# ParkDiffusion: Heterogeneous Multi-Agent Multi-Modal Trajectory Prediction for Automated Parking using Diffusion Models

arXiv: https://arxiv.org/abs/2505.00586 · HTML: https://mlsanity.com/paper/2505.00586/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 1 May 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 23 of 23)

- [MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Prediction](https://mlsanity.com/paper/2111.14973/) (2021)
- [MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusion](https://mlsanity.com/paper/2306.03083/) (2023)
- [The inD Dataset: A Drone Dataset of Naturalistic Road User Trajectories at German Intersections](https://mlsanity.com/paper/1911.07602/) (2019)
- [Leapfrog Diffusion Model for Stochastic Trajectory Prediction](https://mlsanity.com/paper/2303.10895/) (2023)
- [TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents](https://mlsanity.com/paper/1811.02146/) (2018)
- [TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted Interactions](https://mlsanity.com/paper/1812.04767/) (2018)
- [ControlTraj: Controllable Trajectory Generation with Topology-Constrained Diffusion Model](https://mlsanity.com/paper/2404.15380/) (2024)
- [SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2310.05370/) (2023)
- [SIMPL: A Simple and Efficient Multi-agent Motion Prediction Baseline for Autonomous Driving](https://mlsanity.com/paper/2402.02519/) (2024)
- [DICE: Diverse Diffusion Model with Scoring for Trajectory Prediction](https://mlsanity.com/paper/2310.14570/) (2023)
- [ParkingE2E: Camera-based End-to-end Parking Network, from Images to Planning](https://mlsanity.com/paper/2408.02061/) (2024)
- [ParkPredict+: Multimodal Intent and Motion Prediction for Vehicles in Parking Lots with CNN and Transformer](https://mlsanity.com/paper/2204.10777/) (2022)
- [Diffusion-Based Environment-Aware Trajectory Prediction](https://mlsanity.com/paper/2403.11643/) (2024)
- [Multimodal Interaction-aware Motion Prediction for Autonomous Street Crossing](https://mlsanity.com/paper/1808.06887/) (2018)
- [Heterogeneous Trajectory Forecasting via Risk and Scene Graph Learning](https://mlsanity.com/paper/2211.00848/) (2022)
- [Intention-aware Denoising Diffusion Model for Trajectory Prediction](https://mlsanity.com/paper/2403.09190/) (2024)
- [ParkPredict: Motion and Intent Prediction of Vehicles in Parking Lots](https://mlsanity.com/paper/2004.10293/) (2020)
- [Autonomous Vehicle Parking in Dynamic Environments: An Integrated System with Prediction and Motion Planning](https://mlsanity.com/paper/2204.10383/) (2022)
- [Heterogeneous Graph-based Trajectory Prediction using Local Map Context and Social Interactions](https://mlsanity.com/paper/2311.18553/) (2023)
- [Motion Forecasting via Model-Based Risk Minimization](https://mlsanity.com/paper/2409.10585/) (2024)
- [AVM-SLAM: Semantic Visual SLAM with Multi-Sensor Fusion in a Bird's Eye View for Automated Valet Parking](https://mlsanity.com/paper/2309.08180/) (2023)
- [LESS-Map: Lightweight and Evolving Semantic Map in Parking Lots for Long-term Self-Localization](https://mlsanity.com/paper/2310.07390/) (2023)
- [Speeding Up Path Planning via Reinforcement Learning in MCTS for Automated Parking](https://mlsanity.com/paper/2403.17234/) (2024)

## Built on by (most cited first, 5 of 5)

- [ParkDiffusion++: Ego Intention Conditioned Joint Multi-Agent Trajectory Prediction for Automated Parking using Diffusion Models](https://mlsanity.com/paper/2602.20923/) (2026)
- [LAD-Drive: Bridging Language and Trajectory with Action-Aware Diffusion Transformers](https://mlsanity.com/paper/2603.02035/) (2026)
- [Sparse3DTrack: Monocular 3D Object Tracking Using Sparse Supervision](https://mlsanity.com/paper/2603.18298/) (2026)
- [Class-Incremental Motion Forecasting](https://mlsanity.com/paper/2603.09420/) (2026)
- [A Pedestrian-Vehicle Interaction Benchmark and Annotation Framework for Unstructured Scenes via Uncalibrated Cameras](https://mlsanity.com/paper/2605.25947/) (2026)

## Abstract (arXiv)

Automated parking is a critical feature of Advanced Driver Assistance Systems (ADAS), where accurate trajectory prediction is essential to bridge perception and planning modules. Despite its significance, research in this domain remains relatively limited, with most existing studies concentrating on single-modal trajectory prediction of vehicles. In this work, we propose ParkDiffusion, a novel approach that predicts the trajectories of both vehicles and pedestrians in automated parking scenarios. ParkDiffusion employs diffusion models to capture the inherent uncertainty and multi-modality of future trajectories, incorporating several key innovations. First, we propose a dual map encoder that processes soft semantic cues and hard geometric constraints using a two-step cross-attention mechanism. Second, we introduce an adaptive agent type embedding module, which dynamically conditions the prediction process on the distinct characteristics of vehicles and pedestrians. Third, to ensure kinematic feasibility, our model outputs control signals that are subsequently used within a kinematic framework to generate physically feasible trajectories. We evaluate ParkDiffusion on the Dragon Lake Parking (DLP) dataset and the Intersections Drone (inD) dataset. Our work establishes a new baseline for heterogeneous trajectory prediction in parking scenarios, outperforming existing methods by a considerable margin.