mlsanityData to 14 Oct 2026

Expanding the Deployment Envelope of Behavior Prediction via Adaptive Meta-Learning

arXiv 2209.11820 ↗First posted 23 Sep 2022cs.LG cs.CV cs.ROcited by 23

Not on the map. Why?

Abstract (arXiv)

Learning-based behavior prediction methods are increasingly being deployed in real-world autonomous systems, e.g., in fleets of self-driving vehicles, which are beginning to commercially operate in major cities across the world. Despite their advancements, however, the vast majority of prediction systems are specialized to a set of well-explored geographic regions or operational design domains, complicating deployment to additional cities, countries, or continents. Towards this end, we present a novel method for efficiently adapting behavior prediction models to new environments. Our approach leverages recent advances in meta-learning, specifically Bayesian regression, to augment existing behavior prediction models with an adaptive layer that enables efficient domain transfer via offline fine-tuning, online adaptation, or both. Experiments across multiple real-world datasets demonstrate that our method can efficiently adapt to a variety of unseen environments.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 33 of its 63 references that are in the map. First posted on arXiv 23 Sep 2022.

Builds on

33 of 63 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  4. 2013Auto-Encoding Variational Bayescited by 4,053
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  6. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  7. 2018On First-Order Meta-Learning Algorithmscited by 1,018
  8. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  9. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 503
  10. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 463
  11. 2016Learning to reinforcement learncited by 377
  12. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 331
21 more
  1. 2020Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Predictioncited by 325
  2. 2021End-to-end Interpretable Neural Motion Plannercited by 242
  3. 2020One Thousand and One Hours: Self-driving Motion Prediction Datasetcited by 240
  4. 2020It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Predictioncited by 236
  5. 2019Human Motion Trajectory Prediction: A Surveycited by 232
  6. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 229
  7. 2020Transformer Networks for Trajectory Forecastingcited by 181
  8. 2016Towards a Neural Statisticiancited by 121
  9. 2017A Tutorial on Kernel Density Estimation and Recent Advancescited by 101
  10. 2021SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Predictioncited by 97
  11. 2022Remember Intentions: Retrospective-Memory-based Trajectory Predictioncited by 86
  12. 2020Recursive Social Behavior Graph for Trajectory Predictioncited by 66
  13. 2022Adaptive Trajectory Prediction via Transferable GNNcited by 51
  14. 2019Continuous Meta-Learning without Taskscited by 50
  15. 2018Meta-Learning Priors for Efficient Online Bayesian Regressioncited by 48
  16. 2021PredictionNet: Real-Time Joint Probabilistic Traffic Prediction for Planning, Control, and Simulationcited by 29
  17. 2022Transferable and Adaptable Driving Behavior Predictioncited by 20
  18. 2020Safe Active Dynamics Learning and Control: A Sequential Exploration-Exploitation Frameworkcited by 19
  19. 2022Uncertainty estimation for Cross-dataset performance in Trajectory predictioncited by 13
  20. 2021Bayesian Embeddings for Few-Shot Open World Recognitioncited by 8
  21. 2019Robust Online Model Adaptation by Extended Kalman Filter with Exponential Moving Average and Dynamic Multi-Epoch Strategycited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 11; 2025: 5; 2026: 2.

23 papers.

Sort:

By area:

  1. 2024Driving Everywhere with Large Language Model Policy Adaptationcited by 53
  2. 2023Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Predictioncited by 47
  3. 2024SingularTrajectory: Universal Trajectory Predictor Using Diffusion Modelcited by 35
  4. 2024Producing and Leveraging Online Map Uncertainty in Trajectory Predictioncited by 33
  5. 2023trajdata: A Unified Interface to Multiple Human Trajectory Datasetscited by 25
  6. 2024Adapting to Length Shift: FlexiLength Network for Trajectory Predictioncited by 22
  7. 2024T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memorycited by 20
  8. 2025Data Scaling Laws for End-to-End Autonomous Drivingcited by 15
  9. 2023Evaluating Pedestrian Trajectory Prediction Methods with Respect to Autonomous Drivingcited by 11
  10. 2024Recurrent Aligned Network for Generalized Pedestrian Trajectory Predictioncited by 9
  11. 2023CRITERIA: a New Benchmarking Paradigm for Evaluating Trajectory Prediction Models for Autonomous Drivingcited by 8
  12. 2024Accelerating Online Mapping and Behavior Prediction via Direct BEV Feature Attentioncited by 8
11 more
  1. 2025Delving into Mapping Uncertainty for Mapless Trajectory Predictioncited by 6
  2. 2023Adaptive Human Trajectory Prediction via Latent Corridorscited by 5
  3. 2024LoRD: Adapting Differentiable Driving Policies to Distribution Shiftscited by 4
  4. 2024RealTraj: Towards Real-World Pedestrian Trajectory Forecastingcited by 3
  5. 2024MetaTra: Meta-Learning for Generalized Trajectory Prediction in Unseen Domaincited by 2
  6. 2025Towards Predicting Any Human Trajectory In Contextcited by 2
  7. 2024C2INet: Realizing Incremental Trajectory Prediction with Prior-Aware Continual Causal Interventioncited by 0
  8. 2025A Concept for Efficient Scalability of Automated Driving Allowing for Technical, Legal, Cultural, and Ethical Differencescited by 0
  9. 2025AdaSports-Traj: Role- and Domain-Aware Adaptation for Multi-Agent Trajectory Modeling in Sportscited by 0
  10. 2026MetaDAT: Generalizable Trajectory Prediction via Meta Pre-training and Data-Adaptive Test-Time Updatingcited by 0
  11. 2026Unveiling Transferability in Trajectory Prediction via Latent Scene Embeddingscited by 0