Galaxea launches R1 Series for wheeled humanoid manipulation - 2025-02-25 - Article - Galaxea launched the R1 Series as a full-size wheeled dual-arm humanoid platform for data collection, research and real-world manipulation; the robot combines dual arms, a 4-DoF torso and a three-wheel steering chassis.
Research
GigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Architecture - 2026-08-16 - Research Publication - GigaBrain-0.7 combines action control, understanding and planning, and world-model prediction in a three-system embodied model. GigaAI reports training on over 37,000 hours of heterogeneous data and physical evaluation on… - source: arxiv.org
EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control - 2026-05-21 - Research Publication - The authors argue for a persistent action-updated scene state across control calls, and introduce EvoScene-VLA. - source: arxiv.org
CORAL: Scalable Multi-Task Robot Learning via LoRA Experts - 2026-03-10 - Research Publication - To address this dilemma, the authors present CORAL, a backbone- and embodiment-agnostic framework designed primarily to mitigate multi-task interference while remaining naturally extensible to a continuous stream of new… - source: arxiv.org
AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models - 2026-03-09 - Research Publication - To tackle this problem, the authors propose \method, the first subtask-aware VLA framework integrated with a scalable offline post-training pipeline. - source: arxiv.org
Galaxea publishes Open-World Dataset and G0 dual-system VLA model for R1 - 2025-08-30 - Research Publication - We present Galaxea Open-World Dataset, a large-scale, diverse collection of robot behaviors recorded in authentic human living and working environments. - source: arxiv.org
FiveAges robot_usds simulation asset library - Research Publication - A shared library of robot USD assets for ROS 2 control and Isaac Sim development, with configurable robot and end-effector models. - source: github.com
GalaxeaVLA: G0.5 vision-language-action model and robot workflows - Research Publication - Galaxea's VLA software release provides model fine-tuning, simulation evaluation and real-robot deployment workflows, including R1 Pro configurations. - source: github.com
GalaxeaDP: R1 diffusion-policy simulation workflows - Research Publication - GalaxeaDP provides diffusion-policy training, generated-data conversion and simulation evaluation for Galaxea R1 robots. Its source includes R1 Pro and R1 Lite task configurations and distinguishes current simulation workflows from… - source: github.com
Galaxea Manipulation Simulator - Research Publication - Galaxea Manipulation Simulator provides reusable manipulation benchmarks, expert demonstration generation and baseline training/evaluation workflows for R1, R1 Pro and R1 Lite. It includes more than 30 environments across 17 tasks and… - source: github.com
Galaxea Diffusion Policy implementation - Research Publication - GalaxeaDP implements diffusion-policy training, open-loop evaluation and simulated deployment with GalaxeaManipSim and LeRobot data formats. Named task configurations distinguish R1 Pro end-effector/joint policies and R1 Lite joint… - source: github.com