Causal navigation by continuous-time neural networks

conference paper Causal navigation by continuous-time neural networks Advances in Neural Information Processing Systems published yes Charles J Vorbach author Ramin Hasani author Alexander Amini author Mathias Lechner author 3DC22916-F248-11E8-B48F-1D18A9856A87 Daniela Rus author GradSch department ToHe department NeurIPS: Neural Information Processing Systems Formal methods for the design and analysis of complex systems project 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. https://research-explorer.ista.ac.at/download/10670/10679/NeurIPS-2021-causal-navigation-by-continuous-time-neural-networks-Paper.pdf application/pdfno https://creativecommons.org/licenses/by-nc-nd/3.0/ Neural Information Processing Systems Foundation2021Virtual eng 35th Conference on Neural Information Processing Systems 1049-5258 2106.08314 Vorbach CJ, Hasani R, Amini A, Lechner M, Rus D. Causal navigation by continuous-time neural networks. In: 35th Conference on Neural Information Processing Systems. Neural Information Processing Systems Foundation; 2021. C. J. Vorbach, R. Hasani, A. Amini, M. Lechner, and D. Rus, “Causal navigation by continuous-time neural networks,” in 35th Conference on Neural Information Processing Systems, Virtual, 2021. Vorbach, Charles J., et al. “Causal Navigation by Continuous-Time Neural Networks.” 35th Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2021. Vorbach CJ, Hasani R, Amini A, Lechner M, Rus D. 2021. Causal navigation by continuous-time neural networks. 35th Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, . C.J. Vorbach, R. Hasani, A. Amini, M. Lechner, D. Rus, in:, 35th Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2021. Vorbach, C. J., Hasani, R., Amini, A., Lechner, M., & Rus, D. (2021). Causal navigation by continuous-time neural networks. In 35th Conference on Neural Information Processing Systems. Virtual: Neural Information Processing Systems Foundation. Vorbach, Charles J, Ramin Hasani, Alexander Amini, Mathias Lechner, and Daniela Rus. “Causal Navigation by Continuous-Time Neural Networks.” In 35th Conference on Neural Information Processing Systems. Neural Information Processing Systems Foundation, 2021. 106702022-01-25T15:47:50Z2026-07-07T06:49:46Z