Главная
Study mode:
on
1
Introduction
2
Naturalistic Observations
3
How do they do it
4
Reinforcement learning
5
Pseudocode
6
Virtual Birds
7
Platformers
8
Kites
9
Kite Cycles
10
Prototypes
11
Numerical Simulation
12
Dynamical System Analysis
13
Future work
14
Multiagent navigation
15
Questions
16
Schematics
17
Preview Slide
18
Discussion
Description:
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only! Grab it Explore the fascinating world of soaring flight and airborne wind energy through this insightful 33-minute conference talk by Antonio Celani. Delve into the complexities of aerodynamics in turbulent atmospheres and discover how reinforcement learning can be applied to develop near-optimal control strategies for both bird-like soaring and kite-based power extraction. Gain a comprehensive understanding of the subject through topics such as naturalistic observations, virtual bird simulations, kite cycles, and prototypes. Examine numerical simulations, dynamical system analysis, and future prospects in multi-agent navigation. Engage with schematic representations and participate in a thought-provoking discussion on this cutting-edge intersection of biology, physics, and artificial intelligence.

Learning to Fly High: Reinforcement Learning for Soaring and Airborne Wind Energy

PCS Institute for Basic Science
Add to list
0:00 / 0:00