{"ID":2833295,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.03429","arxiv_id":"2512.03429","title":"World Models for Autonomous Navigation of Terrestrial Robots from LIDAR Observations","abstract":"Autonomous navigation of terrestrial robots using Reinforcement Learning (RL) from LIDAR observations remains challenging due to the high dimensionality of sensor data and the sample inefficiency of model-free approaches. Conventional policy networks struggle to process full-resolution LIDAR inputs, forcing prior works to rely on simplified observations that reduce spatial awareness and navigation robustness. This paper presents a novel model-based RL framework built on top of the DreamerV3 algorithm, integrating a Multi-Layer Perceptron Variational Autoencoder (MLP-VAE) within a world model to encode high-dimensional LIDAR readings into compact latent representations. These latent features, combined with a learned dynamics predictor, enable efficient imagination-based policy optimization. Experiments on simulated TurtleBot3 navigation tasks demonstrate that the proposed architecture achieves faster convergence and higher success rate compared to model-free baselines such as SAC, DDPG, and TD3. It is worth emphasizing that the DreamerV3-based agent attains a 100% success rate across all evaluated environments when using the full dataset of the Turtlebot3 LIDAR (360 readings), while model-free methods plateaued below 85%. These findings demonstrate that integrating predictive world models with learned latent representations enables more efficient and robust navigation from high-dimensional sensory data.","short_abstract":"Autonomous navigation of terrestrial robots using Reinforcement Learning (RL) from LIDAR observations remains challenging due to the high dimensionality of sensor data and the sample inefficiency of model-free approaches. Conventional policy networks struggle to process full-resolution LIDAR inputs, forcing prior works...","url_abs":"https://arxiv.org/abs/2512.03429","url_pdf":"https://arxiv.org/pdf/2512.03429v1","authors":"[\"Raul Steinmetz\",\"Fabio Demo Rosa\",\"Victor Augusto Kich\",\"Jair Augusto Bottega\",\"Ricardo Bedin Grando\",\"Daniel Fernando Tello Gamarra\"]","published":"2025-12-03T04:15:31Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\"]","methods":"[\"Reinforcement Learning\",\"Variational Autoencoder\"]","has_code":false}