Expanding the Deployment Envelope of Behavior Prediction via Adaptive Meta-Learning

TL;DR

This paper introduces a meta-learning-based method that enhances behavior prediction models, enabling efficient adaptation to new environments for autonomous systems, thereby facilitating broader deployment across diverse geographic regions.

Contribution

The paper presents a novel meta-learning approach using Bayesian regression to adapt behavior prediction models to new domains with minimal data and fine-tuning.

Findings

Effective domain transfer demonstrated across multiple real-world datasets

Significant improvement in prediction accuracy in unseen environments

Adaptation can be achieved via offline fine-tuning or online methods

Abstract

Learning-based behavior prediction methods are increasingly being deployed in real-world autonomous systems, e.g., in fleets of self-driving vehicles, which are beginning to commercially operate in major cities across the world. Despite their advancements, however, the vast majority of prediction systems are specialized to a set of well-explored geographic regions or operational design domains, complicating deployment to additional cities, countries, or continents. Towards this end, we present a novel method for efficiently adapting behavior prediction models to new environments. Our approach leverages recent advances in meta-learning, specifically Bayesian regression, to augment existing behavior prediction models with an adaptive layer that enables efficient domain transfer via offline fine-tuning, online adaptation, or both. Experiments across multiple real-world datasets demonstrate that our method can efficiently adapt to a variety of unseen environments.