Name
Abstract | ||
|---|---|---|
Attaining autonomous flight is an important task in aerial robotics. Often flight trajectories are not only subject to unknown system dynamics, but also to specific task constraints. This paper presents a motion planning method for generating trajectories with minimal residual oscillations (swing-free) for rotorcraft carrying a suspended loads. We rely on a finite-sampling, batch reinforcement learning algorithm to train the system for a particular load. We find criteria that allow the trained agent to be transferred to a variety of models, state and action spaces and produce a number of different trajectories. Through a combination of simulations and experiments, we demonstrate that the inferred policy is robust to noise and the unmodeled dynamics of the system. The contributions of this work are 1) applying reinforcement learning to solve the problem of finding swing-free trajectories for rotorcraft, 2) designing a problem-specific feature vector for value function approximation, 3) giving sufficient conditions for successful learning transfer to different models, state and action spaces, and 4) verification of the resulting trajectories in both simulation and autonomous control of quadrotors with suspended loads. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/ICRA.2013.6631277 | Robotics and Automation |
Keywords | Field | DocType |
autonomous aerial vehicles,helicopters,learning (artificial intelligence),path planning,robot dynamics,UAVs,aerial robotics,autonomous flight,autonomous quadrotor control,batch reinforcement learning algorithm,finite-sampling,flight trajectory,minimal residual oscillations,motion planning method,problem-specific feature vector,rotorcraft,suspended load,swing-free trajectory learning,system dynamics,task constraints,unmanned aerial vehicles,value function approximation | Motion planning,Residual,Feature vector,Control theory,Transfer of learning,Bellman equation,Control engineering,Artificial intelligence,System dynamics,Engineering,Robotics,Reinforcement learning | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1050-4729 |
ISBN | Citations | PageRank |
978-1-4673-5641-1 | 14 | 0.79 |
References | Authors | |
13 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Aleksandra Faust | 1 | 68 | 14.83 |
| Ivana Palunko | 2 | 121 | 8.82 |
| Patricio Cruz | 3 | 78 | 6.16 |
| Rafael Fierro | 4 | 178 | 19.53 |