CARPAL: Confidence-Aware Intent Recognition for Parallel Autonomy

TL;DR

CARPAL introduces a confidence-aware neural network for driver intent recognition that predicts trajectories and utility statistics, enhancing decision-making safety in autonomous driving systems.

Contribution

It presents a novel multi-task neural network that jointly predicts driver trajectories and utility statistics, improving downstream decision safety in parallel autonomy.

Findings

Outperforms baseline methods in recall and fall-out metrics.

Enhances safety through better intervention and warning capabilities.

Robust to uncertainties in downstream planning tasks.

Abstract

Predicting driver intentions is a difficult and crucial task for advanced driver assistance systems. Traditional confidence measures on predictions often ignore the way predicted trajectories affect downstream decisions for safe driving. In this paper, we propose a novel multi-task intent recognition neural network that predicts not only probabilistic driver trajectories, but also utility statistics associated with the predictions for a given downstream task. We establish a decision criterion for parallel autonomy that takes into account the role of driver trajectory prediction in real-time decision making by reasoning about estimated task-specific utility statistics. We further improve the robustness of our system by considering uncertainties in downstream planning tasks that may lead to unsafe decisions. We test our online system on a realistic urban driving dataset, and demonstrate its advantage in terms of recall and fall-out metrics compared to baseline methods, and demonstrate its effectiveness in intervention and warning use cases.