Causal Navigation by Continuous-time Neural Networks
release_bz6kyrwunjcgnflaeqm5wgv5vm
by
Charles Vorbach, Ramin Hasani, Alexander Amini, Mathias Lechner, Daniela Rus
2021
Abstract
Imitation learning enables high-fidelity, vision-based learning of policies
within rich, photorealistic environments. However, such techniques often rely
on traditional discrete-time neural models and face difficulties in
generalizing to domain shifts by failing to account for the causal
relationships between the agent and the environment. In this paper, we propose
a theoretical and experimental framework for learning causal representations
using continuous-time neural networks, specifically over their discrete-time
counterparts. We evaluate our method in the context of visual-control learning
of drones over a series of complex tasks, ranging from short- and long-term
navigation, to chasing static and dynamic objects through photorealistic
environments. Our results demonstrate that causal continuous-time deep models
can perform robust navigation tasks, where advanced recurrent models fail.
These models learn complex causal control representations directly from raw
visual inputs and scale to solve a variety of tasks using imitation learning.
In text/plain
format
Archived Files and Locations
application/pdf 17.8 MB
file_asp2czehmbbqhbfnuowgbajzb4
|
arxiv.org (repository) web.archive.org (webarchive) |
2106.08314v2
access all versions, variants, and formats of this works (eg, pre-prints)