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/eval/check_parity.py

@@ -0,0 +1,58 @@
+"""对拍：python -m ml.eval.check_parity [--kin ml/assets/kin.json] [--data ml/data/parity.json]
+检查 PyTorch 版 fk / orient / 组对间隙 / 83 维特征 与 JS 一致，以及间隙梯度与有限差分一致。"""
+import argparse, json
+import torch
+from ml.common.kin_torch import Kin
+from ml.common.features import features, GAP_CAP
+
+
+def main():
+    ap = argparse.ArgumentParser()
+    ap.add_argument('--kin', default=None); ap.add_argument('--data', default='ml/data/parity.json')
+    a = ap.parse_args()
+    kin = Kin(a.kin) if a.kin else Kin(dtype=torch.float64)
+    D = json.load(open(a.data, encoding='utf-8'))
+    assert D['fp'] == kin.fp, f"指纹不符：parity {D['fp']} vs kin {kin.fp}（重跑 export_kin.cjs）"
+    R = D['recs']; f64 = torch.float64
+    q = torch.tensor([r['q'] for r in R], dtype=f64)
+    qp = torch.tensor([r['qPrev'] for r in R], dtype=f64)
+    T = torch.tensor([r['T'] for r in R], dtype=f64)
+    Rt = torch.tensor([r['R'] if r['R'] else [0.] * 9 for r in R], dtype=f64)
+    pre = torch.zeros(len(R), 3, 6, dtype=f64); pl = torch.zeros(len(R), dtype=torch.long)
+    for n, r in enumerate(R):
+        for k, d in enumerate(r['prefix']): pre[n, k] = torch.tensor(d, dtype=f64)
+        pl[n] = len(r['prefix'])
+    sub = torch.tensor([r['sub'] if r['sub'] else [0.] * 6 for r in R], dtype=f64)
+    sf = torch.tensor([1. if r['sub'] else 0. for r in R], dtype=f64)
+    kin = Kin(a.kin, dtype=f64) if a.kin else kin
+    xf = kin.cum_xf(q)
+    e_fk = (kin.fk(q, xf) - torch.tensor([r['fk'] for r in R], dtype=f64)).abs().max().item()
+    e_or = (kin.orient(q, xf).reshape(-1, 9) - torch.tensor([r['orient'] for r in R], dtype=f64)).abs().max().item()
+    G = kin.gaps(q, GAP_CAP, xf)
+    gm_js = torch.tensor([r['gm'] for r in R], dtype=f64)
+    e_gm = (G['gm'] - gm_js.clamp(max=GAP_CAP)).abs().max().item()
+    col_js = gm_js.min(-1).values <= 0; col_py = G['gm'].min(-1).values <= 0
+    f = features(kin, q, qp, T, Rt, pre, pl, sub, sf, gm=G['gm'], xf=xf)
+    e_f = (f - torch.tensor([r['feat'] for r in R], dtype=f64)).abs().max().item()
+    # 梯度：最小间隙对 q 的梯度 vs 有限差分（取 50 个无干涉且间隙 < 20 的样本）
+    sel = ((G['gm'].min(-1).values > 0.5) & (G['gm'].min(-1).values < 20)).nonzero().flatten()[:50]
+    rel = []
+    if len(sel):
+        qs = q[sel].clone().requires_grad_(True)
+        g = kin.gaps(qs, GAP_CAP)['gm'].min(-1).values
+        gr, = torch.autograd.grad(g.sum(), qs)
+        h = 1e-4
+        for j in range(6):
+            dq = torch.zeros_like(qs); dq[:, j] = h
+            fd = (kin.gaps(qs.detach() + dq, GAP_CAP)['gm'].min(-1).values - kin.gaps(qs.detach() - dq, GAP_CAP)['gm'].min(-1).values) / (2 * h)
+            rel.append(((gr[:, j] - fd).abs() / (fd.abs() + 1e-3)).max().item())
+    res = {'n': len(R), 'fk_max_abs_mm': e_fk, 'orient_max_abs': e_or, 'gap_max_abs_mm': e_gm,
+           'collide_bool_mismatch': int((col_js != col_py).sum()), 'feat_max_abs': e_f,
+           'grad_rel_err_max': max(rel) if rel else None}
+    ok = e_fk < 1e-6 and e_or < 1e-9 and e_gm < 1e-4 and res['collide_bool_mismatch'] == 0 and e_f < 1e-4 and (not rel or max(rel) < 1e-3)
+    res['PASS'] = bool(ok)
+    print(json.dumps(res, indent=1))
+
+
+if __name__ == '__main__':
+    main()

ml/eval/dump_parity.cjs

@@ -0,0 +1,25 @@
+/* 对拍数据：JS 侧 fk / orient / gapMatrix / 特征（ik-policy.js）→ ml/data/parity.json
+ *   node ml/eval/dump_parity.cjs [N=2000]
+ * 然后 python -m ml.eval.check_parity 比对 PyTorch 版。 */
+'use strict';
+const fs = require('fs'), path = require('path');
+const N = +process.argv[2] || 2000;
+const { S } = require('../../tests/route_bench_setup.cjs')();
+const POL = require('../../webapp/js/ik-policy.js');
+const L = S.LIM, O = S.ORDER;
+let st = 99; const rnd = () => { st = (st * 1664525 + 1013904223) >>> 0; return st / 4294967296; };
+const rq = () => O.map(id => L[id].lo + rnd() * (L[id].hi - L[id].lo));
+const recs = [];
+for (let n = 0; n < N; n++) {
+  const q = rq(), qp = q.map((v, i) => v - (rnd() - 0.5) * 2);
+  const b = rq(); const T = S.fk(b, 0); const pose = rnd() < 0.5; const R = pose ? S.orient(b) : null;
+  const r = Math.floor(rnd() * 4); const prefix = []; for (let k = 0; k < r; k++) prefix.push(q.map(() => (rnd() - 0.5) * 2));
+  const sub = rnd() < 0.5 ? rq() : null;
+  const st0 = { q, qPrev: qp, T, R, prefix, sub };
+  const f = POL.features(S, st0);
+  recs.push({ q, qPrev: qp, T, R, prefix, sub, fk: S.fk(q, 0), orient: S.orient(q), gm: Array.from(S.gapMatrix(q, 40)), feat: Array.from(f) });
+}
+const out = path.join(__dirname, '../data/parity.json');
+fs.mkdirSync(path.dirname(out), { recursive: true });
+fs.writeFileSync(out, JSON.stringify({ fp: S.modelFingerprint(), recs }));
+console.log('wrote', out, recs.length);