Generative Active Learning for Long-tail Trajectory Prediction via Controllable Diffusion Model

• URL: http://arxiv.org/abs/2507.22615v1
• Date: Wed, 30 Jul 2025 12:36:05 GMT
• Title: Generative Active Learning for Long-tail Trajectory Prediction via Controllable Diffusion Model
• Authors: Daehee Park, Monu Surana, Pranav Desai, Ashish Mehta, Reuben MV John, Kuk-Jin Yoon,
• Abstract summary: We introduce Generative Active Learning for Trajectory prediction (GALTraj)<n>GALTraj is the first method to successfully deploy generative active learning into trajectory prediction.<n>Unlike prior simulation methods focused solely on scenario diversity, GALTraj is the first to show how simulator-driven augmentation benefits long-tail learning in trajectory prediction.
• Score: 33.08750291010022
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While data-driven trajectory prediction has enhanced the reliability of autonomous driving systems, it still struggles with rarely observed long-tail scenarios. Prior works addressed this by modifying model architectures, such as using hypernetworks. In contrast, we propose refining the training process to unlock each model's potential without altering its structure. We introduce Generative Active Learning for Trajectory prediction (GALTraj), the first method to successfully deploy generative active learning into trajectory prediction. It actively identifies rare tail samples where the model fails and augments these samples with a controllable diffusion model during training. In our framework, generating scenarios that are diverse, realistic, and preserve tail-case characteristics is paramount. Accordingly, we design a tail-aware generation method that applies tailored diffusion guidance to generate trajectories that both capture rare behaviors and respect traffic rules. Unlike prior simulation methods focused solely on scenario diversity, GALTraj is the first to show how simulator-driven augmentation benefits long-tail learning in trajectory prediction. Experiments on multiple trajectory datasets (WOMD, Argoverse2) with popular backbones (QCNet, MTR) confirm that our method significantly boosts performance on tail samples and also enhances accuracy on head samples.

Related papers

• AMD: Adaptive Momentum and Decoupled Contrastive Learning Framework for Robust Long-Tail Trajectory Prediction [0.37094728988180015]
  We propose an adaptive momentum and decoupled contrastive learning framework (AMD), which integrates unsupervised and supervised contrastive learning strategies.<n>We propose three different criteria to define long-tail trajectories and conduct extensive comparative experiments on the nuScenes and ETH$/$UCY datasets.
  arXiv  Detail & Related papers  (2025-07-02T15:20:40Z)
• Generative Data Mining with Longtail-Guided Diffusion [39.460272573196896]
  We develop a proactive longtail discovery process by imagining additional data during training.<n>We leverage these signals as guidance to generate additional training data from a latent diffusion model.<n>We do not need to expose the predictive model to intermediate diffusion states.
  arXiv  Detail & Related papers  (2025-02-04T03:51:00Z)
• Target-driven Self-Distillation for Partial Observed Trajectories Forecasting [41.636125879090116]
  We introduce a Target-driven Self-Distillation method (TSD) for motion forecasting.<n>By employing self-distillation, the model learns from the feature distributions of both fully observed and partially observed trajectories.<n>This enhances the model's ability to predict motion accurately in both fully observed and partially observed scenarios.
  arXiv  Detail & Related papers  (2025-01-28T07:46:13Z)
• Certified Human Trajectory Prediction [66.1736456453465]
  We propose a certification approach tailored for trajectory prediction that provides guaranteed robustness.<n>To mitigate the inherent performance drop through certification, we propose a diffusion-based trajectory denoiser and integrate it into our method.<n>We demonstrate the accuracy and robustness of the certified predictors and highlight their advantages over the non-certified ones.
  arXiv  Detail & Related papers  (2024-03-20T17:41:35Z)
• Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization [87.21285093582446]
  Diffusion Generative Flow Samplers (DGFS) is a sampling-based framework where the learning process can be tractably broken down into short partial trajectory segments. Our method takes inspiration from the theory developed for generative flow networks (GFlowNets)
  arXiv  Detail & Related papers  (2023-10-04T09:39:05Z)
• Pre-training on Synthetic Driving Data for Trajectory Prediction [61.520225216107306]
  We propose a pipeline-level solution to mitigate the issue of data scarcity in trajectory forecasting. We adopt HD map augmentation and trajectory synthesis for generating driving data, and then we learn representations by pre-training on them. We conduct extensive experiments to demonstrate the effectiveness of our data expansion and pre-training strategies.
  arXiv  Detail & Related papers  (2023-09-18T19:49:22Z)
• EquiDiff: A Conditional Equivariant Diffusion Model For Trajectory Prediction [11.960234424309265]
  We propose EquiDiff, a deep generative model for predicting future vehicle trajectories. EquiDiff is based on the conditional diffusion model, which generates future trajectories by incorporating historical information and random Gaussian noise. Our results demonstrate that EquiDiff outperforms other baseline models in short-term prediction, but has slightly higher errors for long-term prediction.
  arXiv  Detail & Related papers  (2023-08-12T13:17:09Z)
• Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling [69.60713300418467]
  Learning to jump is a general recipe for generative modeling of various types of data. We demonstrate when learning to jump is expected to perform comparably to learning to denoise, and when it is expected to perform better.
  arXiv  Detail & Related papers  (2023-05-28T05:38:28Z)
• Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Tracking [76.27433308688592]
  Accurately modeling quadrotor's system dynamics is critical for guaranteeing agile, safe, and stable navigation. We present a novel Physics-Inspired Temporal Convolutional Network (PI-TCN) approach to learning quadrotor's system dynamics purely from robot experience. Our approach combines the expressive power of sparse temporal convolutions and dense feed-forward connections to make accurate system predictions.
  arXiv  Detail & Related papers  (2022-06-07T13:51:35Z)
• TrajGen: Generating Realistic and Diverse Trajectories with Reactive and Feasible Agent Behaviors for Autonomous Driving [19.06020265777298]
  Existing simulators rely on system-based behavior models for background vehicles, which cannot capture the complex interactive behaviors in real-world scenarios. We propose TrajGen, a two-stage trajectory generation framework, which can capture more realistic behaviors directly from human demonstration. In addition, we develop a data-driven simulator I-Sim that can be used to train reinforcement learning models in parallel based on naturalistic driving data.
  arXiv  Detail & Related papers  (2022-03-31T04:48:29Z)
• Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning [137.39196753245105]
  We present a new model-based reinforcement learning algorithm that learns a multi-headed dynamics model for dynamics generalization. We incorporate context learning, which encodes dynamics-specific information from past experiences into the context latent vector. Our method exhibits superior zero-shot generalization performance across a variety of control tasks, compared to state-of-the-art RL methods.
  arXiv  Detail & Related papers  (2020-10-26T03:20:42Z)
• 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)

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.