Latent imagination facilitates zero-shot transfer in autonomous racing

conference paper Latent imagination facilitates zero-shot transfer in autonomous racing published yes Axel Brunnbauer author Luigi Berducci author Andreas Brandstatter author Mathias Lechner author 3DC22916-F248-11E8-B48F-1D18A9856A87 Ramin Hasani author Daniela Rus author Radu Grosu author ToHe department ICRA: International Conference on Robotics and Automation Vigilant Algorithmic Monitoring of Software project Formal methods for the design and analysis of complex systems project World models learn behaviors in a latent imagination space to enhance the sample-efficiency of deep reinforcement learning (RL) algorithms. While learning world models for high-dimensional observations (e.g., pixel inputs) has become practicable on standard RL benchmarks and some games, their effectiveness in real-world robotics applications has not been explored. In this paper, we investigate how such agents generalize to real-world autonomous vehicle control tasks, where advanced model-free deep RL algorithms fail. In particular, we set up a series of time-lap tasks for an F1TENTH racing robot, equipped with a high-dimensional LiDAR sensor, on a set of test tracks with a gradual increase in their complexity. In this continuous-control setting, we show that model-based agents capable of learning in imagination substantially outperform model-free agents with respect to performance, sample efficiency, successful task completion, and generalization. Moreover, we show that the generalization ability of model-based agents strongly depends on the choice of their observation model. We provide extensive empirical evidence for the effectiveness of world models provided with long enough memory horizons in sim2real tasks. IEEE2022Philadelphia, PA, United States eng 2022 International Conference on Robotics and Automation 1050-4729 9781728196817 2103.04909 00094127760012410.1109/ICRA46639.2022.9811650 7513-7520 Brunnbauer, A., Berducci, L., Brandstatter, A., Lechner, M., Hasani, R., Rus, D., & Grosu, R. (2022). Latent imagination facilitates zero-shot transfer in autonomous racing. In 2022 International Conference on Robotics and Automation (pp. 7513–7520). Philadelphia, PA, United States: IEEE. <a href="https://doi.org/10.1109/ICRA46639.2022.9811650">https://doi.org/10.1109/ICRA46639.2022.9811650</a> Brunnbauer, Axel, et al. “Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing.” 2022 International Conference on Robotics and Automation, IEEE, 2022, pp. 7513–20, doi:<a href="https://doi.org/10.1109/ICRA46639.2022.9811650">10.1109/ICRA46639.2022.9811650</a>. Brunnbauer, Axel, Luigi Berducci, Andreas Brandstatter, Mathias Lechner, Ramin Hasani, Daniela Rus, and Radu Grosu. “Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing.” In 2022 International Conference on Robotics and Automation, 7513–20. IEEE, 2022. <a href="https://doi.org/10.1109/ICRA46639.2022.9811650">https://doi.org/10.1109/ICRA46639.2022.9811650</a>. A. Brunnbauer, L. Berducci, A. Brandstatter, M. Lechner, R. Hasani, D. Rus, R. Grosu, in:, 2022 International Conference on Robotics and Automation, IEEE, 2022, pp. 7513–7520. Brunnbauer A, Berducci L, Brandstatter A, Lechner M, Hasani R, Rus D, Grosu R. 2022. Latent imagination facilitates zero-shot transfer in autonomous racing. 2022 International Conference on Robotics and Automation. ICRA: International Conference on Robotics and Automation, 7513–7520. A. Brunnbauer et al., “Latent imagination facilitates zero-shot transfer in autonomous racing,” in 2022 International Conference on Robotics and Automation, Philadelphia, PA, United States, 2022, pp. 7513–7520. Brunnbauer A, Berducci L, Brandstatter A, et al. Latent imagination facilitates zero-shot transfer in autonomous racing. In: 2022 International Conference on Robotics and Automation. IEEE; 2022:7513-7520. doi:<a href="https://doi.org/10.1109/ICRA46639.2022.9811650">10.1109/ICRA46639.2022.9811650</a> 120102022-09-04T22:02:02Z2025-09-10T09:39:53Z