Building capable embodied AI systems requires more than recording ordinary video. Researchers need structured, synchronized data that helps robots understand what a person sees, how their hands move, and how an operation develops over time.

To address this challenge, Foxtech is introducing HeadGo Ego, a new head-mounted human data collection device designed for embodied AI, robot learning, imitation learning, and dexterous manipulation training.

Combining first-person visual capture, hand keypoint tracking, motion sensing, real-time monitoring, and an integrated backpack-style DataCube system, HeadGo Ego helps research teams collect human operation data in a mobile and practical workflow.

In our previous article, Pocket 3D: Transform Your Panoramic Camera into a Spatial Camera, we explained how Pocket 3D uses LiDAR technology to overcome the pose-capture limitations of panoramic cameras and enable accurate 3D data acquisition. This article explores how the collected data can be used and the broader application value of Pocket 3D.

Creating a realistic three-dimensional model of a physical environment often requires expensive professional scanners, complex software, and specialized technical experience. Mobile scanning applications may be easier to use, but they do not always provide the level of scene quality or output flexibility required for professional projects.

The newly launched Pocket 3D Portable 3D Scanner and Modeling System is designed to bridge this gap. Powered by 3D Gaussian Splatting technology and compatible with selected DJI and Insta360 cameras, Pocket 3D provides a more accessible way to capture real-world spaces and transform them into photorealistic, interactive three-dimensional models.

Collecting water samples from reservoirs, rivers, lakes, ponds, and other difficult-to-access locations can require significant time, labor, and safety preparation. Traditional sampling methods may involve boats, shoreline access, or personnel working close to deep, polluted, or unstable waters.

The EaseDip V400 Smart Water Sampling System provides a more efficient alternative by turning the DJI Matrice 400 into an aerial water-sampling platform. With automatic depth control, manual operation, real-time distance sensing, and multiple safety functions, it helps environmental teams collect water samples remotely while reducing the need for direct human access.

As robots move from simple repetitive motion toward more intelligent interaction, the ability to grasp, feel, and manipulate objects is becoming increasingly important.

A conventional gripper may be sufficient for picking up objects of a fixed shape, but many advanced robotic applications require more human-like hand movements. Robots may need to hold delicate items, adjust their grip in real time, rotate objects, perform gestures, or complete tasks involving both precision and force.

As robotic arms become increasingly important in embodied AI, robot learning, industrial automation, and research education, one key challenge remains: how can humans control robots in a more natural, precise, and efficient way?

Traditional control methods often rely on joysticks, keyboards, teach pendants, or complex remote-control interfaces. These tools can work for basic movements, but they may not fully capture the flexibility, coordination, and intention behind human arm motion.

The ExoArm-7 Wearable Exoskeleton Teleoperation Arm is designed to solve this challenge.

As robots become more compact, intelligent, and flexible, the demand for high-performance joint motors is increasing rapidly. Whether the project involves humanoid robots, robotic arms, exoskeletons, or customized automation platforms, the actuator is one of the most important components that determines motion accuracy, load capacity, and overall system performance.

The Ti5 Robot Joint Motor Series is designed to provide lightweight, compact, and integrated actuator solutions for modern robotics development.

Explore the Ti5 series here:
https://www.foxtechuav.com/search.html?keyword=Ti5

Building capable robots starts with better human demonstrations.

The new Agility A2 + ExoArm-7 VLA Suite is a wearable bimanual teleoperation platform designed to help researchers, developers, and robotics teams move faster from human demonstration to robot learning and real-world task validation.

By combining the Agility A2 dual-arm robot with the ExoArm-7 wearable exoskeleton system, this solution enables natural human motion capture, synchronized multimodal data collection, model training, and real-time robot inference within one integrated workflow.

Building capable embodied AI systems requires more than a robotic arm and an AI model. Researchers and developers need a reliable way to demonstrate tasks, capture synchronized robot data, train policies, and validate whether those policies can perform in the real world.

The new Agility A2 Isomorphic Teleoperation VLA Suite is designed to make that workflow more direct.

Built around a dual-arm leader–follower architecture, the system enables intuitive master-slave teleoperation through one-to-one joint mapping. It combines dual 7-DOF robotic arms, low-latency control, force feedback support, multi-camera RGB-D vision, high-speed data synchronization, and an integrated OpenarmX-LeRobotVLA pipeline for embodied AI research, imitation learning, VLA development, and rapid proof-of-concept validation.

Solar panel cleaning is becoming an increasingly important part of PV operation and maintenance. Dust, sand, bird droppings, and other surface contaminants can build up over time, reducing panel efficiency and increasing maintenance pressure.

For many operators, however, conventional cleaning methods come with familiar challenges: workers need to climb onto rooftops, equipment must be transported across difficult terrain, and large-scale cleaning vehicles may not be practical for remote or complex sites.

As embodied AI continues to move from simulation to real-world robotic tasks, researchers and developers need more than a robotic arm. They need a complete platform that can collect high-quality data, support different VLA models, and help validate robot learning workflows in real environments.

The Agility A2 VR Teleoperation VLA Suite is designed for this purpose. It combines dual-arm robotic manipulation, immersive VR teleoperation, multi-camera 3D vision, synchronized data acquisition, and a VLA-ready software pipeline. More importantly, it supports multiple VLA model options, including ACT, SmoLVLA, Pi0, Pi0.5, and XVLA, giving researchers and developers more flexibility for embodied AI experimentation.

When building an unmanned ground vehicle, one of the biggest challenges is not only choosing the right sensors or payloads, but finding a chassis that can move reliably across complex outdoor environments. Mud, gravel, slopes, uneven roads, construction sites, grassland, and narrow outdoor passages can all affect the stability and performance of a mobile robot.

The TS5.0 100 kg All-Terrain High-Speed Crawler Robot Chassis is designed to solve this problem. With a durable tracked structure, strong load capacity, and flexible equipment integration, it provides a reliable mobile base for outdoor robotics, inspection, security, firefighting, agriculture, research, and customized unmanned vehicle development.