VertiAKD: Adaptive Off-Road Kinodynamics on Vertically Challenging Terrain

2026-08-01

AI Summary

This work addresses the lack of a general, efficient, and minimally retrainable approach for modeling vehicle dynamics across diverse off-road terrains and vehicle configurations. To this end, the authors propose VertiAKD, a framework that fuses vehicle configuration, trajectory transition, and local elevation with semantic terrain features to learn a shared mobility representation, enabling cross-vehicle and cross-terrain knowledge transfer and online adaptation. Notably, VertiAKD achieves zero-gradient online adaptation on geometrically and semantically complex terrain, requiring only one minute of new data for model initialization and continuous refinement. Evaluated on the Chrono-based Verti-Bench simulation environment across five distinct physical vehicle configurations, the method reduces long-horizon prediction error by up to 34.52% compared to direct transfer baselines and improves performance by as much as 94.43%, demonstrating robust closed-loop trajectory tracking in both simulation and real-world experiments.

Abstract

Off-road mobility requires autonomous mobile robots to generalize across heterogeneous vehicle fleets and continuously changing terrain conditions. Existing cross-vehicle adaptation approaches generally assume flat terrain, while terrain-aware kinodynamic models often require platform-specific data collection and retraining. To this end, we propose VertiAKD, a unified framework for transferring and adapting off-road kinodynamic knowledge across diverse vehicles on geometrically and semantically complex terrain simultaneously. VertiAKD learns a shared mobility representation that jointly encodes vehicle configurations, trajectory transitions, and local elevation and semantic terrain features. Given limited data from a novel vehicle operating on unseen terrain, VertiAKD identifies the most relevant mobility descriptors and transfers their knowledge to initialize a terrain-aware kinodynamic model via function encoders, which is then periodically refined online from streaming observations without gradient-based retraining. We evaluate VertiAKD in the Verti-Bench simulator, built on the Chrono multi-physics engine, and on five physical configurations of the Verti-4-Wheeler platform. With only one minute of new trajectory data and associated terrain features, VertiAKD reduces long-horizon prediction error by up to 34.52% over direct mobility descriptor transfer across diverse unseen vehicle configurations and 94.43% over competing baselines. We further demonstrate robust closed-loop trajectory tracking in both simulation and physical experiments, highlighting the effectiveness of terrain-aware cross-vehicle knowledge transfer for accurate modeling and reliable off-road navigation.

Problem

• off-road mobility
• cross-vehicle adaptation
• kinodynamic modeling
• terrain-aware navigation
• knowledge transfer

Innovation

• cross-vehicle adaptation
• terrain-aware kinodynamics
• shared mobility representation
• function encoder
• online refinement