English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep reinforcement learning provides a promising approach for vision-basedcontrol of real-world robots. However, the generalization of such modelsdepends critically on the quantity and variety of data available for training.This data can be difficult to obtain for some types of robotic systems, such asfragile, small-scale quadrotors. Simulated rendering and physics can providefor much larger datasets, but such data is inherently of lower quality: many ofthe phenomena that make the real-world autonomous flight problem challenging,such as complex physics and air currents, are modeled poorly or not at all, andthe systematic differences between simulation and the real world are typicallyimpossible to eliminate. In this work, we investigate how data from bothsimulation and the real world can be combined in a hybrid deep reinforcementlearning algorithm. Our method uses real-world data to learn about the dynamicsof the system, and simulated data to learn a generalizable perception systemthat can enable the robot to avoid collisions using only a monocular camera. Wedemonstrate our approach on a real-world nano aerial vehicle collisionavoidance task, showing that with only an hour of real-world data, thequadrotor can avoid collisions in new environments with various lightingconditions and geometry. Code, instructions for building the aerial vehicles,and videos of the experiments can be found at github.com/gkahn13/GtS

Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight