Complementary Learning System Empowers Online Continual Learning of Vehicle Motion Forecasting in Smart Cities

• URL: http://arxiv.org/abs/2508.19597v2
• Date: Sat, 06 Sep 2025 09:35:56 GMT
• Title: Complementary Learning System Empowers Online Continual Learning of Vehicle Motion Forecasting in Smart Cities
• Authors: Zirui Li, Yunlong Lin, Guodong Du, Xiaocong Zhao, Cheng Gong, Chen Lv, Chao Lu, Jianwei Gong,
• Abstract summary: We introduce Dual-LS, a task-free, online continual learning paradigm for deep neural network (DNN)-based motion forecasting.<n>Tests on naturalistic data spanning three countries, over 772,000 vehicles and cumulative testing mileage of 11,187 km show that Dual-LS mitigates catastrophic forgetting by up to 74.31%.
• Score: 50.14230518748104
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Artificial intelligence underpins most smart city services, yet deep neural network (DNN) that forecasts vehicle motion still struggle with catastrophic forgetting, the loss of earlier knowledge when models are updated. Conventional fixes enlarge the training set or replay past data, but these strategies incur high data collection costs, sample inefficiently and fail to balance long- and short-term experience, leaving them short of human-like continual learning. Here we introduce Dual-LS, a task-free, online continual learning paradigm for DNN-based motion forecasting that is inspired by the complementary learning system of the human brain. Dual-LS pairs two synergistic memory rehearsal replay mechanisms to accelerate experience retrieval while dynamically coordinating long-term and short-term knowledge representations. Tests on naturalistic data spanning three countries, over 772,000 vehicles and cumulative testing mileage of 11,187 km show that Dual-LS mitigates catastrophic forgetting by up to 74.31\% and reduces computational resource demand by up to 94.02\%, markedly boosting predictive stability in vehicle motion forecasting without inflating data requirements. Meanwhile, it endows DNN-based vehicle motion forecasting with computation efficient and human-like continual learning adaptability fit for smart cities.

Related papers

• TEAM: Topological Evolution-aware Framework for Traffic Forecasting--Extended Version [24.544665297938437]
  Topological Evolution-aware Framework (TEAM) for traffic forecasting incorporates convolution and attention.<n>TEAM is capable of much lower re-training costs than existing methods are without jeopardizing forecasting accuracy.
  arXiv  Detail & Related papers  (2024-10-24T22:50:21Z)
• Mitigating Covariate Shift in Imitation Learning for Autonomous Vehicles Using Latent Space Generative World Models [60.87795376541144]
  A world model is a neural network capable of predicting an agent's next state given past states and actions.<n>During end-to-end training, our policy learns how to recover from errors by aligning with states observed in human demonstrations.<n>We present qualitative and quantitative results, demonstrating significant improvements upon prior state of the art in closed-loop testing.
  arXiv  Detail & Related papers  (2024-09-25T06:48:25Z)
• Less is More: Efficient Brain-Inspired Learning for Autonomous Driving Trajectory Prediction [26.14918154872732]
  This paper presents the Human-Like Trajectory Prediction model (H++) H++ emulates human cognitive processes to improve trajectory prediction in autonomous driving (AD) Evaluated using the NGSIM, HighD, and MoCAD benchmarks, H++ demonstrates superior performance compared to existing models.
  arXiv  Detail & Related papers  (2024-07-09T16:42:17Z)
• Mobile Traffic Prediction at the Edge Through Distributed and Deep Transfer Learning [2.391548802248377]
  We investigate a fully decentralized AI solution for mobile traffic prediction that allows data to be kept locally.<n>Two main Deep Learning architectures are designed based on Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs)<n>DTL significantly reduces computational complexity and energy consumption during training, resulting in a reduction of the energy footprint by 60% for CNNs and 90% for RNNs.
  arXiv  Detail & Related papers  (2023-10-22T23:48:13Z)
• Multi-Agent Deep Reinforcement Learning for Dynamic Avatar Migration in AIoT-enabled Vehicular Metaverses with Trajectory Prediction [70.9337170201739]
  We propose a model to predict the future trajectories of intelligent vehicles based on their historical data. We show that our proposed algorithm can effectively reduce the latency of executing avatar tasks by around 25% without prediction.
  arXiv  Detail & Related papers  (2023-06-26T13:27:11Z)
• Vision Paper: Causal Inference for Interpretable and Robust Machine Learning in Mobility Analysis [71.2468615993246]
  Building intelligent transportation systems requires an intricate combination of artificial intelligence and mobility analysis. The past few years have seen rapid development in transportation applications using advanced deep neural networks. This vision paper emphasizes research challenges in deep learning-based mobility analysis that require interpretability and robustness.
  arXiv  Detail & Related papers  (2022-10-18T17:28:58Z)
• Online Training Through Time for Spiking Neural Networks [66.7744060103562]
  Spiking neural networks (SNNs) are promising brain-inspired energy-efficient models. Recent progress in training methods has enabled successful deep SNNs on large-scale tasks with low latency. We propose online training through time (OTTT) for SNNs, which is derived from BPTT to enable forward-in-time learning.
  arXiv  Detail & Related papers  (2022-10-09T07:47:56Z)
• Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking [58.14267480293575]
  We propose a simple yet effective online learning approach for few-shot online adaptation without requiring offline training. It allows an in-built memory retention mechanism for the model to remember the knowledge about the object seen before. We evaluate our approach based on two networks in the online learning families for tracking, i.e., multi-layer perceptrons in RT-MDNet and convolutional neural networks in DiMP.
  arXiv  Detail & Related papers  (2021-12-28T06:51:18Z)
• Generative Adversarial Imitation Learning for End-to-End Autonomous Driving on Urban Environments [0.8122270502556374]
  Generative Adversarial Imitation Learning (GAIL) can train policies without explicitly requiring to define a reward function. We show that both of them are capable of imitating the expert trajectory from start to end after training ends.
  arXiv  Detail & Related papers  (2021-10-16T15:04:13Z)
• A Physics-Informed Deep Learning Paradigm for Car-Following Models [3.093890460224435]
  We develop a family of neural network based car-following models informed by physics-based models. Two types of PIDL-CFM problems are studied, one to predict acceleration only and the other to jointly predict acceleration and discover model parameters. The results demonstrate the superior performance of neural networks informed by physics over those without.
  arXiv  Detail & Related papers  (2020-12-24T18:04:08Z)

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.