From Prediction to Planning With Goal Conditioned Lane Graph Traversals

TL;DR

This paper introduces a goal-conditioned approach that transforms motion prediction models into goal-directed planners for automated driving, improving interpretability and performance.

Contribution

It proposes a novel goal-conditioning method that leverages existing prediction models for planning, enhancing interpretability and effectiveness.

Findings

Outperforms other goal-conditioning methods in benchmarks

Increases model interpretability

Shows promising results on large open-source datasets

Abstract

The field of motion prediction for automated driving has seen tremendous progress recently, bearing ever-more mighty neural network architectures. Leveraging these powerful models bears great potential for the closely related planning task. In this letter we propose a novel goal-conditioning method and show its potential to transform a state-of-the-art prediction model into a goal-directed planner. Our key insight is that conditioning prediction on a navigation goal at the behaviour level outperforms other widely adopted methods, with the additional benefit of increased model interpretability. We train our model on a large open-source dataset and show promising performance in a comprehensive benchmark.