2024-09-27 Autonomy Roadmap - UPDATED after comp sync

Roadmap and topics

  • Oct 3, 2024 Autonomy system ground test geolocation Houston

    • Ground test classical CV detection for geolocation

  • Oct 5, 2024 Fly Autonomy on Houston, run Geolocation (landing pads)

    • Circles should be run on simulation

    • Test classical CV and ML?

    • Fly a circle around a chosen center/radius → Circle mode or bunch of waypoints.

      • Make a waypoint (center), then fly circle

  • Oct 12, 2024 May be moved to next week Oct 19, 2024

    • Fly cluster estimation with geolocation (landing pads). If this doesn’t work, we will opt out to make a simpler detection script.

    • Fly switching waypoints mid-flight and switching modes (ask @Andrew Shum)

  • Oct 19, 2024 Detection ground tested. When is IR camera arriving

    • Flying towards a target (detect a color and go in that direction → guided mode?) (optional)

  • Oct 26, 2024 Fly task 1 code for the first time

    • Fly detection script (either geolocation or new script)

    • Fly a couple of concentric rings with geolocation on.

  • Nov 2, 2024 Fly task 2 (might be tight)

  • May 9, 2025 Competition

CONOPS link: https://www.aerialevolution.ca/wp-content/uploads/2024/09/2025-AEAC-Competition-CONOPS-v1.0-11-September-2024.docx.pdf

  • TASK 1: Autonomous take-off / landing, but manual flying in between? (seek clarification)

    • Front camera only required to get to fire zone if autonomous (finding red balloons) (if not autonomous, pilots already have front camera)

    • 1. Take off autonomously to a certain height

    • 2. Pilot fly to balloons

    • 3. Start search pattern and detection of IR emitters. At the same time, pilots can monitor the video feed to find the “source of fire”

      • UPDATE: Pilots/watchers will save coordinates of drone when source of fire is found, then come back to the source of fire once the search pattern is complete

    • 4. Pilots fly back / RTL

    • 5. Auto-landing script

  • TASK 2:

    • UPDATE: EVERY run will be autonomous, with the pilot ready to manually take over if needed. This will give as many possible chances for an autonomous run to succeed.

    • Pathing (all locations are given beforehand)

      • UPDATE: Decide the order of buckets in which we will deliver water.

        • For simplicity, go to nearest bucket

    • Airside:

      • UPDATE: Needs:

        • 1 IR camera / CV camera with IR lens (for detecting hotspots in task 1, and maybe water source in task 2)

        • 1 CV camera (for finding water source and unloading buckets in task 2, and maybe flying towards balloons in task 1).

      • Depends on mech’s implementation of picking up water/releasing it, might be offloaded to EFS

  • Geolocation - Top priority Oct 26, 2024

    • 1. Using geolocation to get location of IR emitters

    • 2. Fly right on top of IR sensor, then just read GPS data? Centering above the IR emitter

    • 3. Work on both solutions at the same time

  • Detection stuff (combined with ML) Oct 26, 2024

    • Can’t fly too high - flight test it to see how high we want to fly (flight test, starting next term after Geolocation and Detection is done)

    • 1. OpenCV to find “brightspots”

    • UPDATE: 2. Use ML model to find “brightspots”. ML model will be backup solution (we will be using images from future flight tests to train a new ML model)

  • Cluster Estimation - Top priority Oct 26, 2024

    • 1. Take in large number of data points/locations from Geolocation, and group them

  • Autonomous water task

    • Precise coordinates, or precise controls to center drone on water

    • Use CV camera, for edge detection of buckets for loading and unloading (as GPS coordinates might not be precise enough)

    • Use precision landing module, not geolocation

  • Airside vs groundside compute

    • We are doing AIRSIDE compute for this competition

  • Search pattern

    • Search within radius of 100m from “sign of fire” (tower of balloons) Oct 26, 2024

      • 1. Go to sign of fire as center (mark coordinates down manually)

      • 2. Fly spiral/concentric rings (either manually or have someone input it into mission planner or have a script ready)

      • Generate this path given center, radius, drone’s view width

    • Eventually merge Pathing into “airside”

    • Start with searching manually, eventually get to autonomous search pattern

  • KML Oct 26, 2024

    • Record the coordinates from detection, then translate into KML file

    • Do read CONOPS for formatting

  • IR Camera

  • Detection - Fires

  • Detection - Source (940nm IR emitters)

  • Possibly Detection - Fire sign (red balloons)