feat(social-bot): Person state tracker — multi-modal identity fusion #82

Closed
opened 2026-03-01 22:28:15 -05:00 by sl-jetson · 0 comments
Collaborator

Summary

Fusion node: face + voice + position into unified person state.

Requirements

  • Identity fusion: Match face_id + speaker_id + UWB position into single person_id
  • State tracking: Per-person state machine (approaching, engaged, talking, leaving, absent)
  • Multi-camera: Track across 4 CSI cameras with FOV handoff
  • Attention model: Who should robot focus on (closest, loudest, most engaged)
  • ROS2 topics: /social/persons (PersonArray with id, name, position, state, attention_score)
  • Persistence: Remember known persons across sessions
  • Group dynamics: Detect group vs 1:1 interaction

Agent: sl-perception

Labels: social-bot

## Summary Fusion node: face + voice + position into unified person state. ## Requirements - **Identity fusion**: Match face_id + speaker_id + UWB position into single person_id - **State tracking**: Per-person state machine (approaching, engaged, talking, leaving, absent) - **Multi-camera**: Track across 4 CSI cameras with FOV handoff - **Attention model**: Who should robot focus on (closest, loudest, most engaged) - **ROS2 topics**: /social/persons (PersonArray with id, name, position, state, attention_score) - **Persistence**: Remember known persons across sessions - **Group dynamics**: Detect group vs 1:1 interaction ## Agent: sl-perception ## Labels: social-bot
Sign in to join this conversation.
No Label
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: seb/saltylab-firmware#82
No description provided.