2024-11-01 Autonomy Meeting

Pathing

Jane Zeng

• Circle mode will be speedrunning now

• Waypoint circles?

  • PR is up, waiting for local_global_conversion to move to common

• KML generation script - on ground

Airside

Ashish Agrahari

• Cluster estimation progress

  • Almost done

• Geolocation/cluster estimation output to KML module and worker: call it KML processing worker?

  • Also needs to be able to send data to ground through mavlink (can we send custom messages in mavlink?)

  • The ground will then run a script to parse the GPS coords and build KML file

Tasks:

• Achita Anantachina Classical CV method tests

  • R D to look into issue

• Shahvir Wahab Research ROS with ardupilot

  • Done

  • Testing - simulation of drone inputs (camera, GPS, etc.) VS SITL?

  • Tools? how they benefit CV/ML inferencing

    • either develop faster or runs faster

• Shahvir Wahab Testing ROS with ardupilot

  • Will start soon

• Victor Terme Auto landing module

  • Needs to talk to someone about the task

  • He will talk to Tong Zhang later

• Andrew Xu Logging for all workers

  • Working on logs

  • In progress

• Siddh Patel Create log merging script

  • Merged

• Rudimentary geolocation progress?

ML

Vibhinn Gautam

• No notes as of now.

IMACS

Balaji Leninrajan

• PRs for

  • Create widget to execute terminal scripts

  • Implement UI to change address and port (reviewed)

  • Create RTL (reviewed and updated)

• Merged

  • Create navbar

• All other tasks in progress

Obstacle Avoidance

Vyomm Khanna

• Created a DroneKit script for an auto mission that switches from auto to guided mode and then back to auto mode, simulated on mp (works well, allows for intermediate waypoints ie. the output of path deflection algorithm). Aborted flight-test midway due to safety.

  • Guided mode controls is ready

• Wrapping up decision module for vfh

• completed unit tests for lidar_parser, finishing vfh and decision module unit tests. working on integration tests next week.

IR Camera + detection

• IR camera has arrived and it works quite well.

  • The infrared emitter looks like a giant white/bright spot

  • Detection of bright/white spots is needed

  • We will be gathering a lot of data hopefully. Ideally we schedule a couple more flight tests for this purpose. # of images needed - target 1100 for now?

  • We will use classical CV for the model (thru openCV). Flight test on Saturday (and resulting images) will help determine which technique to implement.