Articles tagged with "humanoid-robot"
World’s first flying humanoid robot with jet engines debuts in Italy
Researchers at the Italian Institute of Technology (IIT) have developed and successfully tested iRonCub3, the world’s first jet-powered humanoid robot capable of hovering mid-air. Equipped with four jet engines—two on its arms and two on a backpack—and a titanium spine to withstand extreme heat from exhaust gases reaching 800°C, the 70 kg robot lifted off about 50 centimeters in initial indoor tests. iRonCub3 integrates advanced AI and aerodynamic control systems to maintain stability despite its asymmetrical, human-like form and shifting center of mass, a challenge not present in traditional drones. The robot’s flight control relies on neural networks trained with simulated and experimental data, enabling it to adapt to turbulent airflows and dynamic limb movements in real time. The development of iRonCub3 involved a co-design approach optimizing both the robot’s physical structure and engine placement to maximize flight control and thermal resilience. Collaborations with the Polytechnic of Milan and Stanford University contributed to wind tunnel testing and machine learning integration
roboticshumanoid-robotjet-enginesAIflight-controltitanium-materialsaerial-mobilityHumanoid robot uses NVIDIA tech to run real-world factory operations
Hexagon, in partnership with NVIDIA, has developed AEON, a humanoid robot designed to perform complex industrial tasks such as machine operation, part sorting, inspection, and asset scanning. AEON targets sectors like manufacturing, transportation, aerospace, and logistics, aiming to enhance precision and reduce human error in dynamic factory environments. The robot integrates advanced mechatronics, multimodal sensor fusion, and real-time AI to function as a flexible, autonomous industrial assistant. AEON’s development was accelerated through extensive simulation training using NVIDIA’s Isaac platform, enabling it to acquire navigation and manipulation skills within weeks rather than months. It operates on NVIDIA’s robotics stack, including Jetson Orin computers for real-time decision-making, with plans to upgrade to the IGX Thor platform to improve collaborative safety. The robot also leverages NVIDIA’s Isaac GR00T foundation model and Mimic tools to learn from human demonstrations and generate synthetic motion data, expanding its capabilities. A key feature of AEON is its ability to capture physical
robothumanoid-robotindustrial-automationNVIDIA-AIrobotics-simulationfactory-operationsAI-roboticsWatch: Figure 02 robot achieve near-human package sorting skills
Figure AI’s humanoid robot, Figure 02, has demonstrated significant advancements in package sorting, achieving near-human speed and dexterity by processing parcels in about 4.05 seconds each with a 95% barcode scanning success rate. This marks a 20% speed improvement over earlier demonstrations despite handling more complex tasks involving a mix of rigid boxes, deformable poly bags, and flat padded envelopes. Key to this progress is the upgraded Helix visuomotor system, which benefits from a six-fold increase in training data and new modules for short-term visual memory and force feedback. These enhancements enable the robot to remember partial barcode views, adjust grips delicately, and manipulate flexible parcels by flicking or patting them for optimal scanning. The improvements highlight the potential of end-to-end learning systems in dynamic warehouse environments, where the robot can adapt its sorting strategy on the fly and even generalize its skills to new tasks, such as recognizing a human hand as a signal for handing over parcels without additional programming
roboticshumanoid-robotpackage-sortingmachine-learningforce-feedbackvisual-memoryautomationSweater-wearing humanoid robot gets brain upgrade to clean, cook solo
1X Technologies has introduced Redwood, an advanced AI model powering its humanoid robot NEO, designed to autonomously perform complex household tasks such as laundry, door answering, and home navigation. Redwood is a 160 million-parameter vision-language model that integrates perception, locomotion, and control into a unified system running onboard NEO Gamma’s embedded GPU. This integration enables full-body coordination, allowing NEO to simultaneously control arms, legs, pelvis, and walking commands, which enhances its ability to brace against surfaces, handle higher payloads, and manipulate objects bi-manually. Redwood’s training on diverse real-world data, including both successful and failed task demonstrations, equips NEO with strong generalization capabilities to adapt to unfamiliar objects and task variations, improving robustness and autonomy even in offline or low-connectivity environments. Complementing Redwood, 1X Technologies has developed a comprehensive Reinforcement Learning (RL) controller that expands NEO’s mobility and dexterity for navigating real home environments. This controller supports fluid
robothumanoid-robotAI-modelrobotics-autonomymotion-controlmobile-manipulationreinforcement-learningAtlas humanoid robot adapts to failure, unlocking next-gen dexterity
Boston Dynamics’ humanoid robot Atlas has made significant advancements in dynamic perception and adaptability, enabling it to handle complex, real-world tasks with greater dexterity and reliability. Moving beyond pre-programmed movements, Atlas integrates advanced AI with classical control systems to build a real-time 3D understanding of its environment. This allows the robot to identify objects, assess their properties, and navigate obstacles dynamically, which is essential for performing intricate tasks like picking up car parts and placing them accurately. The robot’s ability to continuously update its environmental model and adjust its actions in real-time helps it compensate for errors such as objects slipping or being out of place. Atlas also demonstrates impressive resilience in challenging scenarios, including operating in poorly lit spaces and overcoming visual obstructions by actively manipulating objects to improve its perspective. A key breakthrough is its capacity to adapt seamlessly to unexpected environmental changes, such as when objects are moved during a task, requiring it to revise its plan on the fly. Furthermore, Atlas can recover from “catastrophic
robothumanoid-robotBoston-Dynamicsdynamic-perception-systemAI-roboticsrobotic-dexterityadaptive-roboticsChinese firm achieves agile, human-like walking with AI control
Chinese robotics startup EngineAI has developed an advanced AI-driven control system that enables humanoid robots to walk with straight legs, closely mimicking natural human gait. This innovative approach integrates human gait data, adversarial learning, and real-world feedback to refine robot movement across diverse environments, aiming to achieve more energy-efficient, stable, and agile locomotion. EngineAI’s lightweight humanoid platform, the PM01, has demonstrated impressive agility, including successfully performing a frontflip and executing complex dance moves from the film Kung Fu Hustle, showcasing the system’s potential for fluid, human-like motion. The PM01 robot features a compact, lightweight aluminum alloy exoskeleton with 24 degrees of freedom and a bionic structure that supports dynamic movement at speeds up to 2 meters per second. It incorporates advanced hardware such as an Intel RealSense depth camera for visual perception and an Intel N97 processor paired with an NVIDIA Jetson Orin CPU for high-performance processing and neural network training. This combination allows the PM01 to interact effectively with its environment and perform intricate tasks, making it a promising platform for research into human-robot interaction and agile robotic assistants. EngineAI’s work parallels other Chinese developments like the humanoid robot Adam, which uses reinforcement learning and imitation of human gait to achieve lifelike locomotion. Unlike traditional control methods such as Model Predictive Control used by robots like Boston Dynamics’ Atlas, EngineAI’s AI-based framework emphasizes adaptability through real-world learning, addressing challenges in unpredictable environments. While still in the research phase, these advancements mark significant progress toward next-generation humanoid robots capable of natural, efficient, and versatile movement.
robothumanoid-robotAI-controlgait-controlreinforcement-learningrobotics-platformenergy-efficient-robotics1X's NEO humanoid gains autonomy with new Redwood AI model
1X Technologies has unveiled Redwood, a new AI model designed to enhance the autonomy of its NEO humanoid robot for home environments. Redwood enables NEO to perform tasks such as laundry, answering doors, and navigating familiar spaces by leveraging real-world training data collected from 1X’s EVE and NEO robots. Key capabilities include generalization to handle task variations and unfamiliar objects, learned behaviors like hand selection and retrying failed grasps, and advanced whole-body, multi-contact manipulation that allows coordinated locomotion and manipulation, including bracing and leaning during tasks. Redwood supports mobile bi-manual manipulation, enabling NEO to move and manipulate objects simultaneously, and operates efficiently on NEO’s onboard embedded GPU. The system also integrates with an off-board language model for real-time voice control, interpreting user intent from speech and conversational context. At the 2025 NVIDIA GTC event, 1X showcased NEO in a nearly continuous teleoperated demo, highlighting Redwood’s potential as one of the first end-to-end mobile manipulation AI systems specifically designed for biped humanoid robots. Eric Jang, VP of AI at 1X, emphasized the model’s role in scaling robotic assistance for household chores. Additionally, CEO Berndt Børnich discussed the broader mission of addressing labor shortages with robotics, the challenges of designing safe and compliant home robots, regulatory hurdles, and societal perceptions of humanoid robots.
robothumanoid-robotartificial-intelligencemobile-manipulationrobotics-AIhome-automationembedded-GPUChina's humanoid robot with full embodied AI works at auto factory
China has deployed AlphaBot2, a general-purpose humanoid robot with full embodied AI, in an automotive factory operated by Dongfeng Liuzhou Motor Co. Developed by Shenzhen-based AI² Robotics, AlphaBot2 performs diverse tasks such as quality inspection, assembly, logistics, and maintenance. This deployment marks the first full-scenario validation of a domestically developed embodied AI model in China’s automotive sector. The robot leverages real factory data to continuously improve its spatial intelligence and learning capabilities through a feedback loop with AI² Robotics’ self-developed embodied large model, enhancing its efficiency, precision, and adaptability in complex, evolving manufacturing environments. AlphaBot2 is powered by the advanced GOVLA AI model, a Vision-Language-Action system built on the AI²R Brain platform, enabling near-human dexterity and full-body coordination with over 34 degrees of freedom. It features 360° spatial sensing, autonomous navigation, and a vertical working range of up to 240 cm, with over six hours of battery life for extended operations. The robot’s flexible manipulation and rapid adaptation reduce deployment time and support mixed-model automotive production lines, demonstrating significant advancements in intelligent manufacturing and factory automation in China.
robothumanoid-robotembodied-AIintelligent-manufacturingfactory-automationroboticsAI-in-roboticsMilan Kovac, Head Of Tesla Optimus Program, Departs - CleanTechnica
Milan Kovac, the head of engineering for Tesla's Optimus humanoid robot program, announced his departure on June 6, 2025, citing a desire to spend more time with his family. Despite initial speculation about possible conflicts with Elon Musk, Kovac expressed strong support for Musk and confidence in the Tesla team’s ability to advance the Optimus project. Tesla confirmed that Ashok Elluswamy, head of the Autopilot team, will assume leadership of the Optimus program. Both Kovac and Musk exchanged respectful public statements, indicating an amicable transition without signs of urgency or internal strife. Elon Musk continues to position Optimus as a transformative product, claiming it could be Tesla’s most significant development ever, with a target price around $30,000. Musk envisions the robot performing everyday tasks such as folding clothes, walking dogs, and cleaning dishes, and he has publicly declared that autonomy and Optimus are Tesla’s long-term priorities. However, skepticism remains among observers and industry watchers, who note that Tesla’s promotional videos—like the one showing Optimus folding a shirt—are staged and that the robot is not yet capable of autonomous operation. Critics draw parallels to previous Tesla hype cycles, such as with Full Self-Driving (FSD) technology, suggesting that Optimus may be similarly overpromised and years away from practical reality. Overall, while Kovac’s departure marks a leadership change, Tesla’s commitment to the Optimus project remains firm under Musk’s vision. Yet, the program faces scrutiny over its current capabilities versus public expectations, highlighting the challenges Tesla faces in delivering on its ambitious humanoid robot goals.
robotTesla-Optimushumanoid-robotautonomous-robotsAI-roboticspersonal-assistant-robotsrobotics-engineeringHeadless humanoid robot built in 40 days to work in Renault factory
Wandercraft, a Paris-based company known for its exoskeleton technology, has developed a headless humanoid robot named Calvin in just 40 days. This voice-controlled, self-balancing robot is designed to perform tough, painful, and non-ergonomic manufacturing tasks, aiming to relieve Renault Group’s workers from such duties while enhancing productivity by reducing production time. Calvin represents Wandercraft’s first industrial humanoid robot and incorporates adaptable hands capable of switching between various end effectors like suction cups and grippers, allowing it to meet diverse operational needs. Beyond industrial applications, Calvin also holds potential for medical care uses. Renault Group has made a strategic investment in Wandercraft, forming a commercial partnership to develop Calvin and future next-generation robots primarily for industrial purposes. This collaboration leverages Renault’s industrial expertise, particularly in design-to-cost and scaling, to industrialize robots and exoskeletons, thereby reducing costs and accelerating automation. Renault’s Chief Industry and Quality Officer, Thierry Charvet, emphasized that the partnership will enable workers to focus on higher-value tasks while improving overall factory productivity. Wandercraft’s CEO Matthieu Masselin highlighted the broader vision of combining robotics and exoskeleton technology to improve lives both in industrial settings and beyond, including clinics and homes.
roboticshumanoid-robotindustrial-automationexoskeleton-technologymanufacturing-roboticsRenault-Groupvoice-controlled-robotWandercraft unveils Calvin, new industrial humanoid, and Renault partnership - The Robot Report
Wandercraft, a French robotics company founded in 2012 with a mission to aid people with severe mobility impairments, has unveiled its first humanoid robot named Calvin. Developed in just 40 days using technology from its exoskeleton products, Calvin is designed primarily for industrial applications. This launch coincides with Renault Group’s minority investment in Wandercraft, aimed at advancing Calvin as a next-generation industrial robot to alleviate workers from physically demanding tasks, improve ergonomics, and boost productivity. Renault will also support commercialization efforts by leveraging its expertise in cost reduction and scaling, facilitating broader market access for Wandercraft’s robotics, including its new exoskeleton, Eve. Wandercraft’s flagship product, the Atalante X exoskeleton, is a self-stabilizing device used in nearly 100 rehabilitation centers worldwide, enabling patients with spinal cord injuries and stroke to walk and relearn natural motion. It features ActiveBalance mode and 12 degrees of freedom for hips, knees, and ankles, offering benefits for both patients and therapists. The device has FDA clearance and CE marking for various conditions. Building on this success, Wandercraft recently introduced a Personal Exoskeleton prototype designed for everyday use in home and community settings, currently undergoing clinical trials. This system also features a fully powered lower body and dynamic walking control, aiming to enhance personal mobility outside clinical environments.
roboticshumanoid-robotexoskeletonindustrial-automationmobility-assistancerehabilitation-technologyRenault-partnershipTesla’s Optimus robot VP is reportedly leaving the company
Milan Kovac, the vice president leading Tesla’s Optimus humanoid robot program, is reportedly leaving the company, according to Bloomberg News. Kovac, who has been with Tesla for nearly a decade and previously worked as a top engineer on the Autopilot team, was appointed to lead the Optimus development in 2022 and became VP of the program in late 2024. He was responsible for driving the engineering teams behind both Optimus and the shared software infrastructure with Autopilot. Tesla CEO Elon Musk has ambitious plans for the Optimus robot, projecting that “thousands” of units will be operating in Tesla factories by the end of 2025, with a rapid scale-up to millions of units per year as soon as possible. Following Kovac’s departure, Ashok Elluswamy, Tesla’s vice president of AI software, will take over leadership of the Optimus project. This leadership change comes amid Tesla’s aggressive push to advance its humanoid robot technology and integrate it into its manufacturing operations.
robotTeslahumanoid-robotOptimusAI-softwarerobotics-engineeringautomationPepper humanoid robot powered by ChatGPT conducts real-world interaction
Researchers from the University of Canberra showcased Pepper, a humanoid robot integrated with ChatGPT, at an Australian innovation festival to study public reactions to AI-powered social robots in real-world settings. Pepper captures audio from users, transcribes it, generates responses via ChatGPT, and communicates back through text-to-speech. The trial involved 88 participants who interacted with Pepper, many for the first time, providing feedback that revealed a broad spectrum of emotions including curiosity, amusement, frustration, and unease. The study underscored the importance of first impressions and real-world contexts in shaping societal acceptance of humanoid robots, especially as they become more common in sectors like healthcare, retail, and education. Key findings highlighted four main themes: user suggestions for improvement, expectations for human-like interaction, emotional responses, and perceptions of Pepper’s physical form. Participants noted a disconnect between Pepper’s human-like appearance and its limited interactive capabilities, such as difficulties in recognizing facial expressions and following social norms like turn-taking. Feedback also pointed to technical and social challenges, including the need for faster responses, greater cultural and linguistic inclusivity—particularly for Indigenous users—and improved accessibility. The study emphasizes that testing social robots “in the wild” provides richer, human-centered insights into how society may adapt to embodied AI companions beyond controlled laboratory environments.
robothumanoid-robotChatGPTAI-powered-robotshuman-robot-interactionsocial-roboticsSoftBank-RoboticsKepler debuts fifth-gen K2 humanoid robot to boost industrial automation
robotindustrial-automationhumanoid-robotautonomous-systemsroboticsadvanced-actuatorsdexterous-handsZerith H1: China’s humanoid robot cleans and restocks hotel rooms
robothumanoid-robothotel-automationAI-technologycleaning-robothospitality-industryrobotics-innovationPorton Man: Humanoid robot to test chemical gear for US Army in real-world conditions
robothumanoid-robotchemical-testingmilitary-technologyroboticsprotective-gearadvanced-roboticsTesla’s Optimus robot takes out trash, vacuums, cleans like a pro
robotTeslaOptimusAIautomationhumanoid-robotreinforcement-learningElon Musk khoe Optimus nhảy điệu giống ông Trump
robotTeslaOptimusAIhumanoid-robotautomationfuture-technologyRobot Unitree H1 'tấn công' kỹ sư
robotUnitree-H1AIroboticssafety-protocolshumanoid-robottechnologyRobot Unitree H1 'nổi điên' tấn công kỹ sư
robotUnitree-H1AIroboticssafety-protocolshumanoid-robottechnologyigus introduces Iggy Rob low-cost humanoid for service, industrial applications
robothumanoid-robotautomationindustrial-applicationsroboticsmotion-plasticsaffordable-robotics2025 Is the Year of the Humanoid Robot Factory Worker
robothumanoid-robotfactory-automationBoston-DynamicsAtlas-robotindustrial-robotsrobotics