exp: 端点进度选择——commit2 到达 52.1%/time_ok 35.2%（n=512），ratio2s 0.343→0.285；附带 50Hz 饥饿实测

- select='endpoint'（候选块末态离目标最近）优于 consist：n=512 到达 +1.3pp、time_ok +6.3pp、ratio −0.058
- 负结论：safety_try 1/2（41.4/44.9%）、K=4（47.3%）、DLS 兜底（52.3%/碰撞+1.1pp）、增益调度（47.3%）
- JS Runner：endpoint 选择落地、冷启动跳前瞻；starveTicks 指标；commit2 平均空转 0.8–1.3 tick，commit3 可覆盖
- route40 endpoint：12/20 ok、13/20 到达、刹车 40.4%

ml/sim/closed_loop.py

@@ -153,7 +153,7 @@ class TeacherOracle:
 def rollout(model, kin, tasks, device, K=8, safety=False, seed=0, max_sec=None, return_traj=False, use_sub=True, sub_override=None,
             qp0=None, steps=1, z_scale=1.0, select='consist', oracle=None, replan='r3', sub_rule='cross',
             fb_gain=0.0, fb_scale=0.0, fb_near=0.2, fb_fallback=0.0, safety_partial=0, commit_n=3, collect=None,
-            fb_exec=0.0, exec_safety=0, fb_ki=0.0, fb_decay=0.9, fb_imax=0.5, fb_every=1):
+            fb_exec=0.0, exec_safety=0, fb_ki=0.0, fb_decay=0.9, fb_imax=0.5, fb_every=1, safety_try=0, sel_w=0.1):
     """use_sub=False：不用子目标（sf=0）；sub_override=(subs [B,M,6] 绝对关节角, n [B] 个数 或 need [B] bool)：冷启动时用给定途经点代替子目标头；
     qp0 [B,6]：起点的上一帧（默认 = q0，即静止起步）。steps：MeanFlow 采样段数；z_scale：噪声缩放；
     select：consist（部署口径：冷启动价值前瞻、之后与上一条已提交计划的一致性）/ value（每次都价值前瞻）/ first（不选，取第 0 条）。
@@ -237,6 +237,10 @@ def rollout(model, kin, tasks, device, K=8, safety=False, seed=0, max_sec=None,
             fut = qe[:, None, None] + torch.cumsum(inc[:, :, r:], 2)          # [B,K,H-r,6]
             if select == 'first':
                 score = torch.zeros(B, K, device=device); score[:, 0] = 1
+            elif select == 'endpoint':
+                qa = fut[:, :, -1].reshape(B * K, 6)
+                e_end, _ = goal_err(kin, qa, T.repeat_interleave(K, 0), R.repeat_interleave(K, 0))
+                score = -e_end.view(B, K)
             elif cold or select == 'value':
                 # 短前瞻：候选末态的价值
                 qa = fut[:, :, -1].reshape(B * K, 6); qb = fut[:, :, -2].reshape(B * K, 6)
@@ -253,6 +257,10 @@ def rollout(model, kin, tasks, device, K=8, safety=False, seed=0, max_sec=None,
                 # 2026-10-19（审查 review_closedloop F5）：上一次是刹停或 DLS 接管的行没有「已提交计划」，
                 # 与 JS（lastPlan = null → 一致性项缺席、各候选同分 → 取第 0 条）一致：同分，稳定排序取第 0 条
                 score = torch.where(last_ok[:, None], -(d2 * w).sum(-1), torch.zeros_like(d2[..., 0]))
+                if select == 'mix':   # 一致性 + 端点进度（w=sel_w/mm）
+                    qa = fut[:, :, -1].reshape(B * K, 6)
+                    e_end, _ = goal_err(kin, qa, T.repeat_interleave(K, 0), R.repeat_interleave(K, 0))
+                    score = score - sel_w * e_end.view(B, K)
             order = torch.sort(score, dim=-1, descending=True, stable=True).indices
             pick = order[:, 0]
             if select == 'average':   # 2026-10-20：候选平均（平滑误差）——所有候选置为 K 条动作的均值
@@ -267,7 +275,8 @@ def rollout(model, kin, tasks, device, K=8, safety=False, seed=0, max_sec=None,
             if safety and safety_partial:   # 2026-10-20：允许「部分安全前缀」——执行到第一个不安全步为止，而不是全拒刹停
                 maxlen = torch.zeros(B, dtype=torch.long, device=device)
                 chosen = torch.zeros(B, commit_n, 6, device=device); chosen_k = pick.clone()
-                for kk in range(K_eff):
+                ntry = min(K_eff, safety_try) if safety_try > 0 else K_eff
+                for kk in range(ntry):
                     ck = inc[ar, order[:, kk], r:r + commit_n]
                     pts = qe[:, None] + torch.cumsum(ck, 1)
                     mids = torch.cat([qe[:, None], pts[:, :-1]], 1) + 0.5 * ck
@@ -281,12 +290,20 @@ def rollout(model, kin, tasks, device, K=8, safety=False, seed=0, max_sec=None,
                     if B == 1 and int(maxlen[0]) >= commit_n: break   # 实时单题：首个全安全候选即停（安全层 16 点→2-4 点）
                 msk = (torch.arange(commit_n, device=device)[None] < maxlen[:, None])
                 commit = torch.where(msk[..., None], chosen, torch.zeros_like(chosen))
+                if fb_gain > 0 and fb_fallback > 0:   # 全拒时兜底：半步朝目标（须通过间隙认证），避免原地停满整个周期
+                    fb1 = dls_steps(kin, qe, T, R, n=1) * fb_fallback
+                    ok1 = kin.gaps(qe + fb1[:, 0], 0.5)['gm'].min(-1).values > 0
+                    fbcom = torch.zeros(B, commit_n, 6, device=device); fbcom[:, 0] = fb1[:, 0]   # 只走一步（重复会被第二步未经认证的位移带进碰撞）
+                    mskf = (maxlen == 0) & ok1
+                    commit = torch.where(mskf[:, None, None], fbcom, commit)
+                    msk = msk | mskf[:, None]
                 brakes += (maxlen == 0).float()
                 pick = chosen_k; committed = maxlen > 0
             elif safety:
                 ok_any = torch.zeros(B, dtype=torch.bool, device=device)
                 chosen = torch.zeros(B, commit_n, 6, device=device); chosen_k = pick.clone()
-                for kk in range(K_eff):
+                ntry = min(K_eff, safety_try) if safety_try > 0 else K_eff
+                for kk in range(ntry):
                     ck = inc[ar, order[:, kk], r:r + commit_n]
                     pts = qe[:, None] + torch.cumsum(ck, 1)
                     mids = torch.cat([qe[:, None], pts[:, :-1]], 1) + 0.5 * ck