Tag: embodied-ai

ScreenAgent is an IJCAI-24 visual language model agent that autonomously controls computers by perceiving screenshots and outputting mouse/keyboard actions. Learn how to deploy this open-source breakthrough.

PointWorld from NVIDIA and Stanford revolutionizes robotic manipulation with native 3D point flow world models. Learn installation, training, evaluation, and why top labs are abandoning 2D approaches for this breakthrough system.

Discover RoboClaw, the open-source embodied intelligence assistant from SJTU's MINT lab. Learn how conversational control, semantic skill interfaces, and community-driven development are revolutionizing robot programming.

NVIDIA's DreamZero achieves #1 robot benchmark rankings with zero-shot generalization using world action models. Learn how to deploy, fine-tune, and extend this open-source robotics breakthrough.

Discover reBot-DevArm, Seeed Studio's fully open-source 6-DOF robotic arm with CERN-OHL-W-2.0 hardware licensing, Apache-2.0 software, and native integration with ROS2, LeRobot, Pinocchio, and NVIDIA Isaac Sim. Build, learn, and deploy embodied AI without proprietary lock-in.

MIT Hydra builds real-time 3D scene graphs from sensor data, enabling hierarchical spatial understanding for robotics. Discover installation, code examples, and why it's outpacing traditional mapping systems.