ml: 数据生成 + 可微运动学对拍 + MeanFlow/WTA 策略与闭环仿真 + APG/挖错/ONNX 导出与运行手册

- M1 数据生成器：采样/老师/距离下界认证/时间律/统计/一致性门禁；确定性老师（碰撞次数计时 + resetSession）、pos 任务冻结 J6、--consensus 邻域共识过滤、Dr 类。
- 全流程代码与运行手册：数据打包/可微运动学与对拍/MeanFlow+WTA 模型/闭环仿真/APG/挖错循环/ONNX 导出；webapp 策略运行时 ik-policy.js、?policy=1 接入、tests/policy_bench.cjs；ik-solver 增 pairList/clusterExport/criticalPairs/pairGap/leverTable。

ml/common/features.py

@@ -0,0 +1,59 @@
+"""策略输入特征（83 维）—— 与 webapp/js/ik-policy.js features() 逐项一致。改动须两边同步并升 FEAT_VER。"""
+import math
+import torch
+
+FEAT_VER = 1
+VMAX = [60., 60., 90., 90., 120., 180.]
+DT = 0.02
+STEP = [v * DT for v in VMAX]
+ACC = 5.0
+H, NJ, PREFIX = 16, 6, 3
+GP = [(0, 2), (0, 3), (0, 4), (0, 5), (0, 6), (2, 4), (2, 5), (3, 5)]
+GAP_CAP = 40.0
+F_DIM = 83
+D2R = math.pi / 180.0
+ROT6 = [0, 3, 6, 1, 4, 7]   # 行主序 3×3 的前两列
+
+
+def wrap180(x):
+    return torch.remainder(x + 180.0, 360.0) - 180.0
+
+
+def features(kin, q, q_prev, T, R, prefix, prefix_len, sub, sub_flag, gm=None, xf=None):
+    """全部为 batch 张量：
+    q, q_prev [B,6] 度；T [B,3] mm；R [B,9]（pos 模式全 0）；pose 标志由 R 是否全 0 判定
+    prefix [B,3,6] 增量（度），prefix_len [B]；sub [B,6]，sub_flag [B]（0/1）
+    gm：kin.gaps(q, 40)['gm'] 可传入复用。"""
+    B = q.shape[0]
+    dt = q.dtype
+    step = torch.tensor(STEP, dtype=dt, device=q.device)
+    xf = xf if xf is not None else kin.cum_xf(q)
+    out = []
+    rad = q * D2R
+    out.append(torch.stack([torch.sin(rad), torch.cos(rad)], -1).reshape(B, 12))
+    lo, hi = kin.lo.to(dt), kin.hi.to(dt)
+    idx = [1, 3, 4]
+    out.append(2 * (q[:, idx] - lo[idx]) / (hi[idx] - lo[idx]) - 1)
+    d = torch.where(kin.cont, wrap180(q - q_prev), q - q_prev)
+    out.append(d / step)
+    p = kin.fk(q, xf); Rq = kin.orient(q, xf).reshape(B, 9)
+    out.append(p / 600)
+    out.append(Rq[:, ROT6])
+    out.append(T / 600)
+    pose = (R.abs().sum(-1) > 0).to(dt)
+    out.append(R[:, ROT6] * pose[:, None])
+    out.append((T - p) / 600)
+    out.append(((T - p) / 50).clamp(-1, 1))
+    out.append(torch.stack([1 - pose, pose], -1))
+    m = (torch.arange(PREFIX, device=q.device)[None, :] < prefix_len[:, None]).to(dt)   # [B,3]
+    out.append((prefix / step * m[:, :, None]).reshape(B, 18))
+    out.append(m)
+    sd = torch.where(kin.cont, wrap180(sub - q), sub - q) / 180 * sub_flag[:, None].to(dt)
+    out.append(sd)
+    out.append(sub_flag[:, None].to(dt))
+    if gm is None:
+        gm = kin.gaps(q, GAP_CAP, xf)['gm']
+    out.append(torch.stack([gm[:, a * 7 + b].clamp(max=GAP_CAP) / GAP_CAP for a, b in GP], -1))
+    f = torch.cat(out, -1)
+    assert f.shape[1] == F_DIM, f.shape
+    return f