feat(pybot×actpred): R2 姿态反馈方案一——MPU6050 独立 IMU token 全链路

- pybot：recorder 逐帧落盘 imu.npy（T×8，roll,pitch,ax,ay,az,gx,gy,gz，与帧/动作同调用对齐）；run_loop 对声明 imu_dim 的 predictor 以 predict(..., imu=) 调用（鸭子类型，旧两参调用向后兼容）

- actpred：新增 --imu-dim；model 序列 [img×F, act×H, (IMU), PRED]（imu_dim>0 时 F+H+2，IMU token 位于 PRED 前）；dataset/train 读 imu.npy（缺失按零向量兜底）；predict/ONNX/Hailo 三后端与 export/gen_calibration/dfc_compile/_npu_test 部署链适配 imu 输入

- 姿态按物理量程固定缩放归一化（imu_norm.py，训练/推理共用，零状态）

- 测试：actpred 128 passed / pybot loop+recorder 28 passed

actpred/_onnx_validate.py

@@ -69,6 +69,17 @@ if action_stats is not None:
 pred_learned = model.pred_token.data.unsqueeze(1).numpy()   # (1,1,1,128)
 pred_none = np.zeros((1, 1, 1, 128), dtype=np.float32)
 
+# R2 方案一：imu_dim>0 时模型/ONNX 多了归一化姿态输入
+imu_dim = cfg.data.imu_dim
+imu_real = None
+imu_zero = None
+if imu_dim > 0:
+    from imu_norm import normalize_imu
+    # 原始姿态（roll=5°, pitch=-3°, 其余 0）→ 部署版输入布局 (1,1,1,imu_dim)
+    imu_real = normalize_imu([5.0, -3.0] + [0.0] * 6, imu_dim).reshape(
+        1, 1, 1, imu_dim)
+    imu_zero = np.zeros((1, 1, 1, imu_dim), dtype=np.float32)
+
 
 def frames_nhwc(imgs):
     """列表帧 → (1,H,W,3) 归一化 float32 NHWC × frame_len"""
@@ -76,35 +87,45 @@ def frames_nhwc(imgs):
     return [chw[i].transpose(1, 2, 0)[None] for i in range(len(imgs))]
 
 
-def run_onnx(imgs, hist, pred):
+def run_onnx(imgs, hist, pred, imu=None):
     feeds = {f"frame{i}": f for i, f in enumerate(frames_nhwc(imgs))}
     feeds["action_history"] = hist[None, None]
     feeds["pred_token"] = pred
+    if imu_dim > 0:
+        feeds["imu"] = imu if imu is not None else imu_zero
     return sess.run(None, feeds)[0].reshape(-1)
 
 
-def run_torch(imgs, hist):
+def run_torch(imgs, hist, imu=None):
     x = torch.stack([tf(Image.fromarray(im)) for im in imgs]).unsqueeze(0)
     hh = torch.tensor(hist).unsqueeze(0)
+    ii = None
+    if imu_dim > 0:
+        ii = torch.tensor(
+            imu if imu is not None else imu_zero).reshape(1, imu_dim).float()
     with torch.no_grad():
-        return model(x, hh).squeeze(0).numpy()
+        return model(x, hh, ii).squeeze(0).numpy()
 
 
-a = run_onnx(imgs_real, hist_real, pred_learned)
-b = run_onnx(imgs_zero, hist_real, pred_learned)
-c = run_onnx(imgs_real, hist_zero, pred_learned)
+a = run_onnx(imgs_real, hist_real, pred_learned, imu_real)
+b = run_onnx(imgs_zero, hist_real, pred_learned, imu_real)
+c = run_onnx(imgs_real, hist_zero, pred_learned, imu_real)
 d = run_onnx(imgs_zero, hist_zero, pred_learned)
-p0 = run_onnx(imgs_real, hist_real, pred_none)
+p0 = run_onnx(imgs_real, hist_real, pred_none, imu_real)
 
 print(f"onnx real_img+real_hist: {np.round(a[:6], 3)}...")
 print(f"onnx pred_token=0 diff : max={np.abs(a - p0).max():.4f}")
 print(f"img sensitivity  (a-b): max={np.abs(a - b).max():.4f}")
 print(f"hist sensitivity (a-c): max={np.abs(a - c).max():.4f}")
 
-ref = run_torch(imgs_real, hist_real)
+ok = np.abs(a - b).max() > 1e-4 and np.abs(a - c).max() > 1e-4
+if imu_dim > 0:
+    e = run_onnx(imgs_real, hist_real, pred_learned, imu_zero)
+    print(f"imu sensitivity  (a-e): max={np.abs(a - e).max():.4f}")
+
+ref = run_torch(imgs_real, hist_real, imu_real)
 print(f"torch reference        : {np.round(ref[:6], 3)}...")
 print(f"onnx vs torch max_diff : {np.abs(a - ref).max():.6e}")
 
-ok = (np.abs(a - b).max() > 1e-4 and np.abs(a - c).max() > 1e-4
-      and np.abs(a - ref).max() < 1e-4)
+ok = ok and np.abs(a - ref).max() < 1e-4
 print("PASS" if ok else "FAIL")