English

Causal Navigation by Continuous-time Neural Networks

Machine Learning 2021-08-18 v2 Artificial Intelligence Neural and Evolutionary Computing Robotics

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.

Keywords

Cite

@article{arxiv.2106.08314,
  title  = {Causal Navigation by Continuous-time Neural Networks},
  author = {Charles Vorbach and Ramin Hasani and Alexander Amini and Mathias Lechner and Daniela Rus},
  journal= {arXiv preprint arXiv:2106.08314},
  year   = {2021}
}

Comments

24 Pages

R2 v1 2026-06-24T03:14:03.838Z