Proceedings ArticleDOI
Watch and Learn: Learning to control feedback linearizable systems from expert demonstrations
Alimzhan Sultangazin,Luigi Pannocchi,Lucas Fraile,Paulo Tabuada +3 more
- pp 8577-8583
TLDR
This paper shows how to combine expert demonstrations into a stabilizing controller, provided that demonstrations are sufficiently long and there are at least $n+1$ of them, where $n$ is the number of states of the system being controlled.Abstract:
In this paper, we revisit the problem of learning a stabilizing controller from a finite number of demonstrations by an expert. By focusing on feedback linearizable systems, we show how to combine expert demonstrations into a stabilizing controller, provided that demonstrations are sufficiently long and there are at least $n+1$ of them, where $n$ is the number of states of the system being controlled. The results are experimentally demonstrated on a CrazyFlie 2.0 quadrotor.read more
Citations
More filters
Proceedings ArticleDOI
Semi-Autonomous Non-singular Terminal Sliding Mode Control of a Micro Aerial Robot for Outdoor Wall Climbing Operation
TL;DR: In this article , a non-singular terminal mode sliding mode controller is developed for output tracking with unmodeled dynamics, parameter uncertainty, and constrained disturbances, allowing the micro aerial robot to climb the wall.
Proceedings ArticleDOI
Semi-Autonomous Non-singular Terminal Sliding Mode Control of a Micro Aerial Robot for Outdoor Wall Climbing Operation
TL;DR: In this article , a non-singular terminal mode sliding mode controller is developed for output tracking with unmodeled dynamics, parameter uncertainty, and constrained disturbances, allowing the micro aerial robot to climb the wall.
Journal ArticleDOI
Learning to control from expert demonstrations
TL;DR: This paper shows how to combine expert demonstrations into a stabilizing controller, provided that demonstrations are sufficiently long and there are at least n + 1 of them, where n is the number of states of the system being controlled.
References
More filters
Proceedings ArticleDOI
Minimum snap trajectory generation and control for quadrotors
Daniel Mellinger,Vijay Kumar +1 more
TL;DR: An algorithm is developed that enables the real-time generation of optimal trajectories through a sequence of 3-D positions and yaw angles, while ensuring safe passage through specified corridors and satisfying constraints on velocities, accelerations and inputs.
Journal ArticleDOI
Is imitation learning the route to humanoid robots
TL;DR: In this article, a review of recent developments in artificial intelligence and neural computation: learning from imitation and the development of humanoid robots is presented. But the authors focus on three important issues: efficient motor learning, the connection between action and perception, and modular motor control in the form of movement primitives.
Proceedings ArticleDOI
End-to-End Driving Via Conditional Imitation Learning
TL;DR: This work evaluates different architectures for conditional imitation learning in vision-based driving and conducts experiments in realistic three-dimensional simulations of urban driving and on a 1/5 scale robotic truck that is trained to drive in a residential area.
Journal ArticleDOI
Autonomous Helicopter Aerobatics through Apprenticeship Learning
TL;DR: These apprenticeship learning algorithms have enabled us to significantly extend the state of the art in autonomous helicopter aerobatics, including the first autonomous execution of a wide range of maneuvers, including in-place flips, in- place rolls, loops and hurricanes.