Causal Navigation By Continuoustime Neural Networks

# Causal Navigation by Continuous-time Neural Networks

**arXiv ID:** 2106.08314
**Authors:** Charles Vorbach, Ramin Hasani, Alexander Amini, Mathias Lechner, Daniela Rus
**Published:** 2021-06-15T17:45:32Z
**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.

## Skill Description

This skill is generated from the arXiv paper: Causal Navigation by Continuous-time Neural Networks (2106.08314).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2106.08314](http://arxiv.org/abs/2106.08314v2)