CAR: Cross-Vehicle Kinodynamics Adaptation via Mobility Representation

2026-03-06

AI Summary

Existing methods for transferring complex motion dynamics models across heterogeneous unmanned vehicles struggle to generalize effectively due to reliance on platform-specific data or oversimplified assumptions. This work proposes the CAR framework, which enables cross-platform dynamics knowledge transfer through a shared motion representation for the first time. By leveraging a Transformer encoder with adaptive layer normalization, CAR constructs a unified latent space that allows rapid adaptation to a new platform using only one minute of trajectory data. Evaluated on four heterogeneous platforms in the Verti-Bench benchmark, the approach—combined with multi-physics engine simulation (Chrono) and nearest-neighbor latent space matching—achieves up to a 67.2% reduction in prediction error. These results demonstrate significant savings in both data and computational costs while validating the method’s effectiveness in both simulated and real-world scenarios.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Computer Vision: Motion & Tracking
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Developing autonomous off-road mobility typically requires either extensive, platform-specific data collection or relies on simplified abstractions, such as unicycle or bicycle models, that fail to capture the complex kinodynamics of diverse platforms, ranging from wheeled to tracked vehicles. This limitation hinders scalability across evolving heterogeneous autonomous robot fleets. To address this challenge, we propose Cross-vehicle kinodynamics Adaptation via mobility Representation (CAR), a novel framework that enables rapid mobility transfer to new vehicles. CAR employs a Transformer encoder with Adaptive Layer Normalization to embed vehicle trajectory transitions and physical configurations into a shared mobility latent space. By identifying and extracting commonality from nearest neighbors within this latent space, our approach enables rapid kinodynamics adaptation to novel platforms with minimal data collection and computational overhead. 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. With only one minute of new trajectory data, CAR achieves up to 67.2% reduction in prediction error compared to direct neighbor transfer across diverse unseen vehicle configurations, demonstrating the effectiveness of cross-vehicle mobility knowledge transfer in both simulated and real-world environments.

Problem

• cross-vehicle adaptation
• kinodynamics
• off-road mobility
• heterogeneous robot fleets
• mobility transfer

Innovation

• Cross-vehicle adaptation
• Mobility representation
• Transformer encoder
• Kinodynamics modeling
• Autonomous off-road mobility