# Learning Inverse Kinodynamics for Accurate High-Speed Off-Road Navigation on Unstructured Terrain

arXiv: https://arxiv.org/abs/2102.12667 · HTML: https://mlsanity.com/paper/2102.12667/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Feb 2021.

## Built on by (most cited first, 25 of 25)

- [Autonomous Vehicles on the Edge: A Survey on Autonomous Vehicle Racing](https://mlsanity.com/paper/2202.07008/) (2022)
- [Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation](https://mlsanity.com/paper/2209.10780/) (2022)
- [RoadRunner -- Learning Traversability Estimation for Autonomous Off-road Driving](https://mlsanity.com/paper/2402.19341/) (2024)
- [VI-IKD: High-Speed Accurate Off-Road Navigation using Learned Visual-Inertial Inverse Kinodynamics](https://mlsanity.com/paper/2203.15983/) (2022)
- [DTG : Diffusion-based Trajectory Generation for Mapless Global Navigation](https://mlsanity.com/paper/2403.09900/) (2024)
- [High-Speed Accurate Robot Control using Learned Forward Kinodynamics and Non-linear Least Squares Optimization](https://mlsanity.com/paper/2206.08487/) (2022)
- [Learning to See Physical Properties with Active Sensing Motor Policies](https://mlsanity.com/paper/2311.01405/) (2023)
- [Learning Terrain-Aware Kinodynamic Model for Autonomous Off-Road Rally Driving With Model Predictive Path Integral Control](https://mlsanity.com/paper/2305.00676/) (2023)
- [Wait, That Feels Familiar: Learning to Extrapolate Human Preferences for Preference Aligned Path Planning](https://mlsanity.com/paper/2309.09912/) (2023)
- [Reinforcement Learning for Wheeled Mobility on Vertically Challenging Terrain](https://mlsanity.com/paper/2409.02383/) (2024)
- [Adaptive Diffusion Terrain Generator for Autonomous Uneven Terrain Navigation](https://mlsanity.com/paper/2410.10766/) (2024)
- [VANP: Learning Where to See for Navigation with Self-Supervised Vision-Action Pre-Training](https://mlsanity.com/paper/2403.08109/) (2024)
- [Grounded Curriculum Learning](https://mlsanity.com/paper/2409.19816/) (2024)
- [A Study on Learning Social Robot Navigation with Multimodal Perception](https://mlsanity.com/paper/2309.12568/) (2023)
- [VertiSelector: Automatic Curriculum Learning for Wheeled Mobility on Vertically Challenging Terrain](https://mlsanity.com/paper/2409.17469/) (2024)
- [GACL: Grounded Adaptive Curriculum Learning with Active Task and Performance Monitoring](https://mlsanity.com/paper/2508.02988/) (2025)
- [STEADY: Simultaneous State Estimation and Dynamics Learning from Indirect Observations](https://mlsanity.com/paper/2203.01299/) (2022)
- [T-CBF: Traversability-based Control Barrier Function to Navigate Vertically Challenging Terrain](https://mlsanity.com/paper/2503.06083/) (2025)
- [Visual Heading Prediction for Autonomous Aerial Vehicles](https://mlsanity.com/paper/2512.09898/) (2025)
- [Context-Conditional Navigation with a Learning-Based Terrain- and Robot-Aware Dynamics Model](https://mlsanity.com/paper/2307.09206/) (2023)
- [Dyna-LfLH: Learning Agile Navigation in Dynamic Environments from Learned Hallucination](https://mlsanity.com/paper/2403.17231/) (2024)
- [Learning a Terrain- and Robot-Aware Dynamics Model for Autonomous Mobile Robot Navigation](https://mlsanity.com/paper/2409.11452/) (2024)
- [Learning Inverse Kinodynamics for Autonomous Vehicle Drifting](https://mlsanity.com/paper/2402.14928/) (2024)
- [ADEPT: Adaptive Diffusion Environment for Policy Transfer Sim-to-Real](https://mlsanity.com/paper/2506.01759/) (2025)
- [Adapting Generalist Vehicle Models for High-Speed MPC Across Terrains](https://mlsanity.com/paper/2607.13319/) (2026)

## Abstract (arXiv)

This paper presents a learning-based approach to consider the effect of unobservable world states in kinodynamic motion planning in order to enable accurate high-speed off-road navigation on unstructured terrain. Existing kinodynamic motion planners either operate in structured and homogeneous environments and thus do not need to explicitly account for terrain-vehicle interaction, or assume a set of discrete terrain classes. However, when operating on unstructured terrain, especially at high speeds, even small variations in the environment will be magnified and cause inaccurate plan execution. In this paper, to capture the complex kinodynamic model and mathematically unknown world state, we learn a kinodynamic planner in a data-driven manner with onboard inertial observations. Our approach is tested on a physical robot in different indoor and outdoor environments, enables fast and accurate off-road navigation, and outperforms environment-independent alternatives, demonstrating 52.4% to 86.9% improvement in terms of plan execution success rate while traveling at high speeds.