`

Timezone: »

 
Poster
Causal Navigation by Continuous-time Neural Networks
Charles Vorbach · Ramin Hasani · Alexander Amini · Mathias Lechner · Daniela Rus

Thu Dec 09 08:30 AM -- 10:00 AM (PST) @ None #None
in Poster Session 6 »

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: Deep Learning · Reinforcement Learning and Planning · Causality

Author Information

Charles Vorbach (Massachusetts Institute of Technology)
Ramin Hasani (MIT)
Alexander Amini (MIT)
Mathias Lechner (IST Austria)
Daniela Rus (Massachusetts Institute of Technology)

More from the Same Authors