FJMP: Factorized Joint Multi-Agent Motion Prediction over Learned Directed Acyclic Interaction Graphs

• URL: http://arxiv.org/abs/2211.16197v2
• Date: Wed, 5 Apr 2023 00:23:12 GMT
• Title: FJMP: Factorized Joint Multi-Agent Motion Prediction over Learned Directed Acyclic Interaction Graphs
• Authors: Luke Rowe, Martin Ethier, Eli-Henry Dykhne, Krzysztof Czarnecki
• Abstract summary: We propose FJMP, a Factorized Joint Motion Prediction framework for interactive driving scenarios. FJMP produces more accurate and scene-consistent joint trajectory predictions than non-factorized approaches. FJMP ranks 1st on the multi-agent test leaderboard of the INTERACTION dataset.
• Score: 8.63314005149641
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Predicting the future motion of road agents is a critical task in an autonomous driving pipeline. In this work, we address the problem of generating a set of scene-level, or joint, future trajectory predictions in multi-agent driving scenarios. To this end, we propose FJMP, a Factorized Joint Motion Prediction framework for multi-agent interactive driving scenarios. FJMP models the future scene interaction dynamics as a sparse directed interaction graph, where edges denote explicit interactions between agents. We then prune the graph into a directed acyclic graph (DAG) and decompose the joint prediction task into a sequence of marginal and conditional predictions according to the partial ordering of the DAG, where joint future trajectories are decoded using a directed acyclic graph neural network (DAGNN). We conduct experiments on the INTERACTION and Argoverse 2 datasets and demonstrate that FJMP produces more accurate and scene-consistent joint trajectory predictions than non-factorized approaches, especially on the most interactive and kinematically interesting agents. FJMP ranks 1st on the multi-agent test leaderboard of the INTERACTION dataset.

Related papers

• FIMP: Future Interaction Modeling for Multi-Agent Motion Prediction [18.10147252674138]
  We propose Future Interaction modeling for Motion Prediction (FIMP), which captures potential future interactions in an end-to-end manner. Experiments show that our future interaction modeling improves the performance remarkably, leading to superior performance on the Argoverse motion forecasting benchmark.
  arXiv  Detail & Related papers  (2024-01-29T14:41:55Z)
• FFINet: Future Feedback Interaction Network for Motion Forecasting [46.247396728154904]
  We propose a novel Future Feedback Interaction Network (FFINet) to aggregate features the current observations and potential future interactions for trajectory prediction. Our FFINet achieves the state-of-the-art performance on Argoverse 1 and Argoverse 2 motion forecasting benchmarks.
  arXiv  Detail & Related papers  (2023-11-08T07:57:29Z)
• BiFF: Bi-level Future Fusion with Polyline-based Coordinate for Interactive Trajectory Prediction [23.895217477379653]
  We propose Bi-level Future Fusion (BiFF) to capture future interactions between interactive agents. Concretely, BiFF fuses the high-level future intentions followed by low-level future behaviors. BiFF achieves state-of-the-art performance on the interactive prediction benchmark of Open Motion dataset.
  arXiv  Detail & Related papers  (2023-06-25T08:11:43Z)
• EPG-MGCN: Ego-Planning Guided Multi-Graph Convolutional Network for Heterogeneous Agent Trajectory Prediction [0.0]
  This paper proposes a ego-planning guided multi-graph convolutional network (EPG-MGCN) to predict the trajectories of heterogeneous agents. EPG-MGCN first models the social interactions by employing four graph topologies. Finally, a category-specific gated recurrent unit (CS-GRU) encoder-decoder is designed to generate future trajectories for each specific type of agents.
  arXiv  Detail & Related papers  (2023-03-29T21:14:05Z)
• A Hierarchical Hybrid Learning Framework for Multi-agent Trajectory Prediction [4.181632607997678]
  We propose a hierarchical hybrid framework of deep learning (DL) and reinforcement learning (RL) for multi-agent trajectory prediction. In the DL stage, the traffic scene is divided into multiple intermediate-scale heterogenous graphs based on which Transformer-style GNNs are adopted to encode heterogenous interactions. In the RL stage, we divide the traffic scene into local sub-scenes utilizing the key future points predicted in the DL stage.
  arXiv  Detail & Related papers  (2023-03-22T02:47:42Z)
• JFP: Joint Future Prediction with Interactive Multi-Agent Modeling for Autonomous Driving [12.460224193998362]
  We propose an end-to-end trainable model that learns directly the interaction between pairs of agents in a structured, graphical model formulation. Our approach improves significantly on the trajectory overlap metrics while obtaining on-par or better performance on single-agent trajectory metrics.
  arXiv  Detail & Related papers  (2022-12-16T20:59:21Z)
• Deep Interactive Motion Prediction and Planning: Playing Games with Motion Prediction Models [162.21629604674388]
  This work presents a game-theoretic Model Predictive Controller (MPC) that uses a novel interactive multi-agent neural network policy as part of its predictive model. Fundamental to the success of our method is the design of a novel multi-agent policy network that can steer a vehicle given the state of the surrounding agents and the map information.
  arXiv  Detail & Related papers  (2022-04-05T17:58:18Z)
• SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction [64.16212996247943]
  We present a Sparse Graph Convolution Network(SGCN) for pedestrian trajectory prediction. Specifically, the SGCN explicitly models the sparse directed interaction with a sparse directed spatial graph to capture adaptive interaction pedestrians. visualizations indicate that our method can capture adaptive interactions between pedestrians and their effective motion tendencies.
  arXiv  Detail & Related papers  (2021-04-04T03:17:42Z)
• Instance-Aware Predictive Navigation in Multi-Agent Environments [93.15055834395304]
  We propose an Instance-Aware Predictive Control (IPC) approach, which forecasts interactions between agents as well as future scene structures. We adopt a novel multi-instance event prediction module to estimate the possible interaction among agents in the ego-centric view. We design a sequential action sampling strategy to better leverage predicted states on both scene-level and instance-level.
  arXiv  Detail & Related papers  (2021-01-14T22:21:25Z)
• SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction [72.37440317774556]
  We propose advances that address two key challenges in future trajectory prediction. multimodality in both training data and predictions and constant time inference regardless of number of agents.
  arXiv  Detail & Related papers  (2020-07-26T08:17:10Z)
• Implicit Latent Variable Model for Scene-Consistent Motion Forecasting [78.74510891099395]
  In this paper, we aim to learn scene-consistent motion forecasts of complex urban traffic directly from sensor data. We model the scene as an interaction graph and employ powerful graph neural networks to learn a distributed latent representation of the scene.
  arXiv  Detail & Related papers  (2020-07-23T14:31:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.