# Learned Perceptive Forward Dynamics Model for Safe and Platform-aware Robotic Navigation

arXiv: https://arxiv.org/abs/2504.19322 · HTML: https://mlsanity.com/paper/2504.19322/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2025.

## Built on by (most cited first, 11 of 11)

- [RELIC: Interactive Video World Model with Long-Horizon Memory](https://mlsanity.com/paper/2512.04040/) (2025)
- [VAMOS: A Hierarchical Vision-Language-Action Model for Capability-Modulated and Steerable Navigation](https://mlsanity.com/paper/2510.20818/) (2025)
- [Ego-Vision World Model for Humanoid Contact Planning](https://mlsanity.com/paper/2510.11682/) (2025)
- [World-Action Models for Robot Learning and Control: A Survey](https://mlsanity.com/paper/2609.16074/) (2026)
- [MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning](https://mlsanity.com/paper/2510.03142/) (2025)
- [Comparison of neural network training strategies for the simulation of dynamical systems](https://mlsanity.com/paper/2512.03851/) (2025)
- [Efficient Coordination with the System-Level Shared State: An Embodied-AI Native Modular Framework](https://mlsanity.com/paper/2601.13945/) (2026)
- [RAY-TOLD: Ray-Based Latent Dynamics for Dense Dynamic Obstacle Avoidance with TDMPC](https://mlsanity.com/paper/2604.27450/) (2026)
- [GUIDE: Goal-Initialized Directional Understanding for End-to-End Legged Navigation](https://mlsanity.com/paper/2606.10832/) (2026)
- [Feeling Terrain Before Crossing: World Models for Off-Road Navigation](https://mlsanity.com/paper/2609.19863/) (2026)
- [From Language Priors to Field Adaptation: Preference Learning for Traversability Estimation](https://mlsanity.com/paper/2610.02974/) (2026)

## Abstract (arXiv)

Ensuring safe navigation in complex environments requires accurate real-time traversability assessment and understanding of environmental interactions relative to the robot`s capabilities. Traditional methods, which assume simplified dynamics, often require designing and tuning cost functions to safely guide paths or actions toward the goal. This process is tedious, environment-dependent, and not generalizable. To overcome these issues, we propose a novel learned perceptive Forward Dynamics Model (FDM) that predicts the robot`s future state conditioned on the surrounding geometry and history of proprioceptive measurements, proposing a more scalable, safer, and heuristic-free solution. The FDM is trained on multiple years of simulated navigation experience, including high-risk maneuvers, and real-world interactions to incorporate the full system dynamics beyond rigid body simulation. We integrate our perceptive FDM into a zero-shot Model Predictive Path Integral (MPPI) planning framework, leveraging the learned mapping between actions, future states, and failure probability. This allows for optimizing a simplified cost function, eliminating the need for extensive cost-tuning to ensure safety. On the legged robot ANYmal, the proposed perceptive FDM improves the position estimation by on average 41% over competitive baselines, which translates into a 27% higher navigation success rate in rough simulation environments. Moreover, we demonstrate effective sim-to-real transfer and showcase the benefit of training on synthetic and real data. Code and models are made publicly available under https://github.com/leggedrobotics/fdm.