Industry Briefing
A single destination for timely, editor-curated robotics news from around the world.
Peking University and Beijing Humanoid Robotics Center Achieve Breakthrough in Cross-Embodiment Imitation
Peking University, in collaboration with the Beijing Humanoid Robotics Innovation Center, has introduced Demo-JEPA, an innovative system designed for cross-embodiment imitation in robotics. This groundbreaking approach allows a Franka robot to learn tasks by observing demonstrations from various robotic platforms. By redefining imitation as a goal-planning problem rather than merely replicating actions, Demo-JEPA significantly improves adaptability among different types of robots. The unveiling of this technology marks a significant advancement in the field of robotics, showcasing the potential for enhanced learning and flexibility in robotic systems.
Cross-Embodiment Imitation Robotic Learning AI Robotics Machine Learning
Google DeepMind Robotics Head Details 'Surprising' Cross-Embodiment AI, Calls Home 'The Hardest Environment'
In a recent interview, Carolina Parada from Google DeepMind highlighted the innovative features of Gemini Robotics 1.5, particularly its unique 'agentic' two-part brain. Parada emphasized the robot's impressive capability to transfer skills across different robotic platforms, showcasing a significant advancement in robotics technology. She also expressed her belief that the home environment represents one of the final frontiers for the application of such technology, suggesting a future where robots could play an integral role in daily household tasks. This discussion sheds light on the ongoing developments in robotics and the potential for transformative impacts in personal living spaces.
vla World-Models AI Gemini google-deepmind Carolina-Parada
Imitation learning is reshaping the training of physical AI for industrial environments
Imitation learning is revolutionizing the training of industrial robots by moving away from traditional rigid programming methods to a more adaptive approach that emphasizes learning through real-world interactions. This shift is highlighted by Anders Billesø Beck, who underscores the importance of high-quality data, the application of force, and the use of production-grade hardware in this new training paradigm. As industries increasingly adopt these advanced techniques, the focus on enhancing the capabilities and efficiency of robots is becoming paramount, paving the way for more sophisticated automation solutions. The transition is not only expected to improve the performance of robots but also to streamline production processes across various sectors.
Starmind's Orbital Compute vs. Terrestrial Data Centers: Analyzing Resource Advantages
Starmind's orbital compute technology presents a significant advantage over traditional ground-based data centers by eliminating constraints related to land, water, and grid permitting. While terrestrial data centers are currently cheaper and faster to construct, with U.S. data center spending reaching $85.3 billion in 2026, Starmind's approach focuses on addressing the growing resource limitations faced by hyperscale facilities. The significance of Starmind's technology lies in its ability to sidestep the increasing challenges of land and water usage. For instance, a 100 MW data center can consume approximately 530,000 gallons of water daily for cooling, while Starmind's AI1 utilizes deployable liquid radiators that require no water. This structural advantage could resonate with investors as the demand for AI computing continues to escalate, potentially leading to annual water withdrawals of up to 1.7 trillion gallons by 2027. Looking ahead, Starmind's next milestones include the launch of AI1 prototypes scheduled for early 2027. However, the technology's claims regarding cooling efficiency and operational reliability remain unverified until real flight data is available. As the industry evolves, the competition between orbital and terrestrial solutions will become increasingly relevant, particularly in the context of resource management and sustainability.
New 10-watt antenna helps underwater robots communicate across 2,296 feet
Researchers have developed an innovative antenna system aimed at enhancing communication between underwater robots, particularly in challenging environments such as murky waters. This advancement comes as part of ongoing efforts to improve the efficiency and effectiveness of robotic operations in marine settings. The new system was unveiled during a technology conference held in San Diego on October 15, 2023. The motivation behind this development stems from the increasing reliance on underwater robots for various applications, including environmental monitoring, search and rescue missions, and marine research. Traditional communication methods often struggle in low-visibility conditions, which can hinder the performance of these robots. The newly designed antenna system utilizes advanced signal processing techniques to facilitate clearer and more reliable communication between multiple robots operating simultaneously. By overcoming the limitations posed by murky water, this technology promises to enhance collaborative efforts among underwater robots, leading to improved outcomes in their respective missions. As the demand for autonomous underwater vehicles continues to grow, this breakthrough could play a crucial role in advancing the capabilities of marine robotics, ultimately contributing to better data collection and exploration of underwater environments.
Embodied or virtually represented: Navigating the embodiment debate in human-robot interaction
In a groundbreaking study published in the May 2026 issue of Science Robotics, researchers have unveiled a new robotic system designed to enhance surgical precision. This innovative technology, developed by a team of engineers and medical professionals, aims to improve patient outcomes in minimally invasive procedures. The research was conducted at a leading medical institution, where the team tested the robotic system in various surgical scenarios. The motivation behind this development stems from the increasing demand for advanced surgical techniques that can reduce recovery times and minimize complications. By integrating advanced algorithms and real-time imaging, the robotic system allows surgeons to perform intricate tasks with greater accuracy than traditional methods. Initial trials have shown promising results, indicating a significant reduction in surgical errors and improved overall efficiency in the operating room. As the medical community continues to seek ways to enhance surgical practices, this new technology represents a significant step forward in the quest for safer and more effective medical interventions. The team plans to conduct further studies to refine the system and explore its applications across different types of surgeries.
Focus
Two Years of Rigorous Testing Across 52 Scenarios: Embodied Intelligence Redefines Visual Navigation Technology
As embodied intelligence moves from laboratory settings to practical applications, researchers are addressing a significant challenge: enabling mobile agents to navigate effectively without relying on satellite signals. A recent exploration into modular visual navigation technology reveals promising advancements that have been validated in extreme environments. This innovative approach enhances the capabilities of various robotic applications, paving the way for more robust and versatile navigation solutions in real-world scenarios. The development of this technology is crucial as it aims to overcome the limitations posed by traditional navigation systems, particularly in areas where satellite signals are unreliable or unavailable.
Visual Navigation Robotics Autonomous Drones Sensor Technology
SpeakOn’s dictation device is a good idea marred by platform limitations
A new device priced at $129 has been launched, designed to enhance transcription capabilities for iPhone users. Utilizing MagSafe technology, this innovative accessory easily attaches to the back of compatible iPhone models, allowing seamless integration across various applications. The device aims to streamline the transcription process, making it more efficient for users who rely on accurate note-taking and documentation. With its release, the product is expected to appeal to professionals, students, and anyone in need of reliable transcription tools. The introduction of this device reflects the growing demand for advanced mobile accessories that improve productivity and user experience.
Hardware iPhone review magsafe transcription ai dictation
Custom Application Development Services Enhance Customer Portal Solutions
The evolution of software development for customer portals has transitioned from basic ticket dashboards to sophisticated omnichannel hubs. These modern portals utilize API-first backends to deliver seamless content across various platforms, including web and mobile applications, addressing the specific needs of regulated industries. As off-the-shelf portal solutions often fall short for sectors like healthcare and finance, the demand for custom application development services is rising. Companies are increasingly seeking tailored solutions to overcome limitations such as rigid data models and licensing constraints, which hinder their ability to support complex workflows and customer journeys. Looking ahead, organizations must focus on defining their portal vision and selecting the right development partner to ensure a successful implementation. The article emphasizes the importance of planning for cross-platform development and long-term support to align with business goals, particularly in industries that require secure and user-friendly experiences.
Computing Software API integration business software cloud computing cloud engineering
Chinese University Develops OriCube Sensor to Enhance Robot Tactile Sensitivity
Researchers from the University of Science and Technology of China have developed the OriCube, a compact six-dimensional force/moment sensor that mimics human fingertip sensitivity. Measuring just 14×14×12 mm and weighing 4 grams, it achieves a remarkable resolution of 3 millinewtons within a 23-newton range, allowing it to detect even the lightest touch, such as a feather. This innovation is significant as it addresses the limitations of current robotic tactile solutions, which often rely on electronic skin or array sensors that face challenges like complex wiring and data processing. By embedding the OriCube directly into the fingertips of robotic hands, the sensor captures minute force changes and calculates precise contact points and force vectors, offering a new approach to tactile perception in robotics. The OriCube has demonstrated low power consumption of 45 milliwatts, minimal crosstalk, and high measurement accuracy. Its ability to sense both delicate touches and withstand impacts positions it as a robust solution for enhancing robotic dexterity in uncertain environments. No further timeline was disclosed at the time of publication.
Robotics Tactile Sensors Force Sensing Artificial Intelligence
1X Enhances NEO Humanoid Robot with Advanced 25-DOF Hands for Versatile Tasks
Norwegian robotics firm 1X has introduced new 25-degree-of-freedom (DOF) tendon-driven hands for its NEO humanoid robot, marking a significant advancement in robotic dexterity. These hands feature 22 actuated joints across the fingers and palm, along with three at the wrist, enabling NEO to perform tasks such as assembling LEGO models and catching balls with precision and strength. The redesigned hands allow for force sensing and durability, overcoming previous hardware limitations in robotic manipulation. With a unique tendon-drive system and low gear ratios, the hands can detect contact forces and provide continuous proprioception, enhancing the robot's ability to manipulate objects safely and effectively. The hands' human-like joint distribution, particularly the opposable thumb, facilitates a wide range of fine manipulation tasks, making NEO suitable for various household applications. 1X has commenced mass production of the NEO robot at its new California facility, aiming to commercialize home robots for daily assistance. The company emphasizes the hands' combination of precision, strength, and safety features, including IP68 waterproofing and self-cleaning capabilities. No further timeline was disclosed at the time of publication.
AI and Robotics
Wanxun Technology Launches Universal Charging Service Engine with 0.000s Tolerance
On July 9, Wanxun Technology unveiled its 'Flexible Charging' universal charging service engine in Beijing, marking the industry's first comprehensive solution for public, dedicated, and home charging applications. This engine features a unique 0.000s tolerance technology, which addresses the core challenges of automatic charging in chaotic environments, enabling reliable and scalable commercial applications across various scenarios. The significance of this launch lies in its potential to overcome the limitations of existing automatic charging solutions, which often struggle with unpredictable variables such as diverse vehicle models, environmental conditions, and user behaviors. Wanxun's technology promises to enhance safety, reliability, and adaptability, making it suitable for a wide range of charging situations, from public stations to private homes. Looking ahead, Wanxun Technology aims to expand its automatic charging solutions across various sectors, including unmanned logistics and public transportation. The company has already initiated collaborations with manufacturers, operators, and government entities to accelerate the deployment of its solutions. No further timeline was disclosed at the time of publication.
What Exactly is Being Modeled by World Models?
Recent discussions in the field of embodied intelligence have brought to light the concept of 'world models,' revealing significant confusion regarding its definition and the diverse methodologies being employed across the industry. Experts are examining the limitations of existing modeling techniques and the challenges posed by data quality, underscoring the necessity of analyzing failures within training data. The discourse emphasizes that the size of parameters alone does not guarantee success in developing effective world models. This exploration is crucial as the industry seeks to enhance the understanding and application of embodied intelligence, paving the way for more robust and reliable systems.
World Models Embodied Intelligence Robotics AI Data Challenges
China’s Alibaba unveils AI brains designed to power the next generation of robots
Alibaba, the Chinese technology giant, has unveiled its inaugural family of embodied AI models, marking a significant advancement in artificial intelligence technology. This launch, which took place recently, aims to enhance the interaction between humans and machines by integrating large language models with physical embodiments. The initiative is part of Alibaba's broader strategy to innovate and lead in the AI sector, responding to the growing demand for more intuitive and responsive AI systems. By leveraging its extensive data resources and expertise in machine learning, Alibaba seeks to revolutionize user experiences across various applications, from customer service to entertainment. The company plans to continue developing these models to further improve their capabilities and expand their use cases in the coming months.
AI and Robotics
NVIDIA research shows robots trained in simulation can handle real-world tasks
Recent advancements in robotics have led to significant improvements in the reliability of robots trained entirely in simulation. Researchers have found that these simulated robots are now capable of performing tasks with greater accuracy and efficiency in real-world environments. This development comes as a response to the growing demand for automation across various industries, where the ability to seamlessly transition from virtual training to practical application is crucial. The breakthrough was reported in October 2023, highlighting the successful application of simulation-based training methods that allow robots to learn complex tasks without the risks and limitations associated with physical training. By utilizing advanced algorithms and machine learning techniques, these robots can adapt to unpredictable conditions and execute tasks that were once considered too challenging for automated systems. As industries increasingly seek to integrate robotic solutions to enhance productivity and reduce labor costs, the ability of these robots to operate reliably in the real world marks a significant milestone in the field of robotics. The ongoing research aims to refine these training methods further, ensuring that robots can meet the diverse needs of various sectors, from manufacturing to healthcare.
Will Robotics Have a ChatGPT Moment?
In the coming decades, billions of AI-powered robots are expected to collaborate with humans across various sectors, including factories, warehouses, elder care, disaster response, and home assistance. By 2025, investments in robotics reached a record $40.7 billion, highlighting the growing interest in this technology. Despite ambitious claims from robotics companies about humanoid robots entering homes soon, significant challenges remain in bridging the gap between current capabilities and the promises made. Experts in AI and robotics, including a professor from Oregon State University and a former Google X executive, emphasize that while AI is revolutionizing robotics, the complexity of real-world environments poses substantial hurdles. Current demonstrations of humanoid robots, such as those showcased at the 2026 Spring Festival Gala in China, often rely on scripted performances rather than genuine autonomy, revealing the limitations of existing technology. The development of general-purpose robots is hindered by the need for vast amounts of high-quality training data and the challenge of creating hardware that can safely interact with humans. As robotics evolves, the focus will shift to practical applications that address real-world needs, with an emphasis on safety and reliability. The path forward involves a series of incremental advancements rather than a single breakthrough, as AI-driven robots gradually begin to deliver tangible benefits across various industries, potentially transforming the economy and improving daily life.
Robotics Everyday-robots Agility-robotics Artificial-intelligence
Chef Robotics Advances Bi-Manual Physical AI System for Prep Table Food Assembly Powered by a Food Foundation Model
Chef Robotics has announced the development of a bi-manual physical AI system aimed at enhancing food assembly tasks on prep tables, such as burger and burrito preparation. This innovative system, which is set to launch on May 19, 2026, will cater to various sectors including ghost kitchens, fast-casual restaurants, and catering services, focusing on lower-volume yet more complex meal assembly compared to traditional food manufacturing processes. The new AI system utilizes two robotic arms for coordinated and dexterous manipulation, mimicking human-like capabilities to handle a variety of food items and utensils. It is powered by Chef's Food Foundation Model (FFM), which employs imitation learning to adapt quickly to diverse tasks and environments, overcoming the limitations of existing robotic systems that struggle with the variability of food materials. Chef Robotics aims to automate manual prep table assembly, a critical area in the food industry that has remained largely reliant on human labor. By leveraging the FFM, the system is designed to learn from demonstrations, allowing it to generalize across different tasks and robotic platforms. This advancement is expected to improve operational efficiency, yield, and consistency in food preparation, ultimately transforming how food assembly is approached in various culinary settings.
Graphene “Tattoos” for Plants Could Form Neural Networks
Researchers at the University of Texas at Austin have developed an innovative graphene "tattoo" that adheres directly to plant leaves, enabling real-time monitoring of leaf hydration. This breakthrough, published in the journal Nano Letters in February, addresses the limitations of traditional methods that require cutting leaves for moisture assessment. The sensor, which functions like a three-terminal transistor, sends electric pulses into the leaf, allowing it to measure moisture levels without disrupting photosynthesis. Led by associate professor Jean Anne Incorvia and graduate student Utkarsh Misra, the team envisions a future where these sensors could form a neural network across forests, providing critical data on drought and fire risks. The flexible and nearly transparent graphene material allows the tattoo to adapt to the leaf's movements, while its unique properties enable it to act as an artificial synapse, potentially enhancing plant-based computing. The concept emerged from a collaboration with geologist Ashley Matheny, highlighting the practical applications of the technology in agriculture and environmental monitoring. The researchers successfully trained a neural network to classify leaf hydration states, paving the way for more sophisticated plant monitoring systems that could help farmers and forest rangers respond to climate change challenges.
Graphene Agriculture Wildfires Neural-networks
Shengshu Technology Launches Motubrain World-Action Model
Shengshu Technology has achieved a significant milestone with its Motubrain model, which has secured the top position on both the WorldArena and RoboTwin 2.0 benchmarks. This accomplishment highlights the model's innovative unified world-action approach, allowing humanoid robots to effectively execute long-horizon tasks across various embodiments. The recognition from these prestigious benchmarks underscores the advancements in robotics technology and the potential for enhanced performance in diverse applications.
News
Cobots vs. Alternatives: The Ultimate Comparison Chart
Modern manufacturing is at a pivotal crossroads as companies seek to balance the demands of high-speed production with the need for flexibility. Traditionally, manufacturers faced a choice between manual labor for intricate tasks and industrial robots for high-volume output. However, the introduction of collaborative robots, or cobots, has provided a versatile solution that combines safety and adaptability, addressing the limitations of both previous options. While traditional industrial robots excel in speed and power, they require substantial investments in safety measures, such as fencing and barriers. On the other hand, manual labor, though flexible, is becoming increasingly unsustainable due to rising costs and labor shortages. Cobots are designed to work alongside humans, equipped with advanced technology that allows them to detect resistance and halt operation, thus eliminating the need for extensive safety infrastructure. This capability enables manufacturers to seamlessly integrate automation into existing production lines without the need for facility expansion. JAKA, a leader in this field, has developed cobots that combine industrial-grade precision with user-friendly features. Their JAKA Zu series can handle payloads of up to 20 kg, while the JAKA Pro series is built to withstand challenging environments, including exposure to metal shavings and liquids. With intuitive programming and wireless teaching, JAKA's cobots empower existing staff to operate them with minimal training, fostering a collaborative environment where technology and human skills enhance production efficiency.
Gradient-based planning for world models at longer horizons
A team of researchers, including Mike Rabbat, Aditi Krishnapriyan, Yann LeCun, and Amir Bar, has introduced GRASP, a new gradient-based planning method designed for learned dynamics in world models. This innovative approach addresses the challenges of long-horizon planning, which has proven to be fragile and inefficient with existing models. GRASP enhances planning by lifting trajectories into virtual states, allowing for parallel optimization across time, and incorporating stochastic elements to facilitate exploration. The development of GRASP comes in response to the limitations of current world models, which, despite their ability to predict complex sequences in high-dimensional spaces, struggle with optimization and can easily fall into local minima. The researchers emphasize that while powerful predictive models exist, effective control and planning remain significant hurdles. By utilizing a collocation-based approach, GRASP optimizes both actions and states, improving computational efficiency and robustness against adversarial vulnerabilities inherent in state gradients. The method also introduces exploration through Gaussian noise in state updates, enhancing the ability to navigate complex planning landscapes. Preliminary results indicate that GRASP significantly outperforms traditional methods in success rates and time efficiency for long-horizon planning tasks. The researchers view GRASP as a foundational step towards more advanced world model planners, with future work aimed at integrating the method into reinforcement learning systems and exploring diffusion-based world models. The full details of the study can be found in their published paper.
Slime-like artificial muscle reshapes on command, heals after damage and turns one robot into many
Researchers have unveiled a groundbreaking artificial muscle that transcends the limitations of traditional robots, which typically execute only predetermined tasks after being manufactured. This innovative technology, detailed in a recent study published in Science Advances, boasts the ability to alter its shape in real time, recover from damage, and be reused, marking a significant advancement in robotics. The development aims to enhance the functionality and adaptability of robotic systems, potentially leading to more versatile applications across various fields. By integrating these dynamic capabilities, the researchers hope to pave the way for smarter, more resilient robots that can better respond to changing environments and tasks.
Robotics
Why AI Systems Fail Quietly
Engineers developing distributed AI platforms are facing a new challenge known as "quiet failure," where systems appear operational but produce incorrect outcomes over time. This issue arises as autonomy in software systems increases, complicating traditional methods of monitoring and observability. In late-stage testing, engineers find that while monitoring dashboards indicate a healthy status, users report that the system's decisions are increasingly flawed. For instance, an AI assistant designed to summarize regulatory updates may continue to function technically but rely on outdated information due to a failure to update its document retrieval process. This disconnect highlights the limitations of conventional observability metrics, which focus on uptime and error rates rather than the ongoing alignment of system behavior with intended outcomes. As autonomous systems operate continuously and make decisions based on evolving contexts, engineers must shift their focus from merely ensuring component functionality to actively supervising overall system behavior. This requires the implementation of supervisory control architectures that can monitor and intervene in real-time, preventing behavior drift before it leads to significant issues. The growing prevalence of quiet failures calls for a rethinking of reliability in engineering, emphasizing the need for continuous behavioral monitoring and control. As AI systems become more autonomous, this new approach will likely extend across various domains, transforming how engineers ensure that systems not only function correctly but also remain aligned with their intended purposes over time.
Software-failure Software-reliability Software-engineering Cloud-computing Autonomous-systems
Why Are Industrial Cobots Crucial for SMEs and High-Mix Manufacturers?
In the evolving landscape of manufacturing, JAKA is addressing the needs of small and medium-sized enterprises (SMEs) and high-mix manufacturers by promoting the adoption of industrial collaborative robots. These robots, such as the JAKA Pro16, are designed to enhance flexibility and efficiency in production lines, allowing companies to quickly adapt to frequent product changes and varied schedules. By integrating collaborative robots, manufacturers can maintain consistent output quality while reducing downtime and the need for extensive retraining of staff. The JAKA Pro16 specifically targets the challenges of manual palletizing, a task often associated with operator fatigue and decreased productivity. Its compact and lightweight design enables it to work alongside human employees, improving overall efficiency and creating a safer work environment. This technology not only minimizes errors and material waste but also ensures that production targets are consistently met, even during fluctuating order volumes. For SMEs, cost and space limitations are significant concerns. JAKA's solutions focus on maximizing resource efficiency, with the Pro16 capable of replacing multiple manual operations across various production lines, thus lowering labor costs. Its compact footprint allows for deployment in facilities with limited space, making advanced automation accessible to smaller manufacturers. By leveraging industrial collaborative robots, JAKA is helping clients achieve scalable automation without substantial upfront investments. This strategic approach not only enhances production capabilities but also supports a more resilient and sustainable manufacturing future, positioning collaborative robotics as a vital component in modern manufacturing operations.
Flexible Robot Path Planning: How to Adapt to Changing Workpiece Geometry
JAKA, a leader in robotics technology, is addressing the challenges of automated finishing processes, particularly in polishing applications where workpiece dimensions can vary. Traditional robots, which rely on fixed programming, often struggle to maintain quality when faced with different part geometries. To overcome this limitation, JAKA has developed a flexible robotic system that intelligently adapts its polishing path in real time, ensuring consistent quality across diverse production batches. This innovative approach integrates advanced sensory technology, such as vision systems and laser scanners, which capture the actual geometry of each workpiece. The robot's control system then compares this data to the ideal CAD model, allowing for dynamic adjustments in its trajectory. JAKA's proprietary force control technology further enhances this adaptability by maintaining optimal contact pressure, compensating for minor deviations in part shape. To simplify the user experience, JAKA's systems feature intuitive graphical off-line programming software that enables operators to easily import new CAD models and generate tool paths with minimal reprogramming. The compact and lightweight design of JAKA's robotic arms facilitates quick repositioning for different production lines, while standardized communication protocols allow for swift integration of various sensors, reducing downtime. By combining mechanical dexterity, integrated perception, and intelligent control algorithms, JAKA is transforming polishing robots from rigid tools into adaptive partners. This advancement ensures high-quality finishing standards, even as product designs evolve, ultimately benefiting manufacturers in high-mix production environments.
Import AI 440: Red queen AI; AI regulating AI; o-ring automation
A recent survey conducted among users of language models reveals a growing interest in the capabilities of large language models (LLMs). The survey, which took place in October 2023, sought to understand user engagement and perceptions regarding LLMs. Participants expressed curiosity about the extent of the models' training and their applications across various fields. The survey highlighted that many users are eager to explore the potential of LLMs in enhancing productivity, creativity, and problem-solving. As organizations increasingly integrate these technologies into their operations, understanding user experiences and expectations becomes crucial. The findings indicate that while many users are aware of the models' capabilities, there remains a significant gap in knowledge regarding their limitations and ethical considerations. This underscores the importance of ongoing education and transparency in the development and deployment of LLMs. As the technology continues to evolve, stakeholders are encouraged to engage in discussions about responsible usage and the future of artificial intelligence in society.
Physical Intelligence Secures $600 Million to Build a Universal Robot Brain, Hitting $5.6 Billion Valuation
A San Francisco startup, supported by CapitalG and Jeff Bezos, is focusing on reinforcement learning to advance general-purpose robotics. This approach distinguishes the company from hardware-centric competitors in the industry. By leveraging advanced algorithms and machine learning techniques, the startup aims to enhance the adaptability and efficiency of robotic systems. The initiative reflects a growing trend in the tech sector, where software-driven solutions are increasingly seen as vital for overcoming the limitations of traditional hardware-based robotics. As the company develops its technology, it seeks to address the diverse challenges faced by various industries, potentially revolutionizing how robots are utilized across different applications.
NVIDIA Details Open-Source GR00T N1 Foundation Model and Hover Controller for Humanoids
At the Marktechpost miniCON Open Source AI 2025, NVIDIA Research Scientist Yuke Zhu unveiled Project GR00T, which focuses on a simulation-first strategy for developing generalist foundation models tailored for humanoid robots. The initiative includes the launch of the open-source GR00T N1 multimodal model and the Hover whole-body controller. These innovations aim to enhance cross-embodiment capabilities and expedite development processes for NVIDIA's robotics partners. This presentation highlights NVIDIA's commitment to advancing robotics technology through collaborative and open-source efforts.
NVIDIA open-source hover GR00TRobotics needs a service framework.
RSF defines a common language for robot service capability, lifecycle operations, certification pathways, and service-provider networks.
