servo-tracking

Solid

Use ONLY to follow/track/watch a movable physical OBJECT vision can recognize (cup, bottle, phone, hand, person, pen, book, remote, toy, keys, pet, a specific face). NEVER use for furniture or fixed locations (desk, table, wall, floor, ceiling, door, window, workspace, room) — those are directions; use servo-control /servo/aim. NEVER use for direction words (left, right, up, down, center). If the user combines a direction AND an object ("look at the desk and follow the cup", "point at the table and track the phone"), fire TWO markers in order — servo-control /servo/aim first, then /servo/track here. The verb "look at" is ambiguous — if what follows is furniture/location, route to servo-control instead.

AI & Automation 147 stars 18 forks Updated today Apache-2.0

Install

View on GitHub

Quality Score: 83/100

Stars 20%
72
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Vision Tracking ## Quick Start Tracks and follows any object by name. YOLOWorld detects the object in the camera frame, TrackerVit follows it in real-time with servo movement. ## Workflow 1. User names an object to track. 2. **If the user also hints at a direction** ("look at desk and follow cup", "point at the table and watch the phone"), fire `/servo/aim` FIRST so the camera is pointing at the right region before YOLO detection runs. Then fire `/servo/track`. The aim should complete in ~2s before the track call takes over. 3. Prefix reply with `[HW:/servo/track:{"target":["<label1>","<label2>"]}]` — the device detects and follows. - `target` accepts a list of candidate labels. Pass 2-4 synonyms/variants to maximise the chance YOLOWorld finds the object on the first try. - A single string also works (`{"target":"cup"}`) for backward compatibility, but the list form is preferred when the object could reasonably have multiple names. 4. To stop, prefix with `[HW:/servo/track/stop:{}] (POST)`. ## Examples **Input:** "Look at the desk and follow the cup" **Output:** `[HW:/servo/aim:{"direction":"desk"}][HW:/servo/track:{"target":["cup","mug","coffee cup"]}]` Looking at the desk and locking onto the cup. **Input:** "Point at the table and track my phone" **Output:** `[HW:/servo/aim:{"direction":"desk"}][HW:/servo/track:{"target":["phone","smartphone","mobile phone"]}]` Aimed at the table, tracking your phone. **Input:** "Follow the cup" **Output:** `[HW:/servo/track:...

Details

Author
autonomous-ai
Repository
autonomous-ai/autonomous-os
Created
2 months ago
Last Updated
today
Language
Python
License
Apache-2.0

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

computer-use

Control the user's Mac via the paired Autonomous Buddy companion app — open/close apps, navigate URLs in Chrome, type text into focused fields, fire keyboard shortcuts, show desktop notifications, write to clipboard, click named UI buttons via macOS Accessibility. Also covers vision-driven tasks (screenshot, find/click unlabelled UI, read text off the screen, drag) — those load `reference/vision.md` for the synchronous see-think-act loop. Use when the user explicitly asks the device to do something on their COMPUTER (e.g. "open Chrome", "go to Gmail", "join Meet", "close Slack", "type … into my Mac", "copy … to clipboard", "click the blue button on my screen", "what's on my Mac right now?"). Do NOT use for hardware control of the device itself (LED, scene, emotion, music, servo) — those are separate skills. Do NOT use if no Mac is paired (the device's web UI shows pairing status under the Buddy card).

147 Updated today
autonomous-ai
AI & Automation Featured

higgsfield-camera

Use when the user asks about camera movements, shot types, or how to describe camera behavior in a Higgsfield prompt. Contains all named camera controls with descriptions, best use cases, and example prompt phrases.

376 Updated 1 weeks ago
OSideMedia
AI & Automation Listed

track-minions

This skill should be used when tracking delegated or multi-step work in a durable store that survives context loss — before spawning agents, while a multi-task wave is in flight, and after compaction or other context loss to recover pending work. It applies to solo, delegated, and multi-agent work alike.

1 Updated today
lklimek