Industry Briefing
A single destination for timely, editor-curated robotics news from around the world.
Xiong Penghang: Most Data is Waste; Human-Centric Approach is Key to Success
Xiong Penghang, the CEO of Haocun Technology, has highlighted the growing significance of human motion data in the field of robotics. As the industry transitions from cognitive models to a focus on physical actions, Haocun Technology has responded by developing high-precision data gloves that accurately capture joint angles. This innovation is paving the way for a new era of embodied intelligence in robotics. The increasing demand for precise motion data signifies a notable transformation within the sector, reflecting the industry's evolving priorities and the potential for enhanced robotic capabilities.
Robotics Motion Capture Embodied Intelligence Data Gloves
Design Around the Data: Sunday Robotics Reveals Why They Built 100 Gloves Before One Robot
In an exclusive interview, Scott Walter, a leader at Sunday Robotics, discussed the company's innovative approach to robotics engineering, emphasizing their "data-first" philosophy that guided the development of their latest robot, Memo. This design strategy prioritizes the training pipeline, ensuring that the robot's capabilities are built around the data it processes rather than adapting the data to fit a pre-existing framework. The insights shared during the interview highlight Sunday Robotics' commitment to leveraging data effectively to enhance robotic functionality and performance. This approach marks a significant shift in how robotics can be developed, aiming to create more efficient and intelligent machines.
Scott Walter Sunday Robotics Memo
PaXini Launches World's First Mass-Produced Data Collection and Execution System PXCap III × PXDex III
PaXini has introduced its latest technological advancements, the PXCap III data collection gloves and the PXDex III execution end-effector, which together represent a significant leap in the integration of data capture and robotic execution. This innovative dual-end system aims to improve data quality for embodied intelligence by addressing the persistent structural discrepancies that have historically existed between data collection devices and robotic execution. The launch of these products is expected to facilitate the seamless deployment of high-quality data, enhancing the efficiency and effectiveness of robotic applications.
Data Collection Robotic Systems Embodied Intelligence Sensor Technology
SynapX Launches SYNData: Multimodal Data Collection System for Embodied AI Era
SynapX has unveiled SYNData, an innovative multimodal data collection system designed to enhance dexterous manipulation capabilities in robotics. This cutting-edge system integrates ego vision, electromyography (EMG) signals, and data from exoskeleton gloves, facilitating the scalable collection of human manipulation data essential for advancing robot learning. The launch of SYNData aims to bridge the gap between human dexterity and robotic functionality, providing researchers and developers with comprehensive tools to improve robotic performance. This development is particularly significant as it addresses the growing demand for more sophisticated and adaptable robotic systems in various applications.
Robotics
SynapX Launches SYNData: Multimodal Data Collection System for Embodied AI Era
SynapX has introduced SYNData, an innovative multimodal data collection system designed to enhance dexterous manipulation capabilities. Launched recently, this system integrates ego vision, electromyography (EMG) signals, and data from exoskeleton gloves, facilitating the scalable collection of human manipulation data essential for advancing robot learning. The development aims to improve the interaction between humans and robots, ultimately contributing to more sophisticated robotic applications in various fields. By harnessing diverse data sources, SYNData promises to provide valuable insights that can drive the evolution of robotic dexterity and functionality.
Robotics
Sunday Unveils "Memo": A Wheeled, Domestic Robot That Learns From $200 Gloves
Sunday Robotics has announced the development of "Memo," a wheeled home robot designed to operate autonomously through the innovative use of the "ACT-1" foundation model. Unlike conventional teleoperated robots, Memo's artificial intelligence is being trained with human data collected through low-cost gloves, enhancing its ability to interact and perform tasks in a home environment. The company aims to launch a beta version of Memo in 2026, marking a significant step forward in the integration of AI technology into everyday life.
Sunday Robotics
Manus Metagloves Pro Haptic: Closing the Feedback Loop for Humanoid Teleoperation
Dutch haptic specialists have unveiled their latest hardware designed to enhance the performance of embodied AI and improve dexterous robot control. This innovative technology aims to deliver high-fidelity data crucial for the development of next-generation robotic systems. The announcement comes as the demand for advanced robotics continues to grow, driven by the increasing integration of AI in various industries. By providing more precise sensory feedback, this new hardware is expected to significantly advance the capabilities of robots, enabling them to perform complex tasks with greater accuracy and efficiency. The launch highlights the ongoing efforts within the tech community to push the boundaries of robotics and artificial intelligence, paving the way for smarter, more responsive machines.
Data Collection Dexterity hand Manus
1HMX Enters the Humanoid Data Race with a High-Fidelity Teleoperation Rig
A new training system, the Nexus NX1, has been launched, combining HaptX gloves and Virtuix treadmills to create a comprehensive solution aimed at enhancing robotic dexterity training. This innovative system is designed to provide realistic haptic feedback, which developers believe is crucial for improving the skills necessary for operating robots effectively. The Nexus NX1 is positioned as a "turnkey" solution, simplifying the training process for users. The introduction of this system comes as the demand for advanced training tools in robotics continues to grow, reflecting the industry's push towards more immersive and effective learning experiences.
teleoperation 1HMX
MIT Engineers Develop Ultrasound Wristband for Real-Time Robotic Hand Control
MIT engineers have created an innovative ultrasound wristband that allows wearers to control a robotic hand through their own movements. This wristband captures real-time images of the wrist's muscles and tendons, translating them into the positions of the fingers and palm using an AI algorithm. Demonstrations have shown that users can wirelessly manipulate a robotic hand to perform tasks like playing the piano or shooting a basketball. This technology is significant as it offers a new method for hand tracking in robotics and virtual reality, potentially replacing traditional techniques that rely on cameras or sensor-laden gloves. The wristband's ability to gather diverse hand motion data could lead to advancements in training humanoid robots for dexterous tasks, including surgical procedures. Xuanhe Zhao, a professor at MIT, emphasizes the immediate impact this work could have on both virtual environments and robotic dexterity. Looking ahead, the research team aims to expand their dataset of hand motions by collecting data from users with varying hand sizes and gestures. This could enhance the capabilities of humanoid robots and improve interactions in virtual settings. No further timeline was disclosed at the time of publication.
Robotics needs a service framework.
RSF defines a common language for robot service capability, lifecycle operations, certification pathways, and service-provider networks.
