feat(training): release V0.9.1 避障训练与基础策略迁移

2026-09-08 10:50:13 +08:00
parent fa5485049a
commit 438e56bcc8
113 changed files with 15027 additions and 539 deletions
@@ -0,0 +1,90 @@
+"""Regenerate CPU mj_ray references: run from repository root in .venv."""
+
+import json
+import math
+import sys
+from pathlib import Path
+
+import mujoco
+import numpy as np
+
+sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
+from task_config import OBSTACLE_TASK, deployment_metadata, validate_task_config  # noqa: E402
+
+
+def generate():
+    config = validate_task_config(
+        OBSTACLE_TASK, {"sensorCfg": {"sensorMode": "multi_ring_raycast"}}, 42
+    )
+    deployment = deployment_metadata(OBSTACLE_TASK, config, 42)
+    boxes = deployment["terrain"]["boxes"]
+    # Low obstacle directly ahead; platform edge is a bounded-floor drop (no invented height map).
+    layouts = {
+        "default": boxes,
+        "low": [boxes[0], {"pos": [0.9, 0, 0.025], "size": [0.2, 0.5, 0.025], "yaw": 0}],
+        "edge": [boxes[0]],
+    }
+    cases = []
+    for layout, position, euler in [
+        ("default", [-5, 0, 0.32], [0, 0, 0]),
+        ("default", [-3, 1, 0.42], [0.23, -0.31, 0.51]),
+        ("default", [-2, -2, 0.5], [-0.35, 0.27, -0.63]),
+        ("low", [0, 0, 0.32], [0, 0, 0]),
+        ("low", [0, 0, 0.32], [0.2, 0.1, -0.1]),
+        ("edge", [5.45, 0, 0.32], [0, 0, 0]),
+    ]:
+        xml = (
+            "<mujoco><worldbody>"
+            + "".join(
+                '<geom type="box" pos="{}" size="{}"/>'.format(
+                    " ".join(map(str, b["pos"])), " ".join(map(str, b["size"]))
+                )
+                for b in layouts[layout]
+            )
+            + "</worldbody></mujoco>"
+        )
+        model = mujoco.MjModel.from_xml_string(xml)
+        data = mujoco.MjData(model)
+        mujoco.mj_forward(model, data)
+        q = np.zeros(4)
+        mujoco.mju_euler2Quat(q, np.array(euler), "xyz")
+        matrix = np.zeros(9)
+        mujoco.mju_quat2Mat(matrix, q)
+        matrix = matrix.reshape(3, 3)
+        origin = np.array(position) + matrix @ np.array([0.3, 0, 0.05])
+        distances, ids = [], []
+        for pitch in [0, -20, -45]:
+            for i in range(16):
+                yaw = math.radians(-45 + i * 90 / 15)
+                p = math.radians(pitch)
+                direction = matrix @ np.array(
+                    [math.cos(p) * math.cos(yaw), math.cos(p) * math.sin(yaw), math.sin(p)]
+                )
+                geom = np.array([-1], dtype=np.int32)
+                distance = mujoco.mj_ray(model, data, origin, direction, None, 1, -1, geom)
+                distances.append(distance)
+                ids.append(int(geom[0]))
+        cases.append(
+            dict(
+                layout=layout,
+                position=position,
+                quaternion=q.tolist(),
+                distances=distances,
+                hitIds=ids,
+                depth=[1 if d < 0 else min(1, d / 4) for d in distances],
+            )
+        )
+    root = Path("web_platform/src/rl/fixtures")
+    (root / "multiRingGolden.json").write_text(
+        json.dumps(
+            dict(source=f"CPU MuJoCo {mujoco.__version__} mj_ray", layouts=layouts, cases=cases),
+            indent=2,
+        )
+        + "\n"
+    )
+    (root / "multiRingDeployment.json").write_text(json.dumps(deployment, indent=2) + "\n")
+    Path("/tmp/go2-multi-ring-stage5/task.json").write_text(json.dumps(config))
+
+
+if __name__ == "__main__":
+    generate()