fix(kin/diag): kin.gaps 粗筛段也按点分块（COARSE_ENTRIES=3e7，≤446 点/块；实测上一版粗筛 4096 点仍 9.3 GiB）；diag_cl 加 D 段（子目标头精度 / 不用子目标 / 老师真实途经点）与目标误差进度比；rollout 加 use_sub、sub_override；本机执行清单更新

ml/sim/closed_loop.py

@@ -65,7 +65,8 @@ def dls_steps(kin, q, T, R, n=3, scale=0.3, lam=0.5):
 
 
 @torch.no_grad()
-def rollout(model, kin, tasks, device, K=8, safety=False, seed=0, max_sec=None, return_traj=False):
+def rollout(model, kin, tasks, device, K=8, safety=False, seed=0, max_sec=None, return_traj=False, use_sub=True, sub_override=None):
+    """use_sub=False：不用子目标（sf=0）；sub_override=(subs [B,2,6] 绝对关节角, need [B] bool)：冷启动时用给定途经点代替子目标头（诊断用）"""
     g = torch.Generator(device=device); g.manual_seed(seed)
     q0, T, R, ex, tr = tasks_to_tensors(tasks, device)
     B = q0.shape[0]
@@ -108,6 +109,8 @@ def rollout(model, kin, tasks, device, K=8, safety=False, seed=0, max_sec=None,
                 sub0 = sub
                 need = sub0[:, 12] > 0.5
                 subs = q[:, None] + sub0[:, :12].view(B, 2, 6) * 180
+                if sub_override is not None: subs, need = sub_override[0].to(device), sub_override[1].to(device)
+                if not use_sub: need = torch.zeros_like(need)
                 nsub = torch.where(need, torch.full_like(nsub, 2), torch.zeros_like(nsub)); sub_t.fill_(tnow)
             fut = qe[:, None, None] + torch.cumsum(inc[:, :, r:], 2)          # [B,K,H-r,6]
             if last is None: