lunduniversity.lu.se

Denna sida på svenska This page in English

Seminars and Events at automatic control

All seminars are held at the Department of Automatic Control, in the seminar room M:2112B on the second floor in the M-building, unless stated otherwise.

 

AI Lund Lunch seminar: Path planning and way-point following for autonomous UAV missions using low-level control

Illustration. Mathematical description on a white bord of the control system for an unmanned aerial vehicle.

Seminarium

From: 2023-06-07 12:00 to 13:15
Place: Online - link by registration
Contact: Jonas [dot] Wisbrant [at] cs [dot] lth [dot] se


Topic: Path planning and way-point following for autonomous UAV missions using low-level control

When: 7 June at 12.00-13.15

Speaker: Lara Laban, PhD Student, Automatic Control.  Lund university

Where: Online - link by registration

Spoken language: English

Abstract

This seminar is a demonstration of an autonomous flight mission in real-time using an unmanned aerial vehicle (UAV), developed at the Department of Automatic Control, Lund University. The project is conducted in collaboration with LUSA (Lund University School of Aviation), which runs the UAS Lab and testbed in Ljungbyhed and has access to controlled airspace for realistic autonomous flight experiments.

For this occasion, we will be using the DJI Matrice 100, equipped with various sensors including a gimbal camera and/or thermal infrared camera, and an onboard SDK (not the commercial version). This is a simple way-point mission that uses low-level control, we will discuss how we managed to gain complete control over the aircraft (controlling angle, speed, velocity) this year; but also what lies ahead for this project in the next four years.

The main focus of the project is for the good of humanity, per se, helping and rescuing people. Automation involves multiple hierarchically organised control-loop layers, monitoring and controlling the progress of a flight plan by means of control actions. Path planning based on sensor data will be used to determine an optimal path for the aircraft to follow while meeting mission objectives and constraints, constraining a vehicle within some tolerance to a motion planning trajectory. We will also discuss the issues with implementing such algorithms on commercial products that have various restrictions and how we managed to overcome that.

Registration

To participate is free of charge, but please sign up at ai.lu.se/2023-06-07/registration and we will send you a link for access at the zoom-platform.