Timezone: »

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) @

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.

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