Imitation learning from a model predictive path-following supervisor produces a neural network policy that follows reference paths and avoids unseen obstacles, trained sample-efficiently on the real quadrotor.
Trajectory tracking with collision avoidance for nonholonomic vehi- cles with acceleration constraints and limited sensing,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Sample Efficient Learning of Path Following and Obstacle Avoidance Behavior for Quadrotors
Imitation learning from a model predictive path-following supervisor produces a neural network policy that follows reference paths and avoids unseen obstacles, trained sample-efficiently on the real quadrotor.