mlsanityData to 7 Oct 2026

Learning to Navigate from Scratch using World Models and Curiosity: the Good, the Bad, and the Ugly

arXiv 2308.15852 ↗First posted 30 Aug 2023cs.ROcited by 0

On the map: World models → World models for navigation

Abstract (arXiv)

Learning to navigate unknown environments from scratch is a challenging problem. This work presents a system that integrates world models with curiosity-driven exploration for autonomous navigation in new environments. We evaluate performance through simulations and real-world experiments of varying scales and complexities. In simulated environments, the approach rapidly and comprehensively explores the surroundings. Real-world scenarios introduce additional challenges. Despite demonstrating promise in a small controlled environment, we acknowledge that larger and dynamic environments can pose challenges for the current system. Our analysis emphasizes the significance of developing adaptable and robust world models that can handle environmental changes to prevent repetitive exploration of the same areas.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in World models for navigation, one of 11 directions in World models. Builds on 32 of its 46 references that are in the map. First posted on arXiv 30 Aug 2023.

Builds on

32 of 46 references.

Closest ancestors · 1

Same direction, newest first

  1. 2019Habitat: A Platform for Embodied AI Research2 Apr

Other references · 31

  1. 2018World Modelscited by 1,444
  2. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  3. 2023Mastering Diverse Domains through World Modelscited by 1,193
  4. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,173
  5. 2020Mastering Atari with Discrete World Modelscited by 990
  6. 2018Exploration by Random Network Distillationcited by 966
  7. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 885
  8. 2022DayDreamer: World Models for Physical Robot Learningcited by 372
  9. 2020Planning to Explore via Self-Supervised World Modelscited by 365
  10. 2019Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challengescited by 313
  11. 2020Learning to Explore using Active Neural SLAMcited by 308
  12. 2016CAD2RL: Real Single-Image Flight without a Single Real Imagecited by 227
19 more
  1. 2017Cognitive Mapping and Planning for Visual Navigationcited by 209
  2. 2017Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Artcited by 182
  3. 2021Reinforcement Learning with Prototypical Representationscited by 179
  4. 2021Rapid Exploration for Open-World Navigation with Latent Goal Modelscited by 118
  5. 2018Driving Policy Transfer via Modularity and Abstractioncited by 91
  6. 2017Surprise-Based Intrinsic Motivation for Deep Reinforcement Learningcited by 83
  7. 2023Multi-View Masked World Models for Visual Robotic Manipulationcited by 78
  8. 2019Shaping Belief States with Generative Environment Models for RLcited by 65
  9. 2022A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontierscited by 62
  10. 2019Contextual Imagined Goals for Self-Supervised Robotic Learningcited by 40
  11. 2021Interesting Object, Curious Agent: Learning Task-Agnostic Explorationcited by 38
  12. 2021Curiosity-Driven Exploration via Latent Bayesian Surprisecited by 22
  13. 2022Mastering the Unsupervised Reinforcement Learning Benchmark from Pixelscited by 20
  14. 2020Shaping Rewards for Reinforcement Learning with Imperfect Demonstrations using Generative Modelscited by 14
  15. 2023RL + Model-based Control: Using On-demand Optimal Control to Learn Versatile Legged Locomotioncited by 14
  16. 2022Learning Robotic Navigation from Experience: Principles, Methods, and Recent Resultscited by 13
  17. 2020First Steps: Latent-Space Control with Semantic Constraints for Quadruped Locomotioncited by 7
  18. 2019Reinforcement Learning-based Visual Navigation with Information-Theoretic Regularizationcited by 6
  19. 2023Symmetry and Complexity in Object-Centric Deep Active Inference Modelscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026VANDERER: Map-Free Exploration using Future-Aware and Visual-Curiosity-Guided Diffusion Policy
  2. 2019Learning Exploration Policies for Navigation
  3. 2025Curiosity-Driven Imagination: Discovering Plan Operators and Learning Associated Policies for Open-World Adaptation
  4. 2025WMNav: Integrating Vision-Language Models into World Models for Object Goal Navigation
  5. 2024X-MOBILITY: End-To-End Generalizable Navigation via World Modeling
  6. 2025NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments
  7. 2025From Curiosity to Competence: How World Models Interact with the Dynamics of Exploration
  8. 2024Learning World Models for Unconstrained Goal Navigation