Multi-agent quadrotor testbed control design: integral sliding mode vs. reinforcement learning

By Steven L. Waslander, G. Hoffmann, Jung Soon Jang, Claire Jennifer Tomlin. 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2005

314 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/2f2a1d07bbb9847bd7198f13cb604e1290304b3f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Marco Hutter
2. Jemin Hwangbo
3. S. Microtechnique
4. Jeremy H. Gillula
5. Claire Jennifer Tomlin
6. Roland Yves Siegwart
7. Angela P. Schoellig
8. Inkyu Sa

In Control and Systems Engineering

1. Jemin Hwangbo
2. Marco Hutter
3. S. Microtechnique
4. Roland Yves Siegwart
5. Jeremy H. Gillula
6. Angela P. Schoellig
7. Wolfgang Ertel
8. Haitham Bou-Ammar

Citations in the corpus

• A survey of quadrotor Unmanned Aerial Vehicles (2012, background): “The purpose of GPS is tracking and localization.”
• design and control of quadrotors with application to autonomous flying (2007, methodology): “Another similar project used this technique to control the altitude of a quadrotor as shown in this paper [40].”
• Controller design for quadrotor UAVs using reinforcement learning (2010, methodology): “Reinforcement learning for quadrotor UAVs has already been investigated in [8], however we are investigating value iteration in this work for faster convergence of the learning process and also apply a full nonlinear model for the learning process.”
• Mathematical modeling and vertical flight control of a tilt-wing UAV (2012, unknown): “Key Words: Tilt-wing, quadrotor, PID, VTOL, hover”
• A simple learning strategy for high-speed quadrocopter multi-flips (2010, methodology): “Most research has so far been focused on near-hover mode operation using simplified linear models, with a variety of extensions such as autonomous long-term operation [1] and various controller design methodologies such as in [3], [4].”
• Reducing Conservativeness in Safety Guarantees by Learning Disturbances Online: Iterated Guaranteed Safe Online Learning (2012, background): “Since IGSOLR treats safety and performance in a parallel manner we will present these two aspects of the problem setup separately.”
• Control of a Quadrotor With Reinforcement Learning (2017, background): “Quadrotor control with reinforcement learning policy is demonstrated in [6] with a real flying vehicle.”