ARI implements the REP-155 aka
ROS4HRI to represents the humans detected by the robot.
See Social perception with ROS4HRI for an introduction to this API and
perception_pipeline for details regarding our implementation.
Note
pal-sdk-23.12 does not covers the full ROS4HRI specification. For instance, groups are
currently not automatically recognised, and thus, the /humans/groups/ topics
do not exist.
Social perception topics#
ARI implements the REP-155 aka ROS4HRI to represents the humans detected by the robot.
See Social perception with ROS4HRI for an introduction to this API and perception_pipeline for details regarding our implementation.
Note
pal-sdk-23.12does not covers the full ROS4HRI specification. For instance, groups are currently not automatically recognised, and thus, the/humans/groups/topics do not exist.Face-related topics#
/humans/faces/*/aligned/humans/faces/*/cropped/humans/faces/*/landmarks/humans/faces/*/roi/humans/faces/tracked/humans/persons/*/face_idBody-related topics#
/humans/bodies/*/cropped/humans/bodies/*/joint_states/humans/bodies/*/position/humans/bodies/*/roi/humans/bodies/*/skeleton2d/humans/bodies/tracked/humans/bodies/*/velocity/humans/persons/*/body_idVoice-related topics#
Caution
As of
pal-sdk-23.12, ARI can only perform speech recognition on a single voice, and does not feature automatic speaker identification.As such, the robot only ever expose one single voice with id
anonymous_speaker./humans/persons/*/voice_id/humans/voices/*/audio/humans/voices/*/is_speaking/humans/voices/*/speech/humans/voices/trackedPerson-related topics#
/humans/persons/*/alias/humans/persons/*/anonymous/humans/persons/*/body_id/humans/persons/*/engagement_status/humans/persons/*/face_id/humans/persons/known/humans/persons/*/location_confidence/humans/persons/tracked/humans/persons/*/voice_idOther topics#
/humans/candidate_matches