SPLIT: Sparse Incremental Learning of Error Dynamics for Control-Oriented Modeling in Autonomous Vehicles

TL;DR

SPLIT introduces a sparse incremental learning framework for vehicle dynamics modeling that enhances accuracy, efficiency, and adaptability in real-time autonomous vehicle control through model decomposition, local learning, and GP sparsification.

Contribution

The paper presents a novel SPLIT framework combining model decomposition, local incremental learning, and GP sparsification for scalable, adaptive vehicle modeling.

Findings

Improves model accuracy and control performance online.

Enables rapid adaptation to vehicle dynamics deviations.

Demonstrates robust generalization to unseen scenarios.

Abstract

Accurate, computationally efficient, and adaptive vehicle models are essential for autonomous vehicle control. Hybrid models that combine a nominal model with a Gaussian Process (GP)-based residual model have emerged as a promising approach. However, the GP-based residual model suffers from the curse of dimensionality, high evaluation complexity, and the inefficiency of online learning, which impede the deployment in real-time vehicle controllers. To address these challenges, we propose SPLIT, a sparse incremental learning framework for control-oriented vehicle dynamics modeling. SPLIT integrates three key innovations: (i) Model Decomposition. We decompose the vehicle model into invariant elements calibrated by experiments, and variant elements compensated by the residual model to reduce feature dimensionality. (ii) Local Incremental Learning. We define the valid region in the feature space and partition it into subregions, enabling efficient online learning from streaming data. (iii) GP Sparsification. We use bayesian committee machine to ensure scalable online evaluation. Integrated into model-based controllers, SPLIT is evaluated in aggressive simulations and real-vehicle experiments. Results demonstrate that SPLIT improves model accuracy and control performance online. Moreover, it enables rapid adaptation to vehicle dynamics deviations and exhibits robust generalization to previously unseen scenarios.