mlsanityData to 14 Oct 2026

Learning to Crawl: Latent Model-Based Reinforcement Learning for Soft Robotic Adaptive Locomotion

arXiv 2510.05957 ↗First posted 7 Oct 2025cs.ROcited by 0

On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation

Abstract (arXiv)

Soft robotic crawlers are mobile robots that utilize soft body deformability and compliance to achieve locomotion through surface contact. Designing control strategies for such systems is challenging due to model inaccuracies, sensor noise, and the need to discover locomotor gaits. In this work, we present a model-based reinforcement learning (MB-RL) framework in which latent dynamics inferred from onboard sensors serve as a predictive model that guides an actor-critic algorithm to optimize locomotor policies. We evaluate the framework on a minimal crawler model in simulation using inertial measurement units and time-of-flight sensors as observations. The learned latent dynamics enable short-horizon motion prediction while the actor-critic discovers effective locomotor policies. This approach highlights the potential of latent-dynamics MB-RL for enabling embodied soft robotic adaptive locomotion based solely on noisy sensor feedback.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 12 of its 36 references that are in the map. First posted on arXiv 7 Oct 2025.

Builds on

12 of 36 references.

References · 12

  1. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  2. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
  3. 2023Mastering Diverse Domains through World Modelscited by 1,253
  4. 2020Mastering Atari with Discrete World Modelscited by 1,007
  5. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 774
  6. 2016Tutorial on Variational Autoencoderscited by 409
  7. 2022DayDreamer: World Models for Physical Robot Learningcited by 400
  8. 2025Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Roboticscited by 51
  9. 2017An Earthworm-Inspired Soft Crawling Robot Controlled by Frictioncited by 1
  10. 2019Understanding Legged Crawling for Soft-Roboticscited by 1
  11. 2023Locomotion and Obstacle Avoidance of a Worm-like Soft Robotcited by 1
  12. 2024Optimal gait design for nonlinear soft robotic crawlerscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Transferable Latent-to-Latent Locomotion Policy for Efficient and Versatile Motion Control of Diverse Legged Robots
  2. 2025Learning Soft Robotic Dynamics with Active Exploration
  3. 2025APEX: Action Priors Enable Efficient Exploration for Robust Motion Tracking on Legged Robots ↗
  4. 2024Latent Action Priors for Locomotion with Deep Reinforcement Learning
  5. 2024Reinforcement Learning Controllers for Soft Robots using Learned Environments
  6. 2025Surrogate compliance modeling enables reinforcement learned locomotion gaits for soft robots ↗
  7. 2024Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control
  8. 2025Whole-Body Constrained Learning for Legged Locomotion via Hierarchical Optimization