DECODE: Domain-aware Continual Domain Expansion for Motion Prediction

TL;DR

DECODE is a continual learning framework for motion prediction in autonomous vehicles that balances specialization and generalization, enabling efficient adaptation to diverse driving scenarios with minimal forgetting.

Contribution

The paper introduces DECODE, a novel continual learning approach that uses hypernetworks and Bayesian techniques to adapt motion prediction models across domains while reducing storage and maintaining robustness.

Findings

Achieves a low forgetting rate of 0.044.

Surpasses traditional strategies in average minADE of 0.584 m.

Effectively adapts across diverse driving conditions.

Abstract

Motion prediction is critical for autonomous vehicles to effectively navigate complex environments and accurately anticipate the behaviors of other traffic participants. As autonomous driving continues to evolve, the need to assimilate new and varied driving scenarios necessitates frequent model updates through retraining. To address these demands, we introduce DECODE, a novel continual learning framework that begins with a pre-trained generalized model and incrementally develops specialized models for distinct domains. Unlike existing continual learning approaches that attempt to develop a unified model capable of generalizing across diverse scenarios, DECODE uniquely balances specialization with generalization, dynamically adjusting to real-time demands. The proposed framework leverages a hypernetwork to generate model parameters, significantly reducing storage requirements, and incorporates a normalizing flow mechanism for real-time model selection based on likelihood estimation. Furthermore, DECODE merges outputs from the most relevant specialized and generalized models using deep Bayesian uncertainty estimation techniques. This integration ensures optimal performance in familiar conditions while maintaining robustness in unfamiliar scenarios. Extensive evaluations confirm the effectiveness of the framework, achieving a notably low forgetting rate of 0.044 and an average minADE of 0.584 m, significantly surpassing traditional learning strategies and demonstrating adaptability across a wide range of driving conditions.