VertiAdaptor: Online Kinodynamics Adaptation for Vertically Challenging Terrain

• URL: http://arxiv.org/abs/2603.06887v1
• Date: Fri, 06 Mar 2026 21:08:19 GMT
• Title: VertiAdaptor: Online Kinodynamics Adaptation for Vertically Challenging Terrain
• Abstract summary: VertiAdaptor (VA) is an online adaptation framework for terrain-aware kinodynamic modeling and planning.<n>VA learns a kinodynamic space spanned by a set of neural ordinary differential equation basis functions, capturing complex vehicle-terrain interactions.<n>VA improves prediction accuracy by up to 23.9% and achieves a 5X faster adaptation time.
• Score: 12.6823418300363
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autonomous driving in off-road environments presents significant challenges due to the dynamic and unpredictable nature of unstructured terrain. Traditional kinodynamic models often struggle to generalize across diverse geometric and semantic terrain types, underscoring the need for real-time adaptation to ensure safe and reliable navigation. We propose VertiAdaptor (VA), a novel online adaptation framework that efficiently integrates elevation with semantic embeddings to enable terrain-aware kinodynamic modeling and planning via function encoders. VA learns a kinodynamic space spanned by a set of neural ordinary differential equation basis functions, capturing complex vehicle-terrain interactions across varied environments. After offline training, the proposed approach can rapidly adapt to new, unseen environments by identifying kinodynamics in the learned space through a computationally efficient least-squares calculation. We evaluate VA within the Verti-Bench simulator, built on the Chrono multi-physics engine, and validate its performance both in simulation and on a physical Verti-4-Wheeler platform. Our results demonstrate that VA improves prediction accuracy by up to 23.9% and achieves a 5X faster adaptation time, advancing the robustness and reliability of autonomous robots in complex and evolving off-road environments.

Related papers

• VertiAKD: Adaptive Off-Road Kinodynamics on Vertically Challenging Terrain [11.894870991511567]
  VertiAKD is a unified framework for transferring and adapting off-road kinodynamic knowledge across diverse vehicles.<n>We demonstrate VertiAKD in the Verti-Bench simulator, built on the Chrono multi-physics engine, and on five physical configurations of the Verti-4-Wheeler platform.
  arXiv  Detail & Related papers  (2026-08-02T02:55:08Z)
• Learning Context-Aware Neural ODE Dynamics for Adaptive Robotic Control [55.01272784312405]
  We propose a context-aware dynamics model based on neural ordinary differential equations.<n>We validate the approach across diverse robotic platforms, including a quadrotor in simulation, as well as a Sphero BOLT robot and a Fanuc manipulator in real-world experiments.
  arXiv  Detail & Related papers  (2026-06-13T20:55:46Z)
• Physics-Informed Reinforcement Learning of Spatial Density Velocity Potentials for Map-Free Racing [73.88859384645264]
  Out-Of-Distribution (OOD) generalization to various racetracks utilizes Machine Learning (ML) to encode the mathematical relation between sensor data and vehicle actuation for end-to-end control.<n>This paper presents a DRL method that parameterizes nonlinear vehicle dynamics from the spectral distribution of depth measurements with a non-geometric, physics-informed reward, to infer vehicle time-optimal and overtaking racing controls with an Artificial Neural Network (ANN)<n>The policy outperforms human demonstrations by 12% in OOD tracks on proportionally scaled hardware, by maximizing the friction circle with tire dynamics that resemble an empirical Pacejka tire model.
  arXiv  Detail & Related papers  (2026-04-10T17:12:07Z)
• CAR: Cross-Vehicle Kinodynamics Adaptation via Mobility Representation [12.994292036520681]
  Cross-vehicle kinodynamics Adaptation via mobility Representation (CAR) is a novel framework that enables rapid mobility transfer to new vehicles.<n>We evaluate CAR using the Verti-Bench simulator, built on the Chrono multi-physics engine, and validate its performance on four distinct physical configurations of the Verti-4-Wheeler platform.
  arXiv  Detail & Related papers  (2026-03-06T20:34:55Z)
• MetAdv: A Unified and Interactive Adversarial Testing Platform for Autonomous Driving [85.04826012938642]
  MetAdv is a novel adversarial testing platform that enables realistic, dynamic, and interactive evaluation.<n>It supports flexible 3D vehicle modeling and seamless transitions between simulated and physical environments.<n>It enables real-time capture of physiological signals and behavioral feedback from drivers.
  arXiv  Detail & Related papers  (2025-08-04T03:07:54Z)
• Meta-Learning Online Dynamics Model Adaptation in Off-Road Autonomous Driving [9.515695438588855]
  High-speed off-road autonomous driving presents unique challenges due to complex, evolving terrain characteristics.<n>We propose a novel framework that combines a Kalman filter-based online adaptation scheme with meta-learned parameters to address these challenges.<n>Our results underscore the effectiveness of meta-learned dynamics model adaptation, advancing the development of reliable autonomous systems.
  arXiv  Detail & Related papers  (2025-04-23T17:51:36Z)
• Monte Carlo Tree Search with Velocity Obstacles for safe and efficient motion planning in dynamic environments [49.30744329170107]
  We propose a novel approach for optimal online motion planning with minimal information about dynamic obstacles.<n>The proposed methodology combines Monte Carlo Tree Search (MCTS), for online optimal planning via model simulations, with Velocity Obstacles (VO), for obstacle avoidance.<n>We show the superiority of our methodology with respect to state-of-the-art planners, including Non-linear Model Predictive Control (NMPC), in terms of improved collision rate, computational and task performance.
  arXiv  Detail & Related papers  (2025-01-16T16:45:08Z)
• EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision [85.17951804790515]
  EmerNeRF is a simple yet powerful approach for learning spatial-temporal representations of dynamic driving scenes. It simultaneously captures scene geometry, appearance, motion, and semantics via self-bootstrapping. Our method achieves state-of-the-art performance in sensor simulation.
  arXiv  Detail & Related papers  (2023-11-03T17:59:55Z)
• Online Calibration of a Single-Track Ground Vehicle Dynamics Model by Tight Fusion with Visual-Inertial Odometry [8.165828311550152]
  We present ST-VIO, a novel approach which tightly fuses a single-track dynamics model for wheeled ground vehicles with visual inertial odometry (VIO) Our method calibrates and adapts the dynamics model online to improve the accuracy of forward prediction conditioned on future control inputs.
  arXiv  Detail & Related papers  (2023-09-20T08:50:30Z)
• Gradient-Based Trajectory Optimization With Learned Dynamics [80.41791191022139]
  We use machine learning techniques to learn a differentiable dynamics model of the system from data. We show that a neural network can model highly nonlinear behaviors accurately for large time horizons. In our hardware experiments, we demonstrate that our learned model can represent complex dynamics for both the Spot and Radio-controlled (RC) car.
  arXiv  Detail & Related papers  (2022-04-09T22:07:34Z)
• Online Domain Adaptation for Occupancy Mapping [28.081328051535618]
  We propose a theoretical framework building upon the theory of optimal transport to adapt model parameters to account for changes in the environment. With the use of high-fidelity driving simulators and real-world datasets, we demonstrate how parameters of 2D and 3D occupancy maps can be automatically adapted to accord with local spatial changes.
  arXiv  Detail & Related papers  (2020-07-01T00:46:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.