM is fully compatible with ROS2, making it ready for real-world robotics integration. Next up: expanding our plug-and-play Physical AI with new modules in development. 🔗 GitHub: github.com/RoboraDev/Vision_…

Robora is excited to announce that we will be attending the R3AL WORLD AI Summit 2025 @token2049 Singapore 🇸🇬 on September 30th! This flagship event brings together global pioneers in AI, robotics, and decentralized infrastructure to solve one of AI’s biggest challenges: its disconnect from reality. We look forward to connecting with founders, builders, and innovators and to showcasing how Robora is pushing the boundaries of real-world robotics powered by AI. See you in Singapore ✨

Robora Sim: A PyBullet-Powered Environment for Learning Robotic Physical Intelligence We are currently building our Robora simulation environment setup for our sim based learning, leveraging PyBullet, an industry-standard physics engine widely used in AI-driven robotics research and development. The environment is optimized with GPU-accelerated learning algorithms, enabling high-speed imitation learning and reinforcement learning within a safe and controlled virtual setup before shipping out to real world. This simulation platform allows our models to learn, adapt, and generalize across different robot morphologies, terrain types and task objectives - all before deployment to the real world. At it's core, the system combines a VLA-powered high-level planner with low-level motion control algorithms, working cohesively to produce emergent, physically intelligent behaviors. This synergy between simulation, learning, and real-world transfer marks a major step forward in our pursuit of adaptive and intelligent robotic systems. Through advanced domain randomization and synthetic data generation, the Robora Simulation Environment ensures that policies trained in simulation transfer effectively to real-world robots, minimizing the sim-to-real gap. Moreover, users will be able to test and integrate their own hardware kits within selected simulation environments in the Robora Dapp, ensuring seamless compatibility and safer real-world implementation.

There will be signs! Thanks to voices like @LarryHashpowerX showing where robotics is heading.

We’re entering a defining phase at $RBR. Robora is evolving into a verifiable robotics ecosystem, an open platform where anyone can contribute, build, and earn. By merging AI, robotics, and blockchain, we’re creating a new layer of Physical-AI infrastructure where every robot’s action, dataset, and contribution is transparent, traceable, and rewarded on-chain. Our vision is simple: Turn the robotics lifecycle into a participatory economy. Here's what's ahead in the coming weeks: Whitepaper V2 – A transparent blueprint of our next development stage. Tech Videos – Showcasing key elements of Robora's Framework. Partnerships & Onboardings – Expanding our global builder and research ecosystem. Full transparency from the team - Including detailed profiles, and personal video introductions from core members. Dapp Launch + 3D Builder – Letting anyone visualize, design, and interact with robots directly on-chain. Further development on the Modules - where each module functions independently yet connects into a unified verifiable framework. 3D Reconstruction Toolkit - Introducing a 3D Reconstruction Toolkit, a collaborative project that lets anyone contribute to the future of real-world simulation environments and earn royalties in return.

We’re proud to announce that Robora has joined the Real World AI Foundry, a global initiative led by IoTeX to shape the future of real-world AI alongside industry leaders and innovators. Together with partners such as Vodafone, Filecoin, Theta, and others, we are working to define shared standards, governance, and deployment frameworks that are grounded in reality, open to all, and aligned with human values. This initiative is centered around the world’s first open ecosystem of Real-World Models (RWMs), intelligent systems trained on live, verified data from sensors, machines, and people. At Robora, our mission has always been to bridge physical systems and intelligent agents. Joining the Foundry aligns perfectly with our vision for Embodied / Physical AI, intelligent systems that interact meaningfully with the real world. We’re excited to contribute to this next chapter of AI infrastructure and invite our community to follow along as we build.

This week has been another important chapter for Robora, with strong progress across product innovation, community engagement, and strategic initiatives. Although a great deal of our efforts are still happening behind the scenes, from exploring new partnerships and developer ecosystems to mapping out future opportunities, we also achieved several noteworthy public milestones: - Started the week by surpassing 2,000 $RBR holders, marking steady community growth. - Partnered with CryptoAutos – $RBR now accepted for car purchases & rentals worldwide. - Partnered with JuliaOS | $JOS – integrating Julia code modules & AI swarms into our robotics platform. Full integration will be available in our Github soon. - Launched the Robora Vision Module (RVM) – plug-and-play robotics with ROS2 compatibility. RVM tools include detection, segmentation, fiducial markers & COCO benchmarking. - Hosted our first AMA – full replay available for the community. - Expanded into academia with researchers in SLAM, perception & motion planning. WIth research progress live on our Github. - More researchers joining, accelerating path from labs to large-scale deployment. - Announced attendance at R3AL WORLD AI Summit @Token2049 Singapore (Sept 30), where we will be showcasing how Robora bridges AI + robotics with blockchain on the global stage.

We will have our first AMA tomorrow, 17 September at 4:00 PM UTC, hosted by our very own @LarryHashpowerX This session will cover our roadmap, technical progress, and upcoming milestones. Join us to hear key updates and what’s next as we continue building.

We promised more transparency. Now it’s time to meet another brilliant mind behind Robora. Quy has been contributing to Robora since 2025, bringing his expertise in computer vision, AI, and robotics to the development of the Vision Module, a core component that powers the platform’s intelligent visual perception. With a Master’s degree in Artificial Intelligence from Seoul National University of Science and Technology, South Korea, he combines strong academic foundations with hands-on engineering experience. At Robora, he focuses on integrating object detection, tracking, and scene understanding into the robotics framework, drawing on his deep experience in multi-object tracking, 3D reconstruction, and camera calibration to design systems that are both accurate and efficient. He also works closely with other engineers to ensure the vision infrastructure is scalable and aligned with Robora’s broader technical goals Before joining Robora, Quy worked as an AI Engineer at EM&AI, where he developed speech-to-text, name entity recognition and sentiment analysis systems. Additionally, he served as a researcher at MINT Lab (mint-lab.github.io/), publishing papers in computer vision and AI. His research on camera calibration, 3D motion tracking, and edge AI has been recognized at major conferences and journals. MINT Lab is an research group for perception, intelligence, and actions for mobile agents and devices such as robots, cars, drones, and also smartphones. MINT Lab belongs to Computer Science and Engineering Department in Seoul National University of Science and Technology (shortly SEOULTECH). Publications of Quy are, amongst others: - Cong Quy Nguyen, Sunglok Choi, MINT Camera Calibration Toolbox, Korea Robotics Society Annual Conference (KRoC), 2025 - Cong Quy Nguyen, Sunglok Choi, Generalized Camera Calibration: Camera Model Selection and Calibration with Effective Image Sampling, IEEE Sensors Journal, Vol. 25, No. 15, 2025 DOI Github: github.com/ncquy With a strong background in machine learning, signal processing, and decentralized AI, Quy continues to bridge the gap between AI research and robotics applications, helping advance Robora’s mission to build intelligent, autonomous systems.

Our collaboration with universities on the Robora Vision Module is now nearing completion. Together, we’ve developed key components that give robots and AI systems the ability to see and understand the world in real time. Next week, we’ll be highlighting some of the incredible people and partners who worked alongside us on these modules. Stay tuned! What we've built: Robora Vision Modules A modular, open-source computer vision system built for robotics and autonomous agents. Core capabilities include: 🧠 Computer Vision AI Modules – modular design, customizable per use case 🎯 Object Detection – real-time bounding boxes 🟣 Instance Segmentation – pixel-level object masks 📍 Marker Detection – ArUco and custom markers for navigation/localization 🔁 Tracking – consistent object recognition across frames 🔄 Multi-task Pipeline – each feature can run standalone or together ⚙️ Lightweight & Integration-Ready – Python-based, works with ROS2 and other robotics platforms 🎥 Demo-Ready – supports live video, webcam, or recorded footage How we're positioning it: Modular by design: use only what you need, or run it all in a unified pipeline Purpose-built for impact: enabling everything from navigation to scene understanding Open and flexible: made to integrate with real-world robotics systems In short: Open-source. Modular. Integration-ready. The foundation for intelligent, autonomous systems. github.com/RoboraDev/Vision_…

We are officially listed on CoinMarketCap. Check us out here: coinmarketcap.com/currencies…

Robora | $RBR is partnering with JuliaOS | $JOS to bring Julia code modules directly into our robotics platform, enhanced by JuliaOS AI agent swarms. This collaboration strengthens Robora’s modular framework, enabling more advanced decision-making, autonomy, and real-world orchestration across our robotic systems. Together with JuliaOS, we’re pushing the frontier of AI + robotics + blockchain, building the foundation for next-gen autonomous systems. Real integration following on the Github of @BuildOnJulia soon!

Dmitriy has been with Robora since the very beginning. From day one, his experience across major blockchain projects and modern infrastructure has been essential in shaping the project’s direction. Together with experts in robotics software engineering, he built the technical framework that serves as the foundation of Robora today. At Robora, he currently leads the development of the 3D Builder, one of the platform’s components. With his knowledge and experience, he also guides the rest of the engineering team, setting standards for architecture and long-term scalability. Before joining Robora, he gained over ten years of experience in fintech, blockchain, and AI. He worked on projects such as Cere Network, where he was involved in building blockchain bridges, explorers, and analytics tools, and is particularly experienced with EVM technologies. His technical expertise also covers microservice architectures, test-driven development, payment systems, and cloud integrations, making him a key contributor in bridging blockchain, AI, and robotics within Robora.

Robora Development Update At Robora, we take huge pride in keeping our community informed as we build. Every step forward is not just a technical milestone but a shared achievement, and that’s why we’re excited to share these updates with you: 1. Model Weights Management Added support for pulling open-source model weights directly from Hugging Face via the huggingface-hub Python package. Built an early CLI tool with rich terminal feedback to simplify model management. 2. Fine-Tuning SDK Roadmap Defined the path for our fine-tuning SDK: starting with Imitation Learning (IL) to adapt VLA models to new robot morphologies. Next, RLHF fine-tuning inside PyBullet, enabling models to handle new tasks, even adapting to edge cases like a robot continuing after losing functionality (e.g. a “broken leg”). Chose PyBullet as the simulation backend for its CUDA acceleration and reliability (with all configs stored in sims-env). 3. 3D Mapping SDK (In Progress) Began development of a companion SDK for creating 3D point cloud maps of real environments. Currently experimenting with photogrammetry to convert raw camera input into 3D meshes, aiming to reduce reliance on LiDAR. 4. Documentation Added roadmap direction and high-level guidance for contributors and interested developers in the Docs directory. 5. Initial Model Integration Prioritized early support for SmolVLA (efficient) and Pi0 (generalist policy) as part of the VLA SDK integration. 6. Development Priorities Current focus: fine-tuning in PyBullet and generating rich 3D simulation datasets. Next steps: inference logic and cloud/online integration, either in parallel or after the simulation-focused phase.

Introducing the Robora 3D Builder by our Co-Founder, Guang Cheng: a web based, drag and drop interface for rapid robotics prototyping. Designed for hobbyists and DIY enthusiasts, the MVP includes 5 - 8 essential hardware modules: wheeled bases, motors, servos, LiDAR, sensors, and an integrated starter brick for power and control. With a user friendly onboarding wizard, real time 3D visualization, and automatic component alignment, building a robot has never been easier. No coding or CAD required. Once your design is ready, export it as a URDF file or a parts list for quick prototyping, simulation, or assembly. Early access to the 3D Builder will be available through our Dapp shortly.

Great to see @LarryHashpowerX on stage at Inclusion 2025 Shanghai, where the conversations around finance, infrastructure and security, IoT and robotics echo much of what we’re building at Robora. Wondering what else we could see from Inclusion 2025👀

Not everything we’re working on is public yet. Connections with key robotics players are already taking shape. Moving faster than most realize. $RBR

This week Robora kept moving from concept to reality, expanding tools for developers, strengthening the hardware ecosystem, and growing the community behind it. Here are the key updates: -The Robora VLA SDK was introduced, a modular toolkit that makes it easier to integrate Vision-Language-Action (VLA) models into flexible robotic systems. It supports leading open-weight VLA models and can run inside simulation environments, helping developers and researchers train, adapt, and deploy intelligent robotics solutions. -A new partnership with Lemorele was announced alongside the Robora P300 (R), a high-performance wireless video streaming device that makes collecting visual data for AI training easier without the need for wired cameras. This unit will integrate directly into the VLA Module and speed up real-world robotics development. -Dmitriy was introduced as one of Robora’s key engineers from the very beginning. He leads the development of the 3D Builder, shaping the core technical foundation of the platform and setting long-term architecture standards for scalability and innovation. -Upcoming giveaways of the Robora P300 (R) hardware were shared for $RBR holders, giving early supporters the chance to contribute to the Physical AI training ecosystem and get early access to important tools. -We surpassed 2,900 $RBR holders!

Robora x ZKML Robora (RBR) and ZKML are joining forces to pioneer verifiable robotics. Robora is building the playground for modular robots, AI “brains,” and a tokenized economy where contributors are rewarded. ZKML brings cutting-edge zero-knowledge proofs to ensure that every model deployed in Robora is both authentic and verifiable. Together, we are creating a new standard: robots that not only act in the physical world, but do so with cryptographic guarantees of integrity and fairness. This partnership bridges physical AI and verifiable ML, ensuring trust at every layer. Privacy + Robotics = Unstoppable

Last week, we introduced Quy as part of our ongoing effort to share more about the people behind Robora, as we uphold transparency in how we work and who we are. This week, we're excited to continue that journey by introducing another key team member: Ege. Meet Ege, an industrial designer from Istanbul shaping the hardware behind Robora’s robotics platform. Starting his journey in aviation, he explored how shape, balance, and materials can push the limits of movement and efficiency. At Robora, he combines creativity and engineering to design the structural systems that bring our robots to life in Simulation Environment and in the real world. In this video, he shares more about himself and his role within Robora.

Real-world data is the missing link between simulation and physical intelligence. With the Lemorele P300 (R), Robora is closing that gap, turning every user into a contributor to embodied AI evolution. It enables real-time, high-definition video capture from any camera, whether it’s mounted on a robot prototype, a drone, or a handheld camera. This visual feed is transmitted wirelessly and losslessly to a connected device (tablet, phone, or PC) that runs the Robora VLA interface or data capture app. The device then streams or uploads these feeds directly into Robora’s cloud or local VLA processing node. By collecting data from diverse environments and use cases, Robora gains the foundation to train and fine-tune its models on real-world sensory information, moving beyond purely simulated data. This approach is key to reducing the sim-to-real gap, the performance difference between robots trained in simulation and those operating in complex physical environments.

Today marks the start of something new. We could have said hi to you ourselves… but instead, we let the future speak. This is only the beginning. Robotics, On-Chain. $RBR Platform is here sooner than you expect.

This marks our first Medium article. With just a 5 minutes read you'll get a better grasp of a high-level overview of our roadmap and what we’re aiming to achieve. robora.medium.com/introducti… From here on, we’ll be sharing monthly updates covering our latest development progress, events we’ve attended, and other key moments along the journey

This week at Robora we focused mainly on development. Our work went into improving the core tools that power the platform, from managing models and fine-tuning capabilities to 3D mapping and computer vision. We also expanded our network by joining new real-world AI initiatives and kept working on connecting research with practical robotics applications. Here are the key updates: - Published a Robora Development Update, sharing progress across the platform: added model weights management with Hugging Face integration, built an early CLI tool for developers, set the plan for the fine-tuning SDK with imitation learning and RLHF in PyBullet, and started work on a 3D Mapping SDK to generate real-world environments. - Robora joined the Real World AI Foundry, a global initiative led by @iotex_io alongside partners like Vodafone, Filecoin, and Theta. This collaboration helps create open standards and frameworks for real-world AI and supports our mission to connect physical systems with intelligent agents. - Released our September Monthly Recap, highlighting the latest development updates and providing an overview of where the platform is heading next. - Announced that our collaboration with universities on the Robora Vision Module is close to completion. This open-source computer vision system gives robots the ability to see and understand the world in real time and will soon be presented together with the researchers and partners who contributed.

This week, Robora continued to evolve from an ambitious idea into a functioning ecosystem. Our focus was on building out the core technology, improving tools for developers and laying the groundwork for the next stage of growth. Step by step, the project is becoming a foundation for Physical AI where robotics, intelligence and blockchain connect into a single verifiable system. We shared a clear look at what’s coming next as Robora enters a pivotal phase. The updated roadmap highlights several major goals ahead including the release of Whitepaper V2, the launch of our Dapp and 3D Builder, new technical videos and deeper development of key modules. All of this is part of our mission to create a participatory robotics ecosystem where actions, data and contributions are transparent and verifiable on-chain. Transparency also remained a priority this week as we introduced Quy, one of the engineers behind Robora’s Vision Module. With strong experience in computer vision, multi-object tracking and 3D reconstruction he plays an important role in building the perception layer that allows robots to understand and interact with their surroundings. We also presented Robora Sim, a new simulation environment built on PyBullet that helps robots learn and adapt before they’re deployed in the real world. By combining VLA-based planning with motion control it supports imitation and reinforcement learning, domain randomization and synthetic data generation all aimed at closing the gap between simulation and reality.

This past week has been a significant one for Robora, marked by major strides across product development, community growth, and strategic transparency. While much of our work continues behind the scenes such as exploring new resources, developer communities, and future opportunities, we also hit several key public milestones: - 3D Builder Public Preview We launched the first public preview of our 3D Builder, offering the community an early look at how robots can be designed and prototyped using our platform. - First Medium Article Our debut article is now live on Medium, offering insights into our journey so far, our long-term vision, and what’s coming next. - Community Milestone Robora’s supporter base has now surpassed 1,000 unique holders, a strong vote of confidence and a testament to growing engagement. - Tokenomics Release We shared a transparent breakdown of our tokenomics, outlining our economic model and token distribution, built for long-term sustainability. We have also vested our Team and R&D Tokens allocation on UNCX for 24 months, reinforcing our commitment to responsible and strategic growth. - Smart Contract Audit in Progress A third-party smart contract audit is currently underway to ensure maximum security for our community and ecosystem.

You can now listen to the full recording of the Space. It was an in depth conversation on what we are building, why it matters, and how we are approaching the next steps. If you were not able to attend, this replay will bring you fully up to speed.

We've got an exciting surprise for our community. Our focus is on bonding and growing together. With that in mind, we're thrilled to introduce our dedicated team, who's been working hard behind the scenes and will continue as we push forward.

Seeing Optimus adapt Kung Fu moves in real time shows how motion, balance and perception are crossing a new threshold. With Robora, we’re focused on making that transition not just possible but practical, building robots that can learn, act and evolve in the real world.

In 45 minutes at 18:00 CET we are going live on X Spaces. This is our first community discussion where we will introduce Robora, share the bigger vision, talk about what we are building right now, and answer questions directly from the community. Join us here: nitter.app/i/spaces/1jMKgRWvjVOxL

We’re excited to announce a new partnership between Robora, $RBR, and Palm AI, $PALM. Together we are working to connect decentralized robotics with scalable AI infrastructure, creating stronger utility for both ecosystems. This collaboration is designed to benefit our communities directly and accelerate adoption for builders worldwide. Robora is committed to driving value into the $RBR ecosystem while supporting $PALM holders through this partnership.

We’re actively working on several fronts to accelerate development and ensure maximum efficiency, with the goal of reaching the market quickly. This week, we focused on the following areas: 1. VLA Fine-Tuning & Adaptation Pipeline We are working on our VLA SDK to support open-weight models including SmolVLA and Pi0 for now, with GrootN1.5 planned for near future, each offering different trade-offs between model size, inference speed, and generalization. Our current focus is on implementing action-head only fine-tuning using QLoRA (where required) a technique that allows efficient training on consumer-grade GPUs while preserving the pretrained vision-language backbone. This approach enables us to remap the model’s action space for different robotic configurations, essentially allowing a single VLA to learn how to control new hardware modules (arms, grippers, mobility units, etc.) without degrading its multimodal reasoning ability. By isolating adaptation to the action head, we maintain the core representation and generalization power of the model while making it contextually aware of our new robotic action space. 2. Reinforcement Learning for Low-Level Control Policy Parallel to the VLA pipeline, we are working on setting up a PyBullet-based physics simulation environment designed for large-scale reinforcement learning experiments. This environment trains neural control policies using Proximal Policy Optimization (PPO) and SAC algorithm, two state-of-the-art algorithms for continuous control. These RL policies are being trained to handle locomotion, balance and stability under dynamically changing environments and turbulences, leveraging parallel simulation for faster convergence and robustness. 3. The key architectural principle here is hierarchical separation of control: The VLA acts as the top-level planner, interpreting natural language commands, visual input, and task context. The RL policy serves as the low-level actuator, executing smooth, stable movements in real time at higher action frequencies. This separation allows the system to combine semantic intelligence with physical resilience making our robots adaptable to diverse terrains, mechanical modules and environmental uncertainties, far beyond what conventional PID or trajectory-based controllers can achieve. Together, these two components form the backbone of our Physical AI stack , a system designed to reason, adapt, and act seamlessly across our robotics stack.

We just surpassed 1,000 holders. We are growing fast and the community is only getting stronger. This is just the beginning. $RBR

Exciting news! The swap pool is officially live on Messier's P2P Exchange! We’re proud to partner with @MessierM87 Now, you can buy or sell the $RBR token directly on p2p.messier.app This is a step towards more accessible crypto solutions.

We go beyond “robots on-chain.” We remove the technical barrier so makers and non-coders can design hardware in a drag-and-drop 3D Builder, attach ready-made Physical AI, and deploy to real robots. Off-chain keeps control fast, while on-chain provides access, payments, and proofs. All so the community can participate and earn from real-world robotics.

A new era where: • Robots are built, trained, and monetized; • Compute flows across a grid, syncing data and intelligence to where it matters; • Every design, brain, and dataset can earn.

In industrial robotics, global giants like ABB, Epson, FANUC, and KUKA dominate the market. Their machines power factories, cars, and electronics across the world. But the industry is shifting. Automation can no longer remain a privilege of the largest, it needs to be accessible, flexible, and built for everyone. That’s why we’re building Robora, a new generation of robotics designed to bring the power of the giants to those who are creating the future.

We’re moving into the next stage of Robora. In the coming days you’ll see: Early Access applications opening First look at the 3D Builder An interview on our strategy & vision Release of the Nexus Hub A major partnership announcement Staking going live Clear steps, steady progress. $RBR

We've almost completed our first week, and it's been an exciting journey setting the foundation for everything that's coming next. This week, we focused on building strong, solid ground to launch all the things we have in store. Here’s a quick recap of what we've accomplished this week: • $RBR TGE and launch • LP locked for 5 years • Listed on CMC + CG • Announcement of 1v1 interview with Co-Founder • Etherscan updated • Meet the team released • Partnership with @MessierM87 and listing on their platform • Partnership with @palmaierc • 800+ holders • Ordered Nvidia Jetson Thor, making us one of the first companies to test it

Next week we are dropping a 1 on 1 interview with our Co Founder: Guang Cheng Luo. A closer look at Robora’s roadmap, our approach to robotics and decentralization, and what the future holds. Learn more about him: linkedin.com/in/guang-cheng-…

We have been getting few questions regarding our tokenomics and token utility. That's why we provided a detailed breakdown below 👇 Token Distribution Total Supply: 100,000,000 $RBR Multi-signature control Treasury: Multi-signature wallet control Marketing: Multi signature wallet control Node Incentives: Multi-signature wallet control Vesting schedules R&D: Linear vesting over 24 months Team: Linear vesting over 24 months Token utility The $RBR token serves multiple functions in the ecosystem: 1. Accessing the 3D builder and Synth Trainer: 2. Buying & Selling Assets on the Marketplace: 3. Node incentives, compute rewards and staking

This week, Robora made solid progress on multiple fronts as we continued to refine our robotics stack, improve performance and move closer to real-world deployment. Our focus has been on improving model adaptability, advancing physical intelligence and strengthening the hardware foundation that supports our platform. We introduced Ege, an industrial designer from Istanbul who plays a key role in shaping Robora’s hardware systems. His background in aviation and product design helps bridge creativity and engineering, designing structural systems that bring our robots to life both in simulation and in real-world environments. Significant strides were also made in hardware integration. We successfully addressed three out of five major challenges for vision-to-prompt integration, including signal communication, wireless connectivity and onboard SDK support. These improvements bring us closer to a fully functional hardware layer that connects directly with our software stack. On the development side, two key components of our Physical AI architecture saw major updates. The first is the VLA Fine-Tuning and Adaptation Pipeline, which enables our models to support different robotic hardware configurations while preserving their reasoning capabilities. Using efficient fine-tuning techniques like QLoRA, we can retrain only the action layer, allowing a single VLA model to adapt to new modules such as grippers, arms or mobility units. In parallel, we continued building a PyBullet-powered simulation environment for reinforcement learning. This platform trains low-level control policies for locomotion, balance and stability in complex and dynamic conditions, using advanced algorithms like PPO and SAC. Our approach relies on a clear separation of control: the VLA model serves as the high-level planner, understanding visual input and task context, while RL-based controllers handle precise, real-time execution. This layered design allows our robots to combine intelligence with physical robustness and adapt to a wide range of environments and mechanical configurations.

Excited to see our friend @LarryHashpowerX on stage at Inclusion 2025 in Shanghai. This event brings together leaders in global finance, tokenization, and next-gen infrastructure. And now, robotics is part of the conversation. Larry will be sharing perspectives closely aligned with Robora’s vision, helping us strengthen our presence in the Asia-Pacific region as Physical AI takes the spotlight. Stay tuned for more👀 $RBR

We’re excited to share that $RBR is live on CoinGecko Follow the stats here : coingecko.com/en/coins/robor…

🚀 Just submitted our request to list $RBR on @coingecko 🎫 Request ID: CL2608250015 🔗 GeckoTerminal URL: geckoterminal.com/eth/pools/…

Physical AI is quickly entering our everyday lives. Faster than most can imagine. By 2030, it is expected that Physical AI will run companies, teach the next generation, keep us healthy and informed, and do most of the heavy lifting. However, today's Physical AI work mainly alone, operating in centralized siloes, not embracing the decentralized capabilities that blockchain can offer. We believe this should and will change. Connecting one robot to another, connecting to us, essentially creating a vertical ecosystem of robotics - Will be the future. And we're here to take the leap.

Robotics just got a serious upgrade. NVIDIA’s new Jetson Thor is built to be the brain of the next generation of robots — faster, smarter, and more efficient than anything before it. Why it matters: Jetson Thor packs 800 TFLOPs of edge AI compute into a compact chip that combines GPU, CPU, deep learning accelerators, and built-in safety modules. This allows advanced AI to run directly on robots without relying on slow or costly cloud connections. We’ve placed our first order of Jetson Thor units. Soon, we’ll be unboxing them with the Robora crew 🎥

Robora is a new kind of playground for robotics and AI on-chain. You can design robots virtually in a 3D builder, train their “brains” to handle real tasks like navigation or assembly, and share or sell what you create as modules in the marketplace. Robots, data, and intelligence become community-driven assets powered by $RBR. Read more about the vision in our docs: robora.gitbook.io/robora-doc…

Buy and sell tax is now 0%. This decision follows detailed financial modeling confirming our ability to sustain operations. New revenue streams are being developed to ensure long term stability. Removing the tax aligns incentives across holders, traders and partners as we move toward a more organic, utility-driven growth model.

We are live: 0x2C431766E48Ec4A17dc052d9d3feF6b6A9ae8D62 Exciting times ahead!

1. Objective This experiment was designed as a proof of concept to show that our VLA model (Pi0) can be successfully fine-tuned for robotic tasks and that our training pipeline, including Weights & Biases (W&B) tracking, works as intended. This integration enables comprehensive tracking of training metrics, hyperparameters, and system utilization, helping ensure better reproducibility and optimization in future fine-tuning runs. 2. Why This Matters This run proved that: The Pi0 VLA model learns properly on real robotic data. W&B analytics integration works, giving us full visibility into loss curves, gradients, GPU usage, and training behavior. We now have a baseline VLA fine-tuning setup that can be repeated and improved. For more technical information, please read on👇 A. Experiment Setup A fine-tuning session was conducted on the Pi0 model, known for its strong embodiment and visuomotor grounding capabilities. The training used the SOARM101 dataset and was executed on an NVIDIA H200 GPU. Key configuration details: - Model: Pi0 - Paligemma backbone (3B) + Gemma based action expert (300M) - Dataset: SOARM101 (robotic manipulation tasks) for POC - Training Steps: 20,000 - Peak VRAM Utilization: Around 35 GiB - Optimizer: AdamW - Learning Rate Scheduler: CosineAnnealing - Framework: Robora VLA fine-tuning pipeline B. Parameter-Efficient Fine-Tuning (PEFT) Integration In addition to the baseline run, follow-up experiments are planned using PEFT techniques such as LoRA and QLoRA. These will evaluate trade-offs between VRAM efficiency and fine-tuning performance. The goal is to establish optimal configurations for efficient adaptation of embodied vision-language-action (VLA) models under limited compute conditions. C. Observations and Analytics The W&B analytics provided detailed visibility into multiple training aspects, including: - Loss convergence across 20K steps - Gradient stability and magnitude distribution - Learning rate dynamics under cosine annealing LR Scheduler wrapper. - GPU utilization and memory efficiency - Optimizer–scheduler interaction effects on overall training performance These analytics will guide the selection of optimal optimizer–scheduler pairs and hyperparameter configurations for upcoming fine-tuning cycles. D. Conclusion and Next Steps This session successfully validated W&B analytics integration and established a strong baseline for Pi0 model fine-tuning on the SO-ARM101 dataset as a proof-of-concept. As soon as our Sim-data pipeline will be ready, we will be able to run even more robust and good fine-tuning session for different robot morphology and tasks. The next phase will include comparative evaluations using LoRA and QLoRA to analyze efficiency and performance trade-offs. Future experiments will also track inference latency, task completion accuracy, and embodied control performance metrics.

1/6 What if building robots & IoT devices was as easy as drag-and-drop? Introducing Robora: A DePIN platform revolutionizing modular robotics! Let's break it down in this thread

Since launch we have been keeping our ear to the ground, listening closely to the community and moving fast. 🟣 First GitHub repo will open publicly shortly with more repos to follow as we scale towards full transparency. 🟣 Sneak peek of the Robora platform in progress showing how on chain robotics and modularity come together. What’s next ⏭️ 🟪Early access for the first 100 people applying through our dApp giving them the chance to test Robora’s core framework before anyone else.

VLA Fine-tuning Module Update A. Fine-Tuning Pipeline Enhancements - Added default configurations and state management for multiple optimizers, including SGD, SGD with Momentum, Adam, and AdamW, enabling end-users to experiment with different optimization strategies. github.com/RoboraDev/VLA_Mod… - Integrated several learning rate scheduler wrappers -> StepLR, CosineAnnealing, LinearDecay, and ExponentialDecay, allowing seamless selection and comparison through Wandb for fine-tuning analytics. github.com/RoboraDev/VLA_Mod… - Default implementations for Pi0, Pi0.5, and SmolVLA support a maximum action and observation dimension of 32. For high-complexity robotic agents such as Humanoid, the action encoder, state encoder, and action decoder feature dimensions will need to be scaled accordingly, these can be done easily as these are 3 lines of pytorch code but have to be implemented from scratch. For each model, this will be specified inside config.py and the corresponding WithExpert.py file will inherit it. github.com/RoboraDev/VLA_Mod… B. PI0 Policy Implementation - Implemented the Pi0 Policy architecture in PyTorch, referencing the Physical Intelligence OpenPI repository for core design principles & configurations. - Implemented PI0Config, will also be added yaml, json support for custom configs in fine-tuning. github.com/RoboraDev/VLA_Mod… C. VLA Util helper functions Implementation - get_device_info, torch_device, device_name for accelerators - JSON Serialize & deserialize functions to store the optimizers state on disk. - Parameters utility helpers : get device, dtype, output shape etc github.com/RoboraDev/VLA_Mod… Plan for Tomorrow: - Support for SmolVLA and Pi0.5 will be implemented next, as these architectures share a common Vision-Language Model (VLM) architecture with minor variations in module structure and feature dimensions. - Lerobot dataset framework integration for dataset management: will integrate online dataset as a Proof-of-concept.

This week, we’ll begin pilot deployments of the capture pipeline within our simulation environment, an intermediary step before scaling to real-world data collection. These tests will validate the full end-to-end flow: from visual capture and 3D reconstruction, to data upload, fine-tuning and behavioral analysis of the VLA model. The purpose is clear: to evaluate how well our models adapt when exposed to semi-synthetic, simulation-anchored data that mimics real-world complexity. By introducing variability in lighting, geometry and object dynamics, we can measure the model’s domain adaptation efficiency and its capacity to generalize across unseen conditions, which is a key metric for narrowing the sim-to-real gap. We’ll also launch the first fine-tuning experiments through the VLA SDK, processing captured scenes and quantifying shifts in model behavior compared to purely simulated inputs. This will help us refine both our data pipeline and our fine-tuning methodology before scaling up to large-scale physical capture campaigns. In parallel, work begins on the Robora Data Policy & Contributor Incentive Layer, designed to credit and reward those who supply valuable visual data. This framework will connect to Robora’s on-chain architecture, establishing verifiable proof-of-contribution and preparing for tokenized incentive mechanisms. The ultimate goal: to transform data collection from a passive process into an active, community-driven ecosystem where every user helps teach embodied intelligence to see, understand and evolve.

Highlights this week: • Lemorele P300 (R) Integration The Lemorele P300 (R) officially joins Robora’s hardware suite, turning every user into a real-world data contributor. It enables real-time, high-definition video capture from any camera (robot, drone, or handheld) and wirelessly streams it to devices running the Robora VLA interface or data capture app. These feeds are then uploaded directly into Robora’s cloud or local VLA nodes, powering real-world model training and fine-tuning. • Smart Contract Audits Completed We finalized our DApp and successfully conducted audits on the smart contracts that will be deployed, through @SolidProof_io . This solidifies the foundation for our upcoming releases. • VLA Fine-Tuning SDK Pipeline Implemented the full code pipeline of the VLA Fine-Tuning SDK, connecting live capture, processing, and model fine-tuning into a single, automated flow. • 3D Reconstruction & Scene Understanding Advanced work on building complete 3D scenes from raw visual data, reconstructing geometry, texture, and spatial layout for real-world mapping and model sharing. On top of that, scene-understanding algorithms now analyze these reconstructions for object segmentation, semantic labeling, pose estimation, and environment profiling, creating structured data that robots can actually learn from. This dual process (reconstruction + understanding) is grounded in the latest robotics research showing that blending real-scene 3D data with simulation sharply reduces the sim-to-real performance gap, enabling more robust perception and adaptability in embodied AI systems.

It’s great to see Larry establishing the foundational partnerships that will enable Robora to thrive as a leading platform for embodied AI. These collaborations are not only laying the groundwork for future innovation but will also bring significant recognition and expanded hardware capabilities to support Robora’s long-term growth and impact. Stay tuned for more confirmed partnerships coming soon.

We’ve officially decided to keep the buy tax to 0% indefinitely to support our community and encourage continued growth. The sell tax remains at 4% as normal, helping sustain the project and its future developments.

We’re closing another strong month at Robora, one filled with real progress, new collaborations and innovation. To everyone who’s been part of this journey, thank you. Your support drives the mission of building a verifiable, open future for robotics. Together, we’re showing how far a community can go when driven by a shared mission. Here’s a look at what we’ve been working on this October, in our latest Medium article👇 robora.medium.com/monthly-re…

Building the Foundation for Real-World 3D Capture We’re making strong progress on Robora’s next step: enabling people to easily capture real-world 3D data using affordable hardware. 1. Smarter Camera Setup We’re finalizing a simple multi-camera system that works together with a depth sensor. This setup allows anyone to record high-quality, multi-angle scenes without expensive gear, making 3D data collection more accessible. 2. Hybrid Processing Pipeline Captured footage is lightly processed on the device (to blur faces, remove license plates, and protect privacy) before being uploaded. The heavy lifting (turning that footage into detailed 3D environments) happens on powerful cloud servers using advanced reconstruction methods. This design keeps the hardware simple while still producing professional-grade visual results. 3. Data Protection & Transparency We’re also adding a compliance layer to ensure all collected data meets privacy and legal standards. Contributors will know exactly how their data is used, how long it’s stored, and what rights or royalties they hold over it. Why This Matters This setup lays the groundwork for Robora’s ecosystem, where creators, developers, and robotics teams can capture and share real-world 3D data safely and efficiently. It’s a major step toward large-scale, decentralized 3D scene generation. What’s Next We’ll begin real-world testing of the capture kit and cloud reconstruction pipeline, fine-tuning the process before opening it up to early contributors.

Robora's 3D-Builder is the heart of our platform, an intuitive web-based DApp that empowers users—from hobbyists to engineers—to design modular robots without coding expertise.

Great suggestion!

What is a Robora Synth? It’s where Vision-Language-Action models finally make AI useful for real robotics work. A Synth is a specialized robotics executor powered by VLA models that performs tasks through a continuous perceive-reason-act cycle. Before diving deeper in Synths and VLA's, let's compare it with the LLMs which most people are already familiar with. Large Language Models (LLMs) like GPT-4, Gemini or Claude are remarkable reasoning engines that excel at generating text, answering questions and even brainstorm idea's. Yet, these LLMs are fundamentally limited to words. They can't interact with real world environments, perceive visual clues or execute precise actions like moving a robot arm or navigating obstacles. VLA models surpass LLMs by integrating visual perception, language understanding, and actionable outputs in a single, efficient forward pass. This makes VLAs better suited for real-world applications because they bridge the gap between abstract reasoning and physical execution. Robora's Synths take this further by integrating community-shared enhancements to fine-tune behaviors and excel in execution.

1/4) The Data Deluge in Robotics. Every robot you encounter is a data volcano, erupting terabytes of complex information. The sleek hardware catches your eye, but the real challenge lies in the chaotic data overwhelming those who manage it. We're here to tackle this crisis, proving that the future of robotics isn’t only better hardware, but a combination with better data infrastructure and real-world data availability

A key limitation in current AI systems is that agents (e.g. those built on LLMs like GPT) can only describe or plan actions but cannot execute them reliably in dynamic, physical settings.

4/4) The future of robotics and IoT hinges not only on advanced hardware but on robust, decentralized data infrastructure. Robora is at the forefront, offering solutions like better data infrastructure (with standardized data pipelines and AI-driven diagnostics to help developers manage and interpret data faster) and a token-incentivized marketplace where real-world data can be shared. These tools prioritize critical data, filter noise, and predict failures before they occur, transforming how the industry handles the chaos. By leveraging blockchain for secure sharing, open-source VLA models for intelligent training, and a 3D builder for custom designs, Robora democratizes access, reduces costs, and redefines reliability.

5/6 Features Spotlight: AI library (YOLOv8 vision, Llama 3 language agents), decentralized compute for deployment, and growth loop: Usage → fees → $RBR buybacks → liquidity! Build, deploy, earn.

6/6 Join us building the future! Check our Gitbook for details or start building. What robot would you create?

4/6 Fair Earnings: Register blueprints in our on-chain registry. Smart contracts auto-split royalties (70% to you)! Sell/licenses earn perpetual income. DePIN security prevents hacks.

3/6 Robora's Solution: Our web-based 3D builder lets you assemble broad range of parts (sensors, actuators) with AI help and cut costs 80%! No vendor lock-in, just seamless designs. Powered by ROS for modularity

2/6 The Problem: Robotics is tough! High costs lock out hobbyists, centralized systems risk 70% breaches at endpoints (IBM data), and manufacturing drags on for months. Innovation stifled, creators underpaid. Sound familiar?

3/4) However, the real issue emerges when hardware fails or performs sub-optimally. A single glitch in a robot’s operation, say a misaligned sensor or a faulty navigation module, can trigger cascading errors. These malfunctions aren’t just mechanical; they’re buried in the data, forcing engineers to sift through terabytes to pinpoint the root cause. This process delays fixes, halts production, and skyrockets costs. Solving these issues isn’t simple. Engineers can’t just reboot a system and move on. They must dive into massive datasets, analyzing logs, sensor outputs, and error codes to diagnose problems. This painstaking process can take hours or days, stalling operations and draining resources.

2/4) Robots rely on real-world data to function correctly. Sensors, cameras, and other inputs must capture accurate, dynamic environmental data to enable precise movements, decisions, and interactions. Without high-quality, real-time data from their surroundings, robots can misinterpret situations, leading to errors, like not being able to make a distinction between an air fryer tray and its body, pulling the entire unit off the counter. With more data comes a better understanding of how the tray separates from the air fryer. Real-world data = robot success. No data = errors.