google-deepmind/robotics-antigravity-plugin

i2rt-yam-ik

Solves 6-DOF inverse kinematics for the I2RT YAM and YAM Pro robot arm using Mink + DAQP on combined YAM + gripper MJCF.

ソースを見る

使い方

  1. インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
  2. 必要なツール、認証情報、対応環境を原文で確認します。
  3. 入力と成果物を指定し、出力を資料と照合します。
npx skills add https://github.com/google-deepmind/robotics-antigravity-plugin --skill i2rt-yam-ik

開始前の確認

  • 導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
  • スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。
リポジトリの原文

見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。

I2RT YAM Inverse Kinematics (mink + daqp via `YamIk`)

Use bundled `YamIk` (pip install mink daqp mujoco, <1 ms/solve on Linux & macOS) parameterized by arm_type ("yam" or "yam_pro") and gripper_type ("linear_4310", "crank_4310", "linear_3507", "flexible_4310", etc.) via combine_arm_and_gripper_xml — never load standalone yam.xml when driving a gripper-equipped arm because bare yam.xml has nsite = 0:

  1. `grasp_site` Frame Convention & Jaw-Closing Axis (`±Y_site`, NOT `+X_site`):
  • YAM has 3 parallel pitch axes (J2 || J3 || J4) and a 74.0 mm J4-J5 non-spherical wrist offset.
  • In i2rt gripper MJCFs, +Z_site is the forward approach vector and parallel-jaw fingers open/close along `grasp_site` `±Y_site` (NOT `+X_site`).
  • Use ik.make_grasp_pose(pos, approach_dir, jaw_perp_axis=...) (for arbitrary 3D approach vectors — top-down, angled, or side grasps) or ik.make_topdown_grasp_pose(x, y, z, obj_yaw_rad=None, tilt_deg=0.0) (tilt_deg=10–15 near outer reach >75%):
  • Pass jaw_perp_axis=None (obj_yaw_rad=None) for symmetric objects to keep wrist roll J6 near neutral 0.
  • For anisotropic objects where jaws must close perpendicular to a target axis a, pass jaw_perp_axis=a (+X_site || ±a so ±Y_site closes across the object, automatically wrapped by ±pi using the loaded MJCF's neutral +X_site at J6 = 0 so J6 stays inside [-2.094, 2.094] rad).
  1. Reliable Seeding & Mandatory FK Verification ([yam_ik.py](scripts/yam_ik.py)):
  • Instantiate ik = YamIk(arm_type=..., gripper_type=...) once and call q_goal = ik.solve(T_target, q_seed=...).
  • Q_DEFAULT_SEED = [0.0, 1.2, 1.2, -1.2, 0.0, 0.0] avoids stalling against J4 in [-1.693, 1.571] rad on downward grasps; pass q_seed=q_actual[:6] for local moves so PostureTask regularizes smoothly around the current configuration.
  • YamIk.solve enforces solver="daqp", ConfigurationLimit, non-adjacent self-collision limits, frozen gripper DOFs (clamped to each model's jnt_range), fresh re-seeding every call, and strict MuJoCo FK verification (pos_err <= 2 mm), raising ValueError before motion if any phase waypoint is unreachable.
同じリポジトリから

関連する Skills

すべての Skills
google-deepmind
コミュニティ

blender-creation

Creates physically calibrated, articulated, PBR-textured 3D MuJoCo assets (MJCF model.xml, .mjz, mjSpec) from scratch using headless Blender (bpy, bmesh, blendermeshutils, assetbuildutils), convex collision synthesis, 10-scenario auditing, and Studio preview. Use only when asked to create, model, or build a 3D MuJoCo object from a URL, image, or text description, or when blender-creation is named. Don't use for non-MuJoCo Blender/Cycles/CAD modeling.

1時間の導入数
2
GitHub Stars
80
更新日
11月17日
google-deepmind
コミュニティ

fr3-duo-control

Franka Duo robot only (Franka Research 3 / FR3 Duo dual-arm cell with Robotiq 2F-85 grippers, ZED Mini and RealSense D405 cameras). Brings up, homes, and controls it via pylibfranka on hardware or in MuJoCo sim. Use only when the user names Franka Duo, FR3 Duo, or fr3duo.

1時間の導入数
2
GitHub Stars
80
更新日
11月17日
google-deepmind
コミュニティ

i2rt-yam-bringup

Checks and installs the I2RT YAM SDK (i2rt), configures Linux socketcan or macOS gsusb CAN bringup for I2RT YAM robot arms, and provides a wave smoke test (wave.py). Use only before bringing up or programming a physical or simulated I2RT YAM robot arm, or when asked to run a wave gesture on an I2RT YAM robot. Don't use for non-YAM CAN bus debugging (e.g. automotive OBD-II or industrial PLC CAN networks) or non-robotics tasks.

1時間の導入数
2
GitHub Stars
80
更新日
11月17日
google-deepmind
コミュニティ

iteration

Staged execution and video-based debugging workflow for physical or MuJoCo simulated robots: splitting a robot manipulation task into stages, testing each stage with one script, reviewing rollout videos, and verifying physical completion after release and settle. Use only when writing code that makes a physical or simulated robot act and move. Don't use for non-robotics software engineering, UI/WebGL testing, or general scripting.

1時間の導入数
2
GitHub Stars
80
更新日
11月17日