---
_id: '7173'
abstract:
- lang: eng
text: Reinforcement learning has achieved state-of-the-art performance in MAV control,
waypoint flight, and obstacle avoidance. However, existing RL approaches often
assume fixed objectives and constraints, with flight behavior largely limited
by vehicle dynamics and orientation considered only when required for locomotion.
Classical planning and model predictive control handle such constraints explicitly,
but require optimization or replanning. This motivates methods that combine learned
local control with explicit constraint handling. We combine reinforcement learning
with control barrier functions to improve constraint-aware execution. We propose
parameterized waypoints that encode orientation, velocity, and corridor constraints.
Simulation and real-world experiments show that a single policy can execute different
constraint-parameterized navigation scenarios, revealing scenario-dependent trade-offs
between traversal time, tracking accuracy, and constraint satisfaction.
author:
- first_name: André
full_name: Kirsch, André
id: '229807'
last_name: Kirsch
- first_name: Jan
full_name: Rexilius, Jan
id: '245736'
last_name: Rexilius
orcid: 0000-0002-4579-214X
orcid_put_code_url: https://api.orcid.org/v2.0/0000-0002-4579-214X/work/227345663
citation:
alphadin: 'Kirsch, André ; Rexilius,
Jan: Reinforcement Learning-based MAV Navigation With Parameterized Waypoints:
Incorporating Orientation, Speed Limits, and Corridor Constraints. In:'
ama: 'Kirsch A, Rexilius J. Reinforcement Learning-based MAV Navigation With Parameterized
Waypoints: Incorporating Orientation, Speed Limits, and Corridor Constraints.'
apa: 'Kirsch, A., & Rexilius, J. (n.d.). Reinforcement Learning-based MAV Navigation
With Parameterized Waypoints: Incorporating Orientation, Speed Limits, and Corridor
Constraints. Presented at the 9th Iberian Robotics Conference (ROBOT), Barcelona.'
bibtex: '@inproceedings{Kirsch_Rexilius, title={Reinforcement Learning-based MAV
Navigation With Parameterized Waypoints: Incorporating Orientation, Speed Limits,
and Corridor Constraints}, author={Kirsch, André and Rexilius, Jan} }'
chicago: 'Kirsch, André, and Jan Rexilius. “Reinforcement Learning-Based MAV Navigation
With Parameterized Waypoints: Incorporating Orientation, Speed Limits, and Corridor
Constraints,” n.d.'
ieee: 'A. Kirsch and J. Rexilius, “Reinforcement Learning-based MAV Navigation With
Parameterized Waypoints: Incorporating Orientation, Speed Limits, and Corridor
Constraints,” presented at the 9th Iberian Robotics Conference (ROBOT), Barcelona.'
mla: 'Kirsch, André, and Jan Rexilius. Reinforcement Learning-Based MAV Navigation
With Parameterized Waypoints: Incorporating Orientation, Speed Limits, and Corridor
Constraints.'
short: 'A. Kirsch, J. Rexilius, in: n.d.'
conference:
end_date: 2026-11-20
location: Barcelona
name: 9th Iberian Robotics Conference (ROBOT)
start_date: 2026-11-18
date_created: 2026-09-21T14:31:38Z
date_updated: 2026-09-21T14:33:10Z
keyword:
- MAV navigation
- Reinforcement learning
- Constrained navigation
- Control barrier functions
language:
- iso: eng
project:
- _id: A827C0AA-C7DA-11E9-B0AE-1F4CB252D58D
name: Institute for Building Intelligence
publication_status: accepted
quality_controlled: '1'
status: public
title: 'Reinforcement Learning-based MAV Navigation With Parameterized Waypoints:
Incorporating Orientation, Speed Limits, and Corridor Constraints'
type: conference
user_id: '229807'
year: '2026'
...
---
_id: '6790'
author:
- first_name: André
full_name: Kirsch, André
id: '229807'
last_name: Kirsch
- first_name: Jan
full_name: Rexilius, Jan
id: '245736'
last_name: Rexilius
orcid: 0000-0002-4579-214X
orcid_put_code_url: https://api.orcid.org/v2.0/0000-0002-4579-214X/work/208820721
citation:
alphadin: 'Kirsch, André ; Rexilius,
Jan: Vision-Based Autonomous Waste Bin Fill-Level Monitoring with a Micro
Aerial Vehicle. In: , 2026'
ama: 'Kirsch A, Rexilius J. Vision-Based Autonomous Waste Bin Fill-Level Monitoring
with a Micro Aerial Vehicle. In: ; 2026. doi:10.1109/IE69249.2026.11539031'
apa: Kirsch, A., & Rexilius, J. (2026). Vision-Based Autonomous Waste Bin Fill-Level
Monitoring with a Micro Aerial Vehicle. Presented at the 22nd International Conference
on Intelligent Environments (IE), Lissabon, Portugal. https://doi.org/10.1109/IE69249.2026.11539031
bibtex: '@inproceedings{Kirsch_Rexilius_2026, title={Vision-Based Autonomous Waste
Bin Fill-Level Monitoring with a Micro Aerial Vehicle}, DOI={10.1109/IE69249.2026.11539031},
author={Kirsch, André and Rexilius, Jan}, year={2026} }'
chicago: Kirsch, André, and Jan Rexilius. “Vision-Based Autonomous Waste Bin Fill-Level
Monitoring with a Micro Aerial Vehicle,” 2026. https://doi.org/10.1109/IE69249.2026.11539031.
ieee: A. Kirsch and J. Rexilius, “Vision-Based Autonomous Waste Bin Fill-Level Monitoring
with a Micro Aerial Vehicle,” presented at the 22nd International Conference on
Intelligent Environments (IE), Lissabon, Portugal, 2026.
mla: Kirsch, André, and Jan Rexilius. Vision-Based Autonomous Waste Bin Fill-Level
Monitoring with a Micro Aerial Vehicle. 2026, doi:10.1109/IE69249.2026.11539031.
short: 'A. Kirsch, J. Rexilius, in: 2026.'
conference:
end_date: 2026-06-18
location: Lissabon, Portugal
name: 22nd International Conference on Intelligent Environments (IE)
start_date: 2026-06-15
date_created: 2026-03-06T12:30:43Z
date_updated: 2026-06-23T06:50:04Z
department:
- _id: '102'
doi: 10.1109/IE69249.2026.11539031
keyword:
- Waste monitoring
- Waste level estimation
- MAV navigation
language:
- iso: eng
main_file_link:
- url: https://ieeexplore.ieee.org/document/11539031
project:
- _id: A827C0AA-C7DA-11E9-B0AE-1F4CB252D58D
name: Institute for Building Intelligence
publication_status: published
quality_controlled: '1'
related_material:
record:
- id: '6993'
relation: other
status: public
status: public
title: Vision-Based Autonomous Waste Bin Fill-Level Monitoring with a Micro Aerial
Vehicle
type: conference
user_id: '220548'
year: '2026'
...