fix(kin/diag): gaps 默认不拼胶囊对（pairs=True 仅 APG 用；实测 4096×40 峰值 4.46 GiB 全在拼接 8.6e7 对）；diag_cl 删 D 段（子目标已排除）、加 E 段（开环幅度与抹 dq 敏感度、老师中段带速度/静止起步闭环）；rollout 加 qp0；本机执行清单更新

ml/sim/closed_loop.py

@@ -65,8 +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, 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）"""
+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):
+    """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；qp0 [B,6]：起点的上一帧（默认 = q0，即静止起步）。均为诊断用"""
     g = torch.Generator(device=device); g.manual_seed(seed)
     q0, T, R, ex, tr = tasks_to_tensors(tasks, device)
     B = q0.shape[0]
@@ -74,7 +74,7 @@ def rollout(model, kin, tasks, device, K=8, safety=False, seed=0, max_sec=None,
     has_ref = torch.isfinite(ex)
     limit = torch.where(has_ref, torch.clamp(2 * ex, min=3.0), torch.full_like(ex, NOREF_SEC)) if max_sec is None else torch.full_like(ex, max_sec)
     nmax = int(math.ceil(limit.max().item() / DT))
-    q, qp = q0.clone(), q0.clone()
+    q, qp = q0.clone(), (qp0.to(device) if qp0 is not None else q0.clone())
     queue = torch.zeros(B, 0, 6, device=device)
     last = None
     subs = torch.zeros(B, 2, 6, device=device); nsub = torch.zeros(B, dtype=torch.long, device=device); sub_t = torch.zeros(B, device=device)