Secretgoodopenpilot big

selfdrive/controls/lib/longitudinal_mpc_lib/long_mpc.py

@@ -54,7 +54,7 @@
 FCW_IDXS = T_IDXS < 5.0
 T_DIFFS = np.diff(T_IDXS, prepend=[0.])
 COMFORT_BRAKE = 2.5
-STOP_DISTANCE = 6.0
+STOP_DISTANCE = 4.0
 CRUISE_MIN_ACCEL = -1.2
 CRUISE_MAX_ACCEL = 1.6
 

selfdrive/controls/lib/longitudinal_planner.py

@@ -90,7 +90,7 @@ def parse_model(model_msg, model_error):
     return x, v, a, j, throttle_prob
 
   def update(self, sm):
-    self.mpc.mode = 'blended' if sm['selfdriveState'].experimentalMode else 'acc'
+    self.mode = 'blended' if sm['selfdriveState'].experimentalMode else 'acc'
 
     if len(sm['carControl'].orientationNED) == 3:
       accel_coast = get_coast_accel(sm['carControl'].orientationNED[1])
@@ -113,7 +113,7 @@ def update(self, sm):
     # No change cost when user is controlling the speed, or when standstill
     prev_accel_constraint = not (reset_state or sm['carState'].standstill)
 
-    if self.mpc.mode == 'acc':
+    if self.mode == 'acc':
       accel_clip = [ACCEL_MIN, get_max_accel(v_ego)]
       steer_angle_without_offset = sm['carState'].steeringAngleDeg - sm['liveParameters'].angleOffsetDeg
       accel_clip = limit_accel_in_turns(v_ego, steer_angle_without_offset, accel_clip, self.CP)
@@ -160,8 +160,17 @@ def update(self, sm):
     self.v_desired_filter.x = self.v_desired_filter.x + self.dt * (self.a_desired + a_prev) / 2.0
 
     action_t =  self.CP.longitudinalActuatorDelay + DT_MDL
-    output_a_target, self.output_should_stop = get_accel_from_plan(self.v_desired_trajectory, self.a_desired_trajectory, CONTROL_N_T_IDX,
+    output_a_target_mpc, output_should_stop_mpc = get_accel_from_plan(self.v_desired_trajectory, self.a_desired_trajectory, CONTROL_N_T_IDX,
                                                                         action_t=action_t, vEgoStopping=self.CP.vEgoStopping)
+    output_a_target_e2e = sm['modelV2'].action.desiredAcceleration
+    output_should_stop_e2e = sm['modelV2'].action.shouldStop
+
+    if self.mode == 'acc':
+      output_a_target = output_a_target_mpc
+      self.output_should_stop = output_should_stop_mpc
+    else:
+      output_a_target = min(output_a_target_mpc, output_a_target_e2e)
+      self.output_should_stop = output_should_stop_e2e or output_should_stop_mpc
 
     for idx in range(2):
       accel_clip[idx] = np.clip(accel_clip[idx], self.prev_accel_clip[idx] - 0.05, self.prev_accel_clip[idx] + 0.05)

selfdrive/modeld/fill_model_msg.py

@@ -90,11 +90,11 @@ def fill_model_msg(base_msg: capnp._DynamicStructBuilder, extended_msg: capnp._D
   fill_xyzt(modelV2.orientationRate, ModelConstants.T_IDXS, *net_output_data['plan'][0,:,Plan.ORIENTATION_RATE].T)
 
   # temporal pose
-  temporal_pose = modelV2.temporalPose
-  temporal_pose.trans = net_output_data['sim_pose'][0,:ModelConstants.POSE_WIDTH//2].tolist()
-  temporal_pose.transStd = net_output_data['sim_pose_stds'][0,:ModelConstants.POSE_WIDTH//2].tolist()
-  temporal_pose.rot = net_output_data['sim_pose'][0,ModelConstants.POSE_WIDTH//2:].tolist()
-  temporal_pose.rotStd = net_output_data['sim_pose_stds'][0,ModelConstants.POSE_WIDTH//2:].tolist()
+  #temporal_pose = modelV2.temporalPose
+  #temporal_pose.trans = net_output_data['sim_pose'][0,:ModelConstants.POSE_WIDTH//2].tolist()
+  #temporal_pose.transStd = net_output_data['sim_pose_stds'][0,:ModelConstants.POSE_WIDTH//2].tolist()
+  #temporal_pose.rot = net_output_data['sim_pose'][0,ModelConstants.POSE_WIDTH//2:].tolist()
+  #temporal_pose.rotStd = net_output_data['sim_pose_stds'][0,ModelConstants.POSE_WIDTH//2:].tolist()
 
   # poly path
   fill_xyz_poly(driving_model_data.path, ModelConstants.POLY_PATH_DEGREE, *net_output_data['plan'][0,:,Plan.POSITION].T)

selfdrive/modeld/modeld.py

@@ -31,7 +31,7 @@
 from openpilot.common.transformations.model import get_warp_matrix
 from openpilot.system import sentry
 from openpilot.selfdrive.controls.lib.desire_helper import DesireHelper
-from openpilot.selfdrive.controls.lib.drive_helpers import get_accel_from_plan, smooth_value
+from openpilot.selfdrive.controls.lib.drive_helpers import get_accel_from_plan, smooth_value, get_curvature_from_plan
 from openpilot.selfdrive.modeld.parse_model_outputs import Parser
 from openpilot.selfdrive.modeld.fill_model_msg import fill_model_msg, fill_pose_msg, PublishState
 from openpilot.selfdrive.modeld.constants import ModelConstants, Plan
@@ -46,8 +46,8 @@
 VISION_METADATA_PATH = Path(__file__).parent / 'models/driving_vision_metadata.pkl'
 POLICY_METADATA_PATH = Path(__file__).parent / 'models/driving_policy_metadata.pkl'
 
-LAT_SMOOTH_SECONDS = 0.0
-LONG_SMOOTH_SECONDS = 0.0
+LAT_SMOOTH_SECONDS = 0.1
+LONG_SMOOTH_SECONDS = 0.3
 MIN_LAT_CONTROL_SPEED = 0.3
 
 
@@ -60,7 +60,11 @@ def get_action_from_model(model_output: dict[str, np.ndarray], prev_action: log.
                                                      action_t=long_action_t)
     desired_accel = smooth_value(desired_accel, prev_action.desiredAcceleration, LONG_SMOOTH_SECONDS)
 
-    desired_curvature = model_output['desired_curvature'][0, 0]
+    desired_curvature = get_curvature_from_plan(plan[:,Plan.T_FROM_CURRENT_EULER][:,2],
+                                                plan[:,Plan.ORIENTATION_RATE][:,2],
+                                                ModelConstants.T_IDXS,
+                                                v_ego,
+                                                lat_action_t)
     if v_ego > MIN_LAT_CONTROL_SPEED:
       desired_curvature = smooth_value(desired_curvature, prev_action.desiredCurvature, LAT_SMOOTH_SECONDS)
     else:
@@ -177,7 +181,7 @@ def run(self, buf: VisionBuf, wbuf: VisionBuf, transform: np.ndarray, transform_
     # TODO model only uses last value now
     self.full_prev_desired_curv[0,:-1] = self.full_prev_desired_curv[0,1:]
     self.full_prev_desired_curv[0,-1,:] = policy_outputs_dict['desired_curvature'][0, :]
-    self.numpy_inputs['prev_desired_curv'][:] = self.full_prev_desired_curv[0, self.temporal_idxs]
+    self.numpy_inputs['prev_desired_curv'][:] = 0*self.full_prev_desired_curv[0, self.temporal_idxs]
 
     combined_outputs_dict = {**vision_outputs_dict, **policy_outputs_dict}
     if SEND_RAW_PRED:

selfdrive/modeld/parse_model_outputs.py

@@ -88,24 +88,23 @@ def parse_vision_outputs(self, outs: dict[str, np.ndarray]) -> dict[str, np.ndar
     self.parse_mdn('pose', outs, in_N=0, out_N=0, out_shape=(ModelConstants.POSE_WIDTH,))
     self.parse_mdn('wide_from_device_euler', outs, in_N=0, out_N=0, out_shape=(ModelConstants.WIDE_FROM_DEVICE_WIDTH,))
     self.parse_mdn('road_transform', outs, in_N=0, out_N=0, out_shape=(ModelConstants.POSE_WIDTH,))
+    self.parse_mdn('lane_lines', outs, in_N=0, out_N=0, out_shape=(ModelConstants.NUM_LANE_LINES,ModelConstants.IDX_N,ModelConstants.LANE_LINES_WIDTH))
+    self.parse_mdn('road_edges', outs, in_N=0, out_N=0, out_shape=(ModelConstants.NUM_ROAD_EDGES,ModelConstants.IDX_N,ModelConstants.LANE_LINES_WIDTH))
+    self.parse_mdn('lead', outs, in_N=ModelConstants.LEAD_MHP_N, out_N=ModelConstants.LEAD_MHP_SELECTION,
+                   out_shape=(ModelConstants.LEAD_TRAJ_LEN,ModelConstants.LEAD_WIDTH))
+    for k in ['lead_prob', 'lane_lines_prob']:
+      self.parse_binary_crossentropy(k, outs)
     self.parse_categorical_crossentropy('desire_pred', outs, out_shape=(ModelConstants.DESIRE_PRED_LEN,ModelConstants.DESIRE_PRED_WIDTH))
     self.parse_binary_crossentropy('meta', outs)
     return outs
 
   def parse_policy_outputs(self, outs: dict[str, np.ndarray]) -> dict[str, np.ndarray]:
     self.parse_mdn('plan', outs, in_N=ModelConstants.PLAN_MHP_N, out_N=ModelConstants.PLAN_MHP_SELECTION,
                    out_shape=(ModelConstants.IDX_N,ModelConstants.PLAN_WIDTH))
-    self.parse_mdn('lane_lines', outs, in_N=0, out_N=0, out_shape=(ModelConstants.NUM_LANE_LINES,ModelConstants.IDX_N,ModelConstants.LANE_LINES_WIDTH))
-    self.parse_mdn('road_edges', outs, in_N=0, out_N=0, out_shape=(ModelConstants.NUM_ROAD_EDGES,ModelConstants.IDX_N,ModelConstants.LANE_LINES_WIDTH))
-    self.parse_mdn('sim_pose', outs, in_N=0, out_N=0, out_shape=(ModelConstants.POSE_WIDTH,))
-    self.parse_mdn('lead', outs, in_N=ModelConstants.LEAD_MHP_N, out_N=ModelConstants.LEAD_MHP_SELECTION,
-                   out_shape=(ModelConstants.LEAD_TRAJ_LEN,ModelConstants.LEAD_WIDTH))
     if 'lat_planner_solution' in outs:
       self.parse_mdn('lat_planner_solution', outs, in_N=0, out_N=0, out_shape=(ModelConstants.IDX_N,ModelConstants.LAT_PLANNER_SOLUTION_WIDTH))
     if 'desired_curvature' in outs:
       self.parse_mdn('desired_curvature', outs, in_N=0, out_N=0, out_shape=(ModelConstants.DESIRED_CURV_WIDTH,))
-    for k in ['lead_prob', 'lane_lines_prob']:
-      self.parse_binary_crossentropy(k, outs)
     self.parse_categorical_crossentropy('desire_state', outs, out_shape=(ModelConstants.DESIRE_PRED_WIDTH,))
     return outs