EVDodge: Embodied AI for High-Speed Dodging on a quadrotor using event cameras

June 9, 2019
Project Page: http://prg.cs.umd.edu/EVDodge arXiv Pre-print: https://arxiv.org/abs/1906.02919 After re-imagining the navigation stack of a micro air vehicle as a series of hierarchical competences, we develop a purposive artificial intelligence based formulation for the problem of general navigation. We call this AI framework "Embodied AI'" - AI design based on the knowledge of the agent’s hardware limitations and timing/computation constraints. Following this design philosophy, we develop a complete AI navigation stack for dodging multiple dynamic obstacles on a quadrotor with a monocular event camera and computation. We also present an approach to directly transfer the shallow neural networks trained in simulation to the real world by subsuming pre-processing using a neural network into the pipeline.

No Previous Videos

Next Video
Design, Modeling and Control of Aerial Robot DRAGON
Design, Modeling and Control of Aerial Robot DRAGON

“Design, Modeling and Control of Aerial Robot DRAGON: Dual-Rotor Embedded Multilink Robot with the Ability ...

Learn the Rules Before you Fly!

Read on