Industry Briefing
A single destination for timely, editor-curated robotics news from around the world.
NVIDIA, Ineffable Intelligence Team Up to Build the Future of Reinforcement Learning Infrastructure
NVIDIA has announced a new engineering collaboration with Ineffable Intelligence, a London-based AI lab, aimed at enhancing the capabilities of reinforcement-learning agents. These AI systems, which learn through trial and error, are designed to transform computational processes into valuable knowledge. The partnership seeks to leverage the strengths of both organizations to advance the development of these intelligent systems, potentially leading to significant breakthroughs in AI applications. The collaboration underscores a growing interest in harnessing advanced AI techniques to drive innovation and efficiency across various sectors.
Launch of Robo-ValueRL: The First Open-Source VLA Reinforcement Learning Framework for Robotics
The Beijing Humanoid Robot Innovation Center and Renmin University of China's Gaoling Artificial Intelligence Institute have launched the Robo-ValueRL open-source framework. This initiative aims to enhance humanoid robots' decision-making capabilities in precision tasks, such as semiconductor assembly, by addressing challenges in data quality, control precision, and adaptability in dynamic environments. Robo-ValueRL introduces a value estimation mechanism based on historical observations, enabling robots to autonomously assess their actions. This closed-loop learning process—observation, value estimation, correction, and iteration—allows for improved accuracy and reduced instability in operations. The framework is fully open-source, providing access to core algorithms, evaluation tools, and standardized protocols for universities, research institutions, and manufacturers. The open-source nature of Robo-ValueRL significantly lowers the barriers for small and medium-sized manufacturers to implement reinforcement learning in specialized fields like semiconductor production and medical device manufacturing. This development marks a shift in humanoid robotics from laboratory experiments to practical industrial applications, paving the way for robots to evolve their decision-making capabilities independently.
Humanoid Robots Reinforcement Learning Precision Manufacturing Open Source Technology
UK startup Humanoid launches reinforcement learning system to improve robot manipulation
UK-based robotics and AI company Humanoid has introduced KinetIQ Ascend, the company’s reinforcement learning approach designed to reach 99.9 percent manipulation reliability at human speed and beyond. KinetIQ Ascend builds on the previously announced KinetIQ platform with trial-and-error learning, helping the company’s robots improve directly on industrial tasks. The new system was tested on several […]
Computing Humanoids News artificial intelligence automation embodied ai
MIT’s SoftMimic Framework Teaches Humanoids to Be Compliant, Not Just Capable
Researchers at MIT's Improbable AI Lab have unveiled SoftMimic, an innovative reinforcement learning framework designed to enhance the safety and compliance of humanoid robots during interactions. Unlike traditional methods that focus on rigid motion tracking, SoftMimic enables robots to adaptively absorb collisions, promoting safer engagement with their environment. This development, announced in October 2023, aims to address the growing need for more flexible and responsive robotic systems in various applications, from manufacturing to personal assistance. By leveraging advanced algorithms, the framework allows humanoids to learn from their experiences, improving their ability to navigate complex scenarios while minimizing the risk of injury to themselves and humans alike.
reinforcement-learning MIT SoftMimic
1X Reveals the RL Core That Gives Its NEO Humanoid Fluid, Whole-Body Mobility
Robotics firm 1X has revealed the advanced reinforcement learning system that drives the movement of its NEO humanoid, following the introduction of its Redwood AI brain. This innovative unified controller allows the robot to perform a variety of human-like actions, including walking, running, and climbing stairs, utilizing only stereo vision for navigation. The announcement highlights 1X's commitment to enhancing robotic mobility and intelligence, showcasing the potential for humanoid robots to interact more naturally within human environments.
reinforcement-learning 1X-technologies Redwood humanoid-robots locomotion robotics-ai
Amazon's ResMimic Teaches Humanoids to Handle Objects by Adding Precision to General Motion
Amazon has unveiled its latest robotics initiative, ResMimic, which aims to enhance the capabilities of humanoid robots in performing complex loco-manipulation tasks. This innovative project employs a two-stage residual learning framework that allows for the efficient teaching of these skills. By refining a general motion policy with specific corrections tailored to individual tasks, the system empowers a Unitree G1 robot to adeptly manage heavy and irregular objects with remarkable precision. This development is part of Amazon's ongoing efforts to advance robotics technology and improve automation processes in various applications.
reinforcement-learning Unitree Robotics AI Amazon robotics
Humanoid says KinetIQ Ascend reinforcement learning approaches human-level dexterity
Humanoid has announced that its KinetIQ Ascend technology achieves an impressive 99.9% manipulation reliability, capable of performing industrial tasks at human speed and even surpassing it. This breakthrough is attributed to advanced reinforcement learning techniques that enable robots to exhibit human-level dexterity. The development marks a significant advancement in robotics, potentially transforming efficiency in various industrial applications.
Artificial Intelligence Artificial Intelligence / Cognition Humanoids News dexterous manipulation humanoid
"Father of Reinforcement Learning Sutton Partners with Tianshan Technology for First Deep Sharing in China! Limited Rare Spots Open for a Short Time, Don't Miss Out!"
In a significant development for the field of artificial intelligence, Richard Sutton, a pioneer in reinforcement learning, has teamed up with Tianshan Technology to host a groundbreaking event in China. This collaboration marks the first deep sharing initiative in the country, aimed at advancing knowledge and application of reinforcement learning techniques. The event is set to take place soon, with limited spots available for participants eager to gain insights from one of the leading experts in the field. Attendees will have the unique opportunity to engage directly with Sutton and learn about the latest advancements and practical applications of reinforcement learning. This initiative reflects a growing interest in AI technologies in China and underscores the importance of collaboration between leading researchers and local tech companies to foster innovation and expertise. Interested individuals are encouraged to secure their spots promptly, as availability is limited.
Robotics Automation AI
Toyota's CUE Robot Advances: Learning to Walk and Dribble with Reinforcement Learning and Sim2Real
Toyota's CUE humanoid robot is advancing its capabilities through a novel approach that integrates reinforcement learning with Sim2Real techniques. This development focuses on improving the robot's walking and dribbling abilities, effectively narrowing the divide between simulated environments and real-world functionality. By employing this innovative method, Toyota aims to enhance the practical applications of robotics, showcasing the potential for more sophisticated interactions in various settings.
Humanoid Robots Reinforcement Learning Sim2Real AI Robotics
Can Robots Trained Through Behavior Cloning Evolve Themselves in Two Hours Using Reinforcement Learning?
Researchers have identified significant limitations in behavior cloning (BC) methods used in robotics, prompting the development of a new approach known as Q2RL. This innovative technique integrates BC with reinforcement learning (RL) to enhance the performance of robots. By leveraging hidden knowledge embedded in BC strategies, Q2RL seeks to improve the efficiency of learning processes while simultaneously lowering the costs tied to data collection and the need for retraining. This advancement represents a crucial step forward in optimizing robotic capabilities, addressing the challenges faced by traditional BC methods.
Reinforcement Learning Behavior Cloning Robotics AI Machine Learning
Sanctuary AI Touts Reinforcement Learning Success for Dexterous Robot Hand Manipulation
Sanctuary AI has showcased its advanced robotic hand, featuring hydraulically actuated five fingers, successfully executing in-hand object reorientation. This demonstration took place recently, highlighting the company's innovative approach to robotics. The robotic hand utilized a reinforcement learning policy that was initially trained in a simulated environment, achieving a notable sim-to-real transfer even when subjected to an unexpected load of 500 grams. Sanctuary AI credits this accomplishment to its proprietary reinforcement learning techniques and the sophisticated design of its high-degree-of-freedom hand hardware, marking a significant milestone in the development of robotic manipulation capabilities.
phoenix sanctuary-ai
Natural Humanoid Walk Using Reinforcement Learning
Researchers have developed an innovative neural network designed for humanoid locomotion, utilizing reinforcement learning to enable robots to walk in a manner akin to humans. This breakthrough was achieved through advanced high-fidelity simulations, which not only improve the robots' walking capabilities but also facilitate a seamless transition from simulated environments to real-world applications. The technology promises to significantly enhance the efficiency and scalability of humanoid robotics, making it a pivotal advancement in the field. The development is expected to impact various sectors, including robotics and automation, by providing more adaptable and capable humanoid robots.
Reinforcement Learning Humanoid Robotics Simulation Technology AI Development Robotics Engineering
Deep Reinforcement Learning Based Autonomous Decision‐Making for Cooperative Uncrewed Aerial Vehicles: A Search and Rescue Real World Application
A recent study published in the Journal of Field Robotics highlights advancements in autonomous robotic systems designed for agricultural applications. Researchers from various institutions collaborated to develop innovative algorithms that enhance the efficiency and precision of robotic farming equipment. The findings, released in early October 2023, emphasize the growing importance of automation in agriculture, particularly in response to labor shortages and the need for sustainable farming practices. The research was conducted in multiple agricultural settings, showcasing how these robotic systems can adapt to different crop types and environmental conditions. By integrating machine learning and sensor technology, the robots are capable of performing tasks such as planting, weeding, and harvesting with minimal human intervention. This development aims to address the challenges faced by farmers, including the rising costs of labor and the increasing demand for food production. The study underscores the potential for these autonomous systems to revolutionize the agricultural sector, making it more efficient and environmentally friendly. As the agricultural industry continues to evolve, the implementation of such technologies could lead to significant improvements in productivity and sustainability.
RESEARCH ARTICLE
A Critical Review of Reinforcement Learning Algorithms for Mobile Robot Path Planning
The Journal of Field Robotics has published an early view article highlighting recent advancements in robotic technology. Researchers from various institutions have collaborated to explore innovative applications of robotics in diverse fields, including agriculture, healthcare, and disaster response. The findings, released in October 2023, underscore the growing importance of robotics in enhancing efficiency and safety across these sectors. The study emphasizes the integration of artificial intelligence and machine learning to improve the functionality and adaptability of robotic systems. By leveraging these technologies, the researchers aim to address complex challenges faced in real-world scenarios, such as precision farming and emergency management. This publication is part of an ongoing effort to disseminate cutting-edge research that can inform future developments in robotics. The collaborative nature of the research showcases a commitment to interdisciplinary approaches, fostering innovation that can lead to significant societal benefits. As the field continues to evolve, the implications of these advancements are expected to resonate across various industries, driving further investment and interest in robotic solutions.
SURVEY ARTICLE
A Feature‐Decoupled and Gated‐Interaction‐Enhanced Deep Reinforcement Learning for Path‐Following of Large‐Inertia Vessels
A recent study published in the Journal of Field Robotics explores advancements in autonomous robotic systems designed for agricultural applications. Researchers from various institutions conducted the study to address the growing need for efficient farming solutions amid increasing global food demand. The findings, released in early October 2023, highlight innovative technologies that enable robots to perform tasks such as planting, monitoring crop health, and harvesting with minimal human intervention. The research was carried out in diverse agricultural settings, demonstrating the robots' adaptability to different environments and crop types. By integrating artificial intelligence and machine learning, these autonomous systems can analyze data in real-time, making informed decisions that enhance productivity and reduce resource waste. The motivation behind this study stems from the challenges faced by the agricultural sector, including labor shortages and the need for sustainable practices. The researchers aim to provide farmers with tools that not only improve efficiency but also contribute to environmental sustainability. Through rigorous testing and validation, the study showcases the potential of these robotic systems to revolutionize farming practices, ultimately leading to increased yields and reduced operational costs. As the agricultural industry continues to evolve, the implementation of such technologies could play a crucial role in meeting future food security challenges.
RESEARCH ARTICLE
Humanoid Announces its KinetIQ Ascend Reinforcement Learning Approach
A groundbreaking robotic system has demonstrated its effectiveness in various manipulation tasks, including retrieving parts from bins, delivering objects to humans, and lifting and moving containers with its dual arms. This innovative technology was rigorously tested and has shown promising results across multiple scenarios, showcasing its potential for practical applications in industries requiring automation. The trials were conducted recently, highlighting the system's versatility and efficiency in handling complex tasks that typically require human intervention. As industries increasingly seek to enhance productivity through automation, this new robotic solution could play a significant role in transforming operational workflows.
Prox Industries accelerates physical AI research with dual-arm UR3e collaborative robots using VLA and reinforcement learning.
Prox Industries has announced its collaboration with Universal Robots (UR) to enhance the development of physical AI through the utilization of UR's "Physical AI Development Support Program." The initiative will focus on accelerating research and development of physical AI by employing a dual-arm robotic configuration using two UR3e collaborative robots. This partnership aims to leverage advanced robotics technology to innovate in the field of AI, reflecting Prox Industries' commitment to advancing automation solutions.
Redefining Optimal Coverage Path Planning for FLS‐Equipped AUVs With Deep Reinforcement Learning
The Journal of Field Robotics has recently published an EarlyView article highlighting advancements in robotic technology. Researchers from various institutions have collaborated to explore innovative applications of robotics in field environments. This study, released in October 2023, focuses on enhancing the efficiency and effectiveness of robotic systems in agricultural and environmental monitoring tasks. The motivation behind this research stems from the increasing demand for precision agriculture and sustainable practices, which necessitate the integration of advanced robotics. By employing cutting-edge algorithms and sensor technologies, the team aims to improve data collection and analysis in challenging outdoor conditions. The findings suggest that these advancements could significantly reduce labor costs and increase productivity for farmers, while also providing critical insights for environmental conservation efforts. This collaborative effort underscores the potential of robotics to transform traditional practices and address pressing global challenges.
RESEARCH ARTICLE
AI Is Designing Radio Chips That Humans Couldn’t Even Imagine
Researchers at Princeton University have made significant strides in the design of radio-frequency integrated circuits (RFICs), a critical component for advancing wireless technologies such as 5G, autonomous vehicles, and satellite communications. Utilizing reinforcement learning and inverse design techniques, the team has developed a method to create RFICs from scratch, drastically reducing design time and achieving record performance levels. This innovative approach leverages AI to navigate the complex design space of RFICs, traditionally seen as an art requiring years of expertise. By employing machine learning algorithms, the researchers can generate novel circuit layouts that outperform existing designs while minimizing the time taken for development. The project, which began after the success of AI in games like Go, aims to overcome the limitations of conventional RFIC design, which has remained largely artisanal. The researchers emphasize the need for large, shared datasets and open ecosystems to further enhance AI's capabilities in understanding electromagnetic and circuit behaviors. As the demand for advanced RFICs grows, the potential for AI-driven design to revolutionize the field is becoming increasingly apparent. The findings have attracted attention within the RF community, sparking discussions about the future of AI in circuit design and the importance of collaboration between AI researchers and chip designers to unlock new possibilities in technology.
Machine-learning Ic-design Chip-design Rf Rfic
SoftServe Introduces Virtual Gyms for Enhanced Robotics Training and Deployment
SoftServe has highlighted the importance of 'virtual gyms' for robotics teams, emphasizing their role in preparing robots for dynamic environments. These high-fidelity simulation environments allow robots to train, fail, and recover safely before real-world deployment, addressing the challenges posed by unpredictable operational conditions. The global robotics market is projected to grow at a 19.6% CAGR from 2026 to 2036, underscoring the need for effective training solutions like virtual gyms to enhance robotic autonomy and performance. The shift from programmed automation to physical AI necessitates that robots adapt to constantly changing environments, which traditional training methods struggle to accommodate. Virtual gyms integrate technologies such as digital twins, reinforcement learning, and sensor modeling to provide a comprehensive training platform. This approach mitigates the risks and costs associated with real-world trials, enabling teams to generate valuable training data in a controlled setting, thus improving deployment success rates. Looking ahead, the adoption of virtual gyms is expected to become a standard practice in robotics development, as they offer a solution to the simulation-to-reality gap. No further timeline was disclosed at the time of publication, but the increasing complexity of robotic tasks suggests that the demand for such training environments will continue to rise as the industry evolves.
Artificial Intelligence Artificial Intelligence / Cognition Autonomous Mobile Robots (AMRs) Development Tools / SDKs / Libraries Industrial Robots Logistics
An AI-powered control system for robots with legs
Walking robots, such as quadruped robotic dogs, must be able to move safely through rough, often changing environments. Today, there are two main ways to program these walking, or legged, robots. The first is called model predictive control. This technique optimizes the robot's behavior but relies on accurate dynamics models, which are challenging to achieve in real-world settings and often require simplifying assumptions. The second is model-free reinforcement learning, which allows the robot to learn reliable but fixed behaviors, making them difficult to adapt after training.
Robotics
Tsinghua alumni launch AI startup, securing hundreds of millions in angel funding for the automotive industry.
Embodied intelligence company Guangxiang Technology has successfully secured hundreds of millions in angel funding, with significant participation from leading investors including Zhuhai Technology Industry Group, Xingsheng Capital, and several others. Founded in April 2025 through a collaboration between Tsinghua University's Vehicle and Transportation Institute and its AI Institute, Guangxiang aims to advance the development of its physical native base model and commercialize embodied intelligent robots for industrial applications. The company's founder and CEO, Zhang Tao, previously led the spatial perception engine at Amap, while co-founder Professor Li Shengbo is a renowned expert in reinforcement learning and autonomous driving. The team, which includes members from major tech firms like Alibaba and Huawei, is focused on a unique technological approach that diverges from mainstream visual-language-action models. Guangxiang's flagship product, the Phi-Bot X1, was launched in June 2026 and is designed for industrial environments. The robot has demonstrated impressive capabilities, completing a full welding operation on an automotive production line without errors during a 21.5-hour continuous run at the 2026 ATC exhibition. The company plans to expand its applications in the automotive sector, targeting the remaining 30% of automation gaps that traditional methods cannot address. Zhang envisions a robust market for automotive production line robots, estimating a potential market size of around 100 billion yuan in China. Guangxiang Technology is committed to refining its products and scaling operations, with a focus on real-world applications and continuous feedback to enhance its offerings.
Smart mobility company becomes top electric motorcycle brand in Indonesia after raising millions from CATL fund.
OMOWAY, a smart two-wheeler mobility company, has successfully completed both Series A and A+ funding rounds, each raising tens of millions of dollars. The A+ round was led by Lochpine Capital, a fund backed by CATL, while Monolith led the A round with participation from CICC Capital and existing investor ZhenFund. Founded less than two years ago, OMOWAY has attracted a strong roster of investors, including Sequoia, ZhenFund, and various funds from the new energy sector. With significant financial backing and industry resources, OMOWAY is accelerating the commercialization of its products globally. In June, the company launched its flagship product, the OMO-X, with its first delivery in Indonesia, where it quickly became the top-selling electric motorcycle in the country during its first month. OMOWAY aims to disrupt the traditional motorcycle market, which has long been dominated by Japanese fuel brands, by addressing common industry challenges such as the high premium on advanced smart products and the lack of technological appeal in affordable options. The OMO-X features advanced technology, including a digital key, automatic side stand, remote control capabilities, and a large 10.25-inch interactive display, significantly enhancing user experience. The OMO-X Smart model focuses on intelligent mobility, while the OMO-X Balance is the world's first mass-produced self-balancing motorcycle, utilizing gyroscopic technology to improve stability. OMOWAY is also developing a reinforcement learning model for real-world driving conditions and has implemented a 360° panoramic vision system for enhanced safety. With a proprietary technology framework that integrates AI and robotics, OMOWAY is expanding its dealer network in Indonesia and plans to enter markets in Thailand, Singapore, and Europe, aiming to evolve transportation into intelligent partnerships for various applications.
Turing Award Winner Richard Sutton Visits Beijing Humanoid Robot Innovation Center
Richard Sutton, a prominent figure in artificial intelligence and recognized as the 'Father of Reinforcement Learning', visited the Beijing Humanoid Robot Innovation Center to explore the latest developments in embodied intelligence technologies. During his visit, which highlighted the center's innovative work, Sutton participated in discussions and observed demonstrations of sophisticated humanoid robots designed for logistics and domestic tasks. He underscored the significance of merging reinforcement learning with embodied intelligence, suggesting that this integration is crucial for the future evolution of AI.
Reinforcement Learning Humanoid Robots Embodied Intelligence AI Research
Breaking Through Data Bottlenecks: Si 0.5 Enables Millisecond Mapping from Human to Dexterous Hands
Zhongke Silicon Memory has unveiled MoReL, an innovative modular reinforcement learning framework designed to enhance embodied intelligence by facilitating real-time mapping of human hand movements to a variety of dexterous robotic hands. This significant advancement, announced recently, aims to tackle the prevalent issues of data scarcity and compatibility that have hindered the effective control of robotic systems. By enabling precise and efficient manipulation across different robotic platforms, MoReL eliminates the necessity for extensive reconfiguration, thereby streamlining the integration of human-like dexterity in robotics. This development marks a pivotal step forward in the field, promising to enhance the functionality and adaptability of robotic hands in various applications.
Robotic Manipulation Reinforcement Learning Dexterous Robotics Human-Robot Interaction
Unbounded Dynamics Launches MWA™ Model, Tops Global Embodied Intelligence Rankings
Unbounded Dynamics has introduced the MWA™ model, marking a significant advancement in embodied intelligence as it becomes the first long-sequence bidirectional physical causal chain. This innovative model has secured the top ranking in the RoboCasa GR1 TableTop competition, outperforming industry giants such as NVIDIA and Xiaopeng. By incorporating a distinctive 'hidden space world model' alongside reinforcement learning, the MWA™ model equips robots with the ability to comprehend physical laws and implement accurate strategies in intricate real-world environments. This development highlights Unbounded Dynamics' commitment to pushing the boundaries of robotic intelligence and performance.
Embodied Intelligence Reinforcement Learning Robotics Artificial Intelligence
NIO enhances smart driving education; Ren Shaoqing states innovation will reshape competition.
On June 18, NIO announced the rollout of its latest world model software across multiple vehicle platforms, including eight NT2.0 models, four NT2.5 models, and six NT3.0 models. This update allows NIO to run the same complex autonomous driving code on different generations of chips, addressing a common industry challenge where software updates were often limited to the latest hardware, leaving older vehicle owners at a disadvantage. The initiative stems from a long-term effort by NIO's team, led by Ren Shaoqing, who began exploring solutions in 2020. NIO developed an AI infrastructure that bridges gaps between different chip architectures, enhancing vehicle processing speeds with an AI compiler and automating deployment processes with AI agents. This innovation has significantly reduced deployment times from days to just a couple of hours. NIO's approach includes running the latest models in a "shadow mode" on production vehicles to gather valuable data without interfering with user driving. This data is used to train smarter models, creating a feedback loop that enhances the software's performance. The company has reported a substantial increase in its autonomous driving capabilities, attributing this to a shift in understanding the development cycle of physical AI. As the industry evolves, NIO has restructured its autonomous driving team to focus on foundational research and innovation, positioning itself to leverage advancements in large model technology and closed-loop reinforcement learning. The company aims to enhance its competitive edge by continuously improving its algorithms and data systems, ultimately striving for a more robust autonomous driving experience.
Xiaohongshu's Evolving-RL: A New Paradigm for Self-Evolving AI Agent Skills
Researchers at Xiaohongshu (RED), a prominent Chinese lifestyle and social commerce platform, have introduced Evolving-RL, an innovative reinforcement learning framework. This groundbreaking development allows artificial intelligence agents to autonomously enhance their skills through experiential learning, eliminating the need for separate modules dedicated to skill extraction. The announcement was made recently, highlighting the platform's commitment to advancing AI technology. The Evolving-RL framework represents a significant step forward in the field of machine learning, as it enables AI systems to adapt and improve based on their interactions and experiences. This advancement is expected to have wide-ranging implications for various applications in social commerce and beyond, as it streamlines the learning process for AI agents, making them more efficient and capable of handling complex tasks.
AI
SAP SE (SAP), Cyberwave Deploy Autonomous AI Robots in Logistics Warehouse
SAP SE and Cyberwave have successfully deployed fully autonomous, AI-powered robots in SAP's logistics warehouse located in St. Leon-Rot, Germany, as of May 11, 2026. This initiative represents a significant advancement for SAP, transitioning its Physical AI technology from research to practical application. The robots, powered by SAP’s cloud-native Logistics Management solution and the SAP Business Technology Platform, are now capable of performing various tasks including box folding, packaging, and shipping fulfillment. The deployment addresses common challenges in logistics robotics, such as unpredictable environments and diverse object shapes that often hinder traditional systems. Cyberwave's innovative platform utilizes Vision-Language-Action and Reinforcement Learning models, enabling non-expert operators to teach robots new tasks through simple demonstrations. This approach significantly reduces training time from weeks to hours and allows robots to adapt to dynamic conditions in real-time. As a result of this integration, SAP has reported increased warehouse throughput and a decrease in physically demanding tasks for human workers. The project serves as a successful reference implementation, showcasing how a robust digital infrastructure combined with adaptive AI can enhance logistics operations. Both SAP and Cyberwave are now focused on further developing these Embodied AI capabilities to support future large-scale deployments.
A stair-climbing robot that catches itself when it falls
Researchers at the Singapore University of Technology and Design (SUTD) have created an innovative safety system utilizing reinforcement learning to enhance the capabilities of service robots navigating stairs. This development addresses a significant challenge in the deployment of autonomous robots in environments with staircases, where falls can pose serious risks. The system enables the robot to brace itself during a mid-fall, potentially preventing damage and ensuring safer operation. This breakthrough was announced in October 2023, marking a pivotal step forward in robotics technology aimed at improving the functionality and reliability of service robots in everyday settings.
Robotics
Torc Robotics Announces First-Ever Autonomous-Trucking Partnership at Mila to Advance Physical AI
Torc Robotics has announced a groundbreaking partnership with the Quebec Artificial Intelligence Institute, known as Mila, aimed at enhancing physical AI research. This collaboration, revealed on May 27, 2026, marks Torc as the first autonomous trucking company to join Mila's ecosystem in Montreal. The partnership will provide Torc access to top academic talent, including students and researchers, and includes dedicated research space on-site. By embedding itself within Mila's renowned environment, Torc intends to advance its capabilities in areas such as generative world models, multi-agent behavior modeling, and reinforcement learning. This initiative is part of Torc's mission to develop safe and scalable autonomous trucks, with a focus on bridging the gap between research and real-world applications. Mila, recognized globally for its contributions to machine learning, has a strong network of researchers and ties to leading Canadian universities, making it an ideal partner for Torc. The collaboration builds on a relationship that began in 2020 and reflects Torc's commitment to investing in AI talent and research partnerships. Both organizations aim to unlock safer and more efficient autonomous transportation solutions, contributing to the commercialization of autonomous trucking technology.
Video Friday: Atlas Versus a Fridge
IEEE Spectrum robotics has released its latest edition of "Video Friday," showcasing a variety of innovative robotics videos and announcing upcoming robotics events scheduled for 2026. Notable events include ICRA 2026 in Vienna from June 1-5, and the Summer School on Multi-Robot Systems in Prague from July 29 to August 4. Among the highlights, Boston Dynamics' Atlas robot demonstrates significant advancements in strength and adaptability, showcasing its ability to lift heavy objects and navigate complex environments using advanced reinforcement learning and control systems. This marks a pivotal moment for humanoid robots as they transition from laboratory settings to dynamic industrial applications. Additionally, the SpikerBot, a robot designed to be programmed by wiring neurons instead of traditional coding, has successfully reached its funding goal on Kickstarter. Other innovations include wheeled-legged robots that enhance mobility and a biomimetic robotic hummingbird developed at the Advanced Vertical Flight Laboratory, which mimics natural flight dynamics. The release also features advancements in construction technology, with Dusty Robotics introducing the FieldPrinter 2, a more efficient and intelligent version of its predecessor, and Noble Machines showcasing their autonomous robots designed for hazardous industrial tasks at NVIDIA GTC 2026. These developments reflect a broader trend in robotics, where technology is increasingly integrated into real-world applications, enhancing efficiency and safety across various industries.
Humanoid-robots Video-friday Robot-videos Educational-robots Biomimetics Quadruped-robots
Japanese Team Develops Snake Robot with New Rolling Motion, Achieving 10x Energy Efficiency
A research team at Osaka Metropolitan University has made significant advancements in robotics by training a snake-like robot to roll forward, which has notably improved its energy efficiency. By employing deep reinforcement learning techniques, the robot is able to maintain a nearly straight trajectory while achieving energy consumption reductions of up to tenfold compared to conventional crawling methods. This breakthrough not only showcases the potential for more efficient robotic movement but also opens avenues for further developments in energy-efficient robotic applications.
Snake Robots Energy Efficiency Deep Reinforcement Learning Robotics Motion Control
Dexbotic 2.0: Advancing Embodied Intelligence with PyTorch
Dexbotic 2.0 has been enhanced into a robust framework aimed at advancing embodied intelligence, specifically tackling significant challenges in the integration of Visual Language Agents (VLA) and Reinforcement Learning (RL). This upgraded framework is instrumental in training the DM0 model, which has recently achieved the top position in the RoboChallenge rankings, demonstrating its superior capabilities in executing complex real-world robotic tasks. The development reflects ongoing efforts to improve robotic intelligence and performance, marking a significant milestone in the field.
Embodied Intelligence Robotic Framework Deep Learning AI Models
Google's SkillOS Framework: Enabling AI Agents to Self-Evolve Without Parameter Overload
Google has introduced a groundbreaking framework called SkillOS, aimed at improving the learning capabilities of AI agents. This development addresses a significant challenge in the field of artificial intelligence by enabling agents to manage their skill libraries through reinforcement learning. By allowing these agents to retain and refine skills acquired from previous tasks, SkillOS enhances their ability to effectively tackle new challenges. The announcement comes as part of Google's ongoing efforts to advance AI technology and improve its practical applications. This innovative approach is expected to lead to more adaptable and efficient AI systems, ultimately benefiting various industries reliant on artificial intelligence solutions.
AI Reinforcement Learning Skill Management Machine Learning
Peking University Team Proposes LaST-R1 Framework, Enabling Robots to 'Think and Act' Simultaneously!
Researchers from Peking University and the Chinese University of Hong Kong have unveiled the LaST-R1 framework, a groundbreaking integration of latent reasoning into reinforcement learning. This development, announced recently, aims to enhance the decision-making capabilities of robots by enabling them to not only execute actions but also comprehend and adapt to various physical states. The framework is designed to improve robots' performance in real-world scenarios, addressing the limitations of traditional reinforcement learning methods. By incorporating latent reasoning, the LaST-R1 framework represents a significant advancement in the field of robotics, potentially leading to more intelligent and responsive machines.
Reinforcement Learning Robot Perception AI Frameworks Physical Reasoning
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.
AGIBOT Launches Genie Studio Agent to Enable Scalable Robot Deployment
AGIBOT has introduced Genie Studio Agent, a zero-code platform aimed at simplifying and scaling the deployment of robots. Launched recently, this innovative tool enables users without programming skills to design intricate workflows using a user-friendly visual interface. The platform addresses the complexities associated with deploying robots in real-world scenarios by offering a robust software infrastructure that encompasses simulation features, reinforcement learning for ongoing optimization, and proactive management tools. This initiative is part of AGIBOT's commitment to making robotic technology more accessible and efficient for a broader range of users.
robotics AI automation software development technology
The Synthetic Engine: How AGIBOT Genie Sim 3.0 Resolves the Embodied AI Data Bottleneck
AGIBOT has introduced a groundbreaking unified simulation infrastructure designed to enhance the transition from digital training to real-world application. This innovative system leverages large language model (LLM)-driven spatial world models alongside massively parallel reinforcement learning techniques. By integrating these advanced technologies, AGIBOT aims to significantly accelerate the development and deployment of robotic systems. The announcement, made recently, highlights the company's commitment to advancing artificial intelligence and robotics, providing a robust framework that could revolutionize how machines are trained and utilized in various industries. The infrastructure is expected to streamline processes, improve efficiency, and ultimately lead to more effective physical deployments of AI-driven solutions.
AI Week open-source China AGIBOT
AGIBOT Introduces Genie Sim 3.0, an Integrated Simulation, Data, and Benchmarking Platform for Embodied AI
AGIBOT has unveiled Genie Sim 3.0, an advanced platform aimed at improving embodied artificial intelligence in robotics. Launched recently, this open-source platform addresses significant challenges in robotics development by incorporating features such as environment generation, data scalability, and standardized evaluation methods. Genie Sim 3.0 enables the creation of 3D environments driven by large language models (LLMs) and includes a comprehensive framework for evaluating robot algorithms. The platform also integrates deeply with reinforcement learning, streamlining the experimentation and deployment processes for robotics. This upgrade is expected to facilitate faster advancements in the field, enhancing the capabilities and efficiency of robotic systems.
Embodied AI Robotics Simulation Reinforcement Learning Data Evaluation
Video Friday: Digit Learns to Dance—Virtually Overnight
In a recent roundup of advancements in robotics, IEEE Spectrum highlighted several notable developments and upcoming events in the field. Among the key innovations is Digit, a humanoid robot that can learn new whole-body control capabilities overnight through sim-to-real reinforcement training, enhancing its performance in various tasks. Additionally, the introduction of GEN-1 marks a significant milestone in robot learning, achieving a 99% success rate in simple physical tasks and drastically reducing task completion time. Unitree has made strides by open-sourcing the UnifoLM-WBT-Dataset, a comprehensive dataset for humanoid robot teleoperation, which has been available since March 5, 2026. Meanwhile, researchers presented MRReP, a Mixed Reality interface that allows users to guide autonomous mobile robots in human-shared environments through hand gestures. In other developments, Sanctuary AI showcased its advanced hydraulic hands capable of dexterous manipulation, while China’s Yuxing 3-06 satellite successfully completed an in-orbit refueling test, paving the way for future satellite servicing. Furthermore, Japan Railway West collaborated with Serendix to utilize 3D printing technology for rapid construction at Hatsushima station, demonstrating innovative solutions to infrastructure challenges. Upcoming robotics events include ICRA 2026 in Vienna from June 1-5, and the Summer School on Multi-Robot Systems in Prague from July 29 to August 4, 2026, providing platforms for further exploration and collaboration in the robotics sector.
Humanoid-robots Video-friday Robot-ai Human-robot-interaction Teleoperation Industrial-robots
Training Driving AI at 50,000× Real Time
General Motors (GM) is advancing its autonomous driving technology by addressing the complex challenges associated with unpredictable road scenarios, known as the "long tail." This initiative is crucial as GM aims to achieve fully autonomous vehicles capable of navigating diverse environments safely. The company employs a combination of large-scale simulations, reinforcement learning, and advanced AI models, such as Vision Language Action (VLA), to enhance the decision-making capabilities of its autonomous systems. To prepare for rare and unexpected driving situations, GM conducts millions of high-fidelity simulations that replicate real-world conditions. These simulations allow engineers to test the vehicles against hazardous scenarios that would be difficult to encounter safely in reality. Additionally, GM utilizes innovative techniques like “Seed-to-Seed Translation” to generate synthetic training data, enabling the modeling of extreme weather conditions and traffic scenarios. The development process also incorporates a unique dual-frequency model that balances high-level decision-making with immediate vehicle control, ensuring quick responses to dynamic road conditions. Furthermore, GM's approach includes adversarial testing to identify potential safety risks by challenging the AI's perception capabilities. As GM continues to refine its autonomous driving technology, the company is focused on creating an ecosystem that integrates various learning methods and addresses the critical edge cases that will determine the readiness of autonomous vehicles for widespread deployment. This comprehensive strategy aims to enhance safety and reliability, paving the way for a future where autonomous driving can operate without human intervention.
Autonomous-vehicles Self-driving-cars Gm
Tencent hires multiple core engineers from ByteDance’s Seed AI team
Tencent has intensified its recruitment efforts by hiring senior personnel from ByteDance's Seed AI team, focusing on expertise in visual AI platforms, infrastructure engineering, training infrastructure, and reinforcement learning algorithms. This strategic move aligns with Tencent's initiative to expedite the development of its large language models, as the company prepares for the anticipated launch of its next-generation Hunyuan 3.0 system in the second half of the year. The hiring spree reflects Tencent's commitment to enhancing its AI capabilities amid increasing competition in the tech industry.
News Feed
Video Friday: Humanoid Learns Tennis Skills Playing Humans
IEEE Spectrum robotics has released its latest edition of Video Friday, showcasing a variety of innovative robotics videos and announcing upcoming events in the field. Notable events include the International Conference on Robotics and Automation (ICRA) scheduled for June 1-5, 2026, in Vienna, and a Summer School on Multi-Robot Systems from July 29 to August 4, 2026, in Prague. Among the featured advancements, researchers have developed LATENT, a system designed to teach humanoid robots tennis skills by learning from imperfect human motion data. This innovation addresses the challenges of replicating human-like athleticism in robotics. Additionally, a breakthrough has been achieved in robotic manipulation, with a robot successfully peeling an apple using dual dexterous hands, showcasing significant progress in bimanual tasks. The development of MoDE-VLA, a control system that integrates vision, language, force, and touch data, further enhances the robot's ability to perform complex tasks with stability and precision. This shared-autonomy approach allows human operators to guide robots in executing intricate movements. In other highlights, collaborations between Tesollo and Hanyang University have led to advancements in robotic hand technology, while the Fluent Robotics Lab at the University of Michigan is set to present a paper on operational PR2 robots. The KAIST DRCD Lab has also demonstrated the capabilities of its humanoid robot, trained through deep reinforcement learning. As robotics continues to evolve, these innovations reflect the ongoing efforts to bridge the gap between human-like dexterity and robotic functionality.
Humanoid-robots Video-friday Robot-locomotion Nvidia Robot-manipulation Quadruped-robots
KAIST Humanoid v0.7: High-Speed Locomotion and the "Moonwalk" of Technical Independence
KAIST’s DRCD Lab has introduced an advanced bipedal robot platform that can run at speeds of up to 12 km/h while exhibiting human-like agility. This innovative technology, revealed recently, utilizes proprietary 3K planetary gearboxes combined with hybrid reinforcement learning techniques. The development aims to enhance robotic mobility and adaptability, potentially paving the way for more sophisticated applications in various fields, including robotics research and human-robot interaction. The lab's efforts reflect a growing trend in robotics to create machines that can navigate environments with the same fluidity and responsiveness as humans.
South Korea k-humanoid-alliance KAIST
NVIDIA Launches Vera CPU, Purpose-Built for Agentic AI
NVIDIA has unveiled the NVIDIA Vera CPU, marking a significant advancement in computing technology tailored for agentic AI and reinforcement learning. This groundbreaking processor, introduced today, boasts double the efficiency and operates 50% faster than conventional rack-scale CPUs. The launch underscores NVIDIA's commitment to enhancing AI capabilities, positioning the Vera CPU as a vital tool for developers and researchers aiming to push the boundaries of artificial intelligence. By optimizing performance specifically for AI applications, NVIDIA aims to meet the growing demands of the tech industry and facilitate more sophisticated AI solutions.
DiDi Autonomous Driving launches Voyager Labs for multimodal end-to-end driving research
DiDi Autonomous Driving has launched DiDi Voyager Labs, a new research initiative aimed at advancing end-to-end autonomous driving through the development of multimodal large models, world models, and reinforcement learning. This initiative, announced recently, will collaborate with a research team led by Professor Li Shengbo from Tsinghua University. The partnership is designed to leverage a joint framework that combines specialized expertise and resources to enhance the capabilities of autonomous driving technologies. This strategic move underscores DiDi's commitment to innovation in the autonomous vehicle sector and its efforts to stay at the forefront of technological advancements in this rapidly evolving field.
News Feed
Video Friday: Robot Dogs Haul Produce From the Field
IEEE Spectrum's weekly feature, Video Friday, showcases a variety of innovative robotics videos and highlights upcoming robotics events, including the International Conference on Robotics and Automation (ICRA) scheduled for June 1-5, 2026, in Vienna. This week’s selection includes demonstrations of the Lynx M20 robots, which are designed to address the logistical challenges of transporting harvested crops in mountainous regions. Research from a collaboration between the Max Planck Institute for Intelligent Systems, the University of Michigan, and Cornell University reveals that magnetic microrobot swarms can manipulate larger objects without direct contact, showcasing their potential for complex tasks such as assembly and movement of small items. Meanwhile, Georgia Tech is investigating how bipedal robots can recover from balance loss in unpredictable environments, aiming to enhance their functionality in real-world applications. In a separate initiative, Carnegie Mellon University's TartanAUV team is refining their autonomous underwater vehicle, Osprey, in preparation for the annual RoboSub competition. Additionally, advancements in tilt-rotor aerial robots are being explored to improve control and maneuverability through reinforcement learning techniques. The feature also includes educational tools like the Astorino robot, designed for teaching robotics in schools, and discussions on the need for more realistic datasets for autonomous driving. Overall, the content reflects the ongoing evolution and application of robotics across various fields, emphasizing both technical advancements and educational initiatives.
Humanoid-robots Video-friday Swarm-robotics Quadruped-robots Farm-robots Bipedal-robots
How can robots acquire skills through interactions with the physical world? An interview with Jiaheng Hu
Researchers are tackling the challenges of controlling high-degree-of-freedom systems, such as mobile manipulators, which are essential for both household and industrial robotics. Despite the potential of reinforcement learning to develop effective robot control policies, scaling these methods to more complex systems has presented significant difficulties. To address this issue, a team has introduced SLAC, or Simulation-Pretrained Latent Action Space, a novel approach designed to enhance the scalability of reinforcement learning in robotic applications. This innovative method aims to streamline the process of training robots, making it easier to implement advanced control strategies in real-world scenarios. The ongoing research highlights the importance of developing efficient robotic systems that can adapt to various environments and tasks, ultimately paving the way for more versatile and capable robots in the future.
Simulating the 'Masterpiece': XPENG Robotics Unveils Design Framework and Lattice Musculature for IRON
XPENG Robotics has unveiled a comprehensive technical analysis detailing the innovative 'body logic' of its IRON humanoid robot. This deep-dive, released recently, highlights significant advancements in the robot's design, including a revamped reinforcement learning framework and proprietary algorithms that enable the simulation of intricate 3D-printed lattice muscles. The development aims to enhance the robot's functionality and adaptability, showcasing XPENG's commitment to pushing the boundaries of robotics technology. This initiative reflects the company's broader strategy to integrate advanced machine learning techniques with cutting-edge manufacturing processes, positioning the IRON humanoid as a leader in the evolving robotics landscape.
China XPeng IRONRobotics needs a service framework.
RSF defines a common language for robot service capability, lifecycle operations, certification pathways, and service-provider networks.
