ParkDiffusion++: Ego Intention Conditioned Joint Multi-Agent Trajectory Prediction for Automated Parking using Diffusion Models

TL;DR

ParkDiffusion++ is a novel diffusion-based model that jointly predicts ego intentions and multi-agent trajectories for automated parking, enabling more accurate and safe decision-making in complex driving scenarios.

Contribution

It introduces an ego intention tokenizer, ego-conditioned joint prediction, safety-guided denoising, and counterfactual knowledge distillation, advancing multi-agent trajectory prediction methods.

Findings

Achieves state-of-the-art results on DLP and inD datasets.

Provides qualitatively plausible what-if scenarios showing agent reactions.

Improves prediction accuracy and safety in automated parking.

Abstract

Automated parking is a challenging operational domain for advanced driver assistance systems, requiring robust scene understanding and interaction reasoning. The key challenge is twofold: (i) predict multiple plausible ego intentions according to context and (ii) for each intention, predict the joint responses of surrounding agents, enabling effective what-if decision-making. However, existing methods often fall short, typically treating these interdependent problems in isolation. We propose ParkDiffusion++, which jointly learns a multi-modal ego intention predictor and an ego-conditioned multi-agent joint trajectory predictor for automated parking. Our approach makes several key contributions. First, we introduce an ego intention tokenizer that predicts a small set of discrete endpoint intentions from agent histories and vectorized map polylines. Second, we perform ego-intention-conditioned joint prediction, yielding socially consistent predictions of the surrounding agents for each possible ego intention. Third, we employ a lightweight safety-guided denoiser with different constraints to refine joint scenes during training, thus improving accuracy and safety. Fourth, we propose counterfactual knowledge distillation, where an EMA teacher refined by a frozen safety-guided denoiser provides pseudo-targets that capture how agents react to alternative ego intentions. Extensive evaluations demonstrate that ParkDiffusion++ achieves state-of-the-art performance on the Dragon Lake Parking (DLP) dataset and the Intersections Drone (inD) dataset. Importantly, qualitative what-if visualizations show that other agents react appropriately to different ego intentions.