<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"><channel><title>ARX Infinity blog</title><link>https://arx-global.us/blog/</link><description>Robot learning hardware, teleoperation and data collection.</description><language>en</language><item><title>Choosing a robot arm for VLA research in 2026: X5, PiPER, WidowX AI and SO-101 compared</title><link>https://arx-global.us/blog/choosing-a-research-robot-arm/</link><guid>https://arx-global.us/blog/choosing-a-research-robot-arm/</guid><pubDate>Sat, 10 Oct 2026 08:00:00 +0800</pubDate><description>Published specs and list prices for four popular research arms, ARX X5, AgileX PiPER, Trossen WidowX AI and SO-101, and how to choose for imitation learning and VLA work.</description></item><item><title>Research built with ARX arms: 25 projects from 2024 to 2026</title><link>https://arx-global.us/blog/research-built-with-arx/</link><guid>https://arx-global.us/blog/research-built-with-arx/</guid><pubDate>Sat, 10 Oct 2026 08:00:00 +0800</pubDate><description>Robot learning projects that ran on ARX hardware, from π0 to Xiaomi-Robotics-1, grouped by topic, with the evidence for each.</description></item><item><title>Leader–follower teleoperation: a practical guide for robot learning labs</title><link>https://arx-global.us/blog/leader-follower-teleoperation/</link><guid>https://arx-global.us/blog/leader-follower-teleoperation/</guid><pubDate>Sat, 10 Oct 2026 08:00:00 +0800</pubDate><description>What leader–follower teleoperation is, why imitation-learning labs use it, what hardware it needs, how it compares with VR and SpaceMouse control, and how ARX systems record demonstrations.</description></item><item><title>How to set up a bimanual data-collection station</title><link>https://arx-global.us/blog/bimanual-data-collection-station/</link><guid>https://arx-global.us/blog/bimanual-data-collection-station/</guid><pubDate>Sat, 10 Oct 2026 08:00:00 +0800</pubDate><description>A step-by-step checklist for a two-arm teleoperation station: arms, cameras, computer, CAN binding, camera mapping, and the collect–train–deploy loop, based on ARX's published documentation.</description></item><item><title>Why force control matters for imitation learning</title><link>https://arx-global.us/blog/force-control-imitation-learning/</link><guid>https://arx-global.us/blog/force-control-imitation-learning/</guid><pubDate>Sat, 10 Oct 2026 08:00:00 +0800</pubDate><description>What force-controlled and quasi-direct-drive arms change for teleoperation, data collection and policy deployment, and which control features to check before you buy a research arm.</description></item><item><title>Egocentric data for robot learning: what recent work shows</title><link>https://arx-global.us/blog/egocentric-data-for-robot-learning/</link><guid>https://arx-global.us/blog/egocentric-data-for-robot-learning/</guid><pubDate>Sat, 10 Oct 2026 08:00:00 +0800</pubDate><description>What egocentric (first-person) human data is, what EgoVerse, EgoWAM, UMI and Xiaomi-Robotics-1 show about using it, and how to pair it with robot data and real arms for testing.</description></item><item><title>Mobile manipulation platforms for research: lift, head and base control explained</title><link>https://arx-global.us/blog/mobile-manipulation-platforms/</link><guid>https://arx-global.us/blog/mobile-manipulation-platforms/</guid><pubDate>Sat, 10 Oct 2026 08:00:00 +0800</pubDate><description>What a research mobile manipulator needs (a base you can drive from code, a lift, a movable head camera, VR teleoperation and the same data pipeline as your tabletop stations), with ARX LIFT 2 and X7 as worked examples.</description></item></channel></rss>
