仅需Python基础，从0构建自己的具身智能机器人；从0逐步构建VLA/OpenVLA/SmolVLA/Pi0， 深入理解具身智能
-
Updated
Aug 18, 2026 - Python
#
openvla
Here are 22 public repositories matching this topic...
Robotics Data Toolkit | Convert between robotics dataset formats (RLDS, LeRobot v2/v3, Zarr, HDF5, Rosbag). Inspect, visualize, and analyze datasets. Works with HuggingFace Hub. Built for OpenVLA, Octo, LeRobot, and Diffusion Policy workflows.
robotics hdf5 data-quality-checks vla data-quality octo dataset-conversion lerobot openvla rlds physical-ai rlds-to-lerobot hdf5-to-rlds
-
Updated
Jul 22, 2026 - Python
Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment
robotics imitation-learning calvin knowledge-distillation vla robot-learning generalization catastrophic-forgetting behavior-cloning robot-manipulation embodied-ai libero foundation-models vision-language-model vision-language-action openvla
-
Updated
Aug 18, 2026 - Python
PickAgent: OpenVLA-powered Pick and Place Agent | Gradio&Simulation | Vision Language Action Model
-
Updated
Aug 10, 2025 - Python
ROS2-native runtime, benchmark, and adapter hub for Vision-Language-Action models.
benchmark robotics simulation inference-server vla robot-learning ros2 pybullet embodied-ai openpi vision-language-action lerobot openvla robot-policy vla-runtime
-
Updated
Jun 17, 2026 - Python
Independent VLA research notes: OpenVLA / π0 / Spirit paper reviews, LIBERO reproduction, XLeRobot integration. Transitioning from AD motion planning to embodied AI.
robotics vla paper-reviews embodied-ai libero spirit-ai vision-language-action lerobot openvla xlerobot vla-openvla-robotics-embodied-ai-lerobot
-
Updated
Jun 6, 2026 - Python
Train and deploy Vision-Language-Action models natively on Apple Silicon.
macos machine-learning reinforcement-learning robotics lora imitation-learning vla robot-learning mlx action-prediction apple-silicon vision-language-model diffusion-policy openvla
-
Updated
Mar 11, 2026 - Python
FR3 robot in Gazebo integrated with 4-bit quantized OpenVLA and MoveIt
-
Updated
Nov 21, 2025 - C++
A full-stack Embodied AI simulation suite powered by Genesis World: featuring OpenVLA closed-loop evaluation, procedural scene generation, massively parallel GPU RL (Unitree Go2), and multi-physics coupling (PBD/SPH).
reinforcement-learning robotics simulation multi-physics ppo embodied-ai unitree-go2 openvla vla-model rsl-rl
-
Updated
Aug 8, 2026 - Python
[ICML 2026] Think Less, Act Early: Reinforced Latent Reasoning with Early Exit in Vision-Language-Action Models
reinforcement-learning robotics vla robotics-algorithms early-exit vision-language-action openvla latent-reasoning icml-2026
-
Updated
May 15, 2026 - Python
A RoboNix Skill for experience-memory retrieval and verified action reuse across OpenVLA and π0.
vector-database embodied-ai qdrant retrieval-augmented openvla experience-memory robonix heisd rt-cache
-
Updated
Jul 19, 2026 - Python
Safety monitors for learned robot policies under distribution shift. A benchmark for which monitor still works once the deployment distribution moves.
-
Updated
Aug 11, 2026 - Python
Model-agnostic robot policy deployment with safety checks, dry-run, audit/replay, metrics and FastAPI.
-
Updated
Aug 9, 2026 - Python
OpenVLA-compatible action-model layer + model-agnostic robot agent runtime (state machine, safety validation, failure recovery), verified in tabletop sim, LIBERO and Gazebo/ROS 2
-
Updated
Aug 18, 2026 - Python
Unofficial PyTorch reproduction for OpenVLA: An Open-Source Vision-Language-Action Model.
robotics pytorch reproduction robot-manipulation vision-language-action openvla unofficial-implementation
-
Updated
Jul 2, 2026 - Python
A RoboNix Skill for motion-aware action verification, compensation, and policy recovery in embodied VLA execution.
-
Updated
Jul 19, 2026 - Python
Minecraft → VLA robot interface. Expose a Minecraft player as a standard embodied AI chassis (camera, joint states, action space) for VLA models like SmolVLA, OpenVLA, π₀.₅.
-
Updated
Jul 29, 2026 - Python
Reproducing OpenVLA-7B on LIBERO 4-suite on a single commodity GPU. 400 rollouts, 4 demo videos, 6 debugging gotchas, all open.
benchmark robotics reproduction vla robot-learning huggingface embodied-ai libero vision-language-action openvla openvla-libero-vla-robotics-embodied-ai-benchmark
-
Updated
May 8, 2026 - Shell
Archived FutureChunk: preserved local VLA data-chunking prototype; no LIBERO/OpenVLA robot result claimed.
reinforcement-learning robotics evaluation imitation-learning world-models libero vision-language-action openvla
-
Updated
Jul 16, 2026 - Python
Improve this page
Add a description, image, and links to the openvla topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the openvla topic, visit your repo's landing page and select "manage topics."