rldb/mcap: vendor MCAP spec 0.1 and validator

egomimic/rldb/mcap/proto/egoverse.proto

@@ -0,0 +1,137 @@
+// Generated by `python -m egomimic.rldb.mcap.schemas`; do not edit by hand.
+// EgoVerse vendor spec 0.1: message types not covered by foxglove schemas.
+
+syntax = "proto3";
+
+package egoverse;
+
+// A 3D vector.
+message Vector3 {
+  double x = 1;
+  double y = 2;
+  double z = 3;
+}
+
+// A rotation; must be unit length.
+message Quaternion {
+  double x = 1;
+  double y = 2;
+  double z = 3;
+  double w = 4;
+}
+
+// A child frame's pose in its parent (T_parent_child): m and a unit quaternion.
+message Pose {
+  Vector3 position = 1;
+  Quaternion orientation = 2;
+}
+
+// Optional per-camera facts foxglove.CameraCalibration has no field for, on the
+// camera's <topic>-info-extra, published once next to <topic>-info.
+message CameraInfoExtra {
+  string frame_id = 1;  // the camera's frame, as in its -info
+  double valid_radius = 2;  // px from the principal point where the lens model holds (fisheye); 0 = the whole image
+  int32 upright_rotation_cw_deg = 3;  // clockwise turn (0, 90, 180, 270) that makes a frame upright, for sensors mounted sideways
+}
+
+// One raw IMU sample, straight off the device: no gravity removal, no fusion.
+message Imu {
+  string frame_id = 1;  // IMU frame; must be linked in /tf_static
+  Vector3 linear_acceleration = 2;  // m/s^2, gravity included
+  Vector3 angular_velocity = 3;  // rad/s
+}
+
+// IMU noise model, as SLAM/VIO tools expect it. Published once. Datasheet values
+// are fine when the device does not calibrate them.
+message ImuInfo {
+  string frame_id = 1;
+  double accel_noise_density = 2;  // m/s^2/sqrt(Hz)
+  double accel_random_walk = 3;  // m/s^3/sqrt(Hz)
+  double gyro_noise_density = 4;  // rad/s/sqrt(Hz)
+  double gyro_random_walk = 5;  // rad/s^2/sqrt(Hz)
+}
+
+// State of the vendor's SLAM at this time, one per head pose.
+message TrackingQuality {
+  enum State {
+    UNKNOWN = 0;
+    OK = 1;
+    LOST = 2;
+    RELOCALIZED = 3;
+  }
+  State state = 1;
+}
+
+// One hand at one time: its joints and/or the wrist pose. Joints are in the order
+// the episode's hand-joints key lists them (names from spec.HAND_JOINTS). Set
+// valid = false when the hand is not tracked; never write zeros in its place.
+// A device without keypoints leaves positions empty and sets wrist_pose.
+message HandKeypoints {
+  string frame_id = 1;  // frame positions and wrist_pose are in
+  repeated double positions = 2;  // (x, y, z) in m per hand-joints entry, flattened; or empty
+  float confidence = 3;  // whole-hand tracking confidence in [0, 1]
+  bool valid = 4;  // hand tracked and its values usable
+  repeated float joint_confidence = 5;  // optional: per-joint confidences in [0, 1], one per joint
+  Pose wrist_pose = 6;  // optional: T_frame_wrist
+}
+
+// Where the wearer looks, as in Aria MPS eye gaze. frame_id is centered between
+// the eyes with +x to the wearer's left, +y up, +z forward; the gaze point is
+// depth * normalize(tan(yaw), tan(pitch), 1). Set valid = false when gaze is not
+// tracked; never write zeros in its place.
+message EyeGaze {
+  string frame_id = 1;  // gaze frame; linked in /tf_static
+  double yaw = 2;  // rad, positive = looking left
+  double pitch = 3;  // rad, positive = looking up
+  double depth = 4;  // m, distance to the gaze point
+  bool valid = 5;  // gaze tracked and values usable
+}
+
+// Measured state of one arm. Joint arrays follow joint_names. ee_pose is
+// T_base_ee: the end effector in the arm-base frame (frame_id), row-major 4x4.
+message ArmState {
+  string frame_id = 1;  // arm-base frame, e.g. "left_arm_base"
+  repeated string joint_names = 2;
+  repeated double position = 3;  // rad (or m, prismatic)
+  repeated double velocity = 4;  // rad/s (or m/s)
+  repeated double torque = 5;  // N*m (or N)
+  repeated double ee_pose = 6;  // 16 values, row-major
+}
+
+// Command sent to one arm at this time (the target it was told to reach),
+// same conventions as ArmState.
+message ArmAction {
+  string frame_id = 1;  // arm-base frame
+  repeated string joint_names = 2;
+  repeated double position = 3;  // rad (or m, prismatic)
+  repeated double ee_pose = 4;  // 16 values, row-major
+}
+
+// Gripper opening, measured (ee-state) or commanded (ee-action).
+message GripperState {
+  double position = 1;  // 0 = closed, 1 = fully open
+}
+
+// One task performed in the recording; a recording may hold several
+// (e.g. iron, then fold, then pack). Starts at the message's log time.
+message Task {
+  string name = 1;  // task slug, e.g. "fold_clothes"
+  string description = 2;  // free text for this instance
+  repeated string objects = 3;  // object slugs involved
+  int64 end_time_unix_ns = 4;  // task end, absolute Unix ns
+}
+
+// A label over [start, end), start being the message's log time; it must lie
+// inside one /task (or the recording, without /task). Field `data` matches
+// ABC-130k's /subtask-annotation.
+message Annotation {
+  string data = 1;  // English text
+  int64 end_time_unix_ns = 2;  // end, absolute Unix ns; 0 = point event (one frame wide)
+  string annotation_type = 3;  // default "language"
+  string annotation_vendor = 4;  // who wrote it; default the episode's vendor
+}
+
+// Task text for the episode, e.g. "fold the shirt and put it in the basket".
+message Instruction {
+  string data = 1;
+}