Brief

Researchers have developed Phone2Act, a novel teleoperation system that utilizes a standard smartphone as a 6-DoF robot controller through Google ARCore. This low-cost, hardware-agnostic framework is designed to simplify and scale the collection of manipulation data for training Vision-Language-Action (VLA) models. By decoupling control logic and supporting various robot platforms, Phone2Act enables researchers to more affordably gather diverse datasets for immediate use in fine-tuning models like GR00T-N1.5. AI

Researchers have developed aerial-autonomy-stack, an open-source framework designed to accelerate the development and deployment of autonomous drones. This ROS2-based system integrates perception algorithms with flight controllers like PX4 and ArduPilot. It enables end-to-end simulation at over 20 times faster than real-time, significantly reducing the build-test-release cycle for perception-based aerial autonomy. AI

A new open-source project called Text-to-CAD enables users to generate CAD models using coding agents like Codex and Claude Code. The tool supports exporting models in various formats including STEP, STL, and URDF, and allows for local execution without a backend. It also includes a CAD Explorer for inspecting generated geometry and a robot motion skill for ROS 2/MoveIt integration. AI