mlsanityData to 14 Oct 2026

Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks

arXiv 2105.12374 ↗First posted 26 May 2021cs.LGcited by 56

Not on the map. Why?

Abstract (arXiv)

Continual learning is essential for all real-world applications, as frozen pre-trained models cannot effectively deal with non-stationary data distributions. The purpose of this study is to review the state-of-the-art methods that allow continuous learning of computational models over time. We primarily focus on the learning algorithms that perform continuous learning in an online fashion from considerably large (or infinite) sequential data and require substantially low computational and memory resources. We critically analyze the key challenges associated with continual learning for autonomous real-world systems and compare current methods in terms of computations, memory, and network/model complexity. We also briefly describe the implementations of continuous learning algorithms under three main autonomous systems, i.e., self-driving vehicles, unmanned aerial vehicles, and urban robots. The learning methods of these autonomous systems and their strengths and limitations are extensively explored in this article.

Key facts. Cited by 56 papers in the map (data through 14 Oct 2026). Builds on 43 of its 88 references that are in the map. First posted on arXiv 26 May 2021.

Builds on

43 of 88 references.

References · 43

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  4. 2016Learning without Forgettingcited by 2,496
  5. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  6. 2016Progressive Neural Networkscited by 1,361
  7. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
  8. 2017Continual Learning with Deep Generative Replaycited by 1,158
  9. 2017Lifelong Learning with Dynamically Expandable Networkscited by 694
  10. 2018Universal Transformerscited by 647
  11. 2019Three scenarios for continual learningcited by 614
  12. 2019Gradient based sample selection for online continual learningcited by 571
31 more
  1. 2019Online Continual Learning with Maximally Interfered Retrievalcited by 379
  2. 2018Large-Scale Study of Curiosity-Driven Learningcited by 280
  3. 2018Learning to Drive in a Daycited by 273
  4. 2018Task-Free Continual Learningcited by 221
  5. 2017Multi-task Self-Supervised Visual Learningcited by 200
  6. 2019Meta-Learning Representations for Continual Learningcited by 189
  7. 2017FearNet: Brain-Inspired Model for Incremental Learningcited by 177
  8. 2020Continual Lifelong Learning in Natural Language Processing: A Surveycited by 152
  9. 2019Continual Unsupervised Representation Learningcited by 147
  10. 2020A Neural Dirichlet Process Mixture Model for Task-Free Continual Learningcited by 134
  11. 2018Continuous Learning in Single-Incremental-Task Scenarioscited by 109
  12. 2019Uncertainty-guided Continual Learning with Bayesian Neural Networkscited by 102
  13. 2020BADGR: An Autonomous Self-Supervised Learning-Based Navigation Systemcited by 102
  14. 2019Latent Replay for Real-Time Continual Learningcited by 97
  15. 2020iTAML: An Incremental Task-Agnostic Meta-learning Approachcited by 90
  16. 2018Real-time self-adaptive deep stereocited by 80
  17. 2020Never Stop Learning: The Effectiveness of Fine-Tuning in Robotic Reinforcement Learningcited by 23
  18. 2019Uncertainty-Aware Data Aggregation for Deep Imitation Learningcited by 20
  19. 2020Online Continual Learning on Sequencescited by 14
  20. 2019Knowledge is Never Enough: Towards Web Aided Deep Open World Recognitioncited by 12
  21. 2020Active Learning-based Classification in Automated Connected Vehiclescited by 7
  22. 2017Composing Meta-Policies for Autonomous Driving Using Hierarchical Deep Reinforcement Learningcited by 4
  23. 2019A Framework for On-line Learning of Underwater Vehicles Dynamic Modelscited by 4
  24. 2019Locally Weighted Regression Pseudo-Rehearsal for Online Learning of Vehicle Dynamicscited by 4
  25. 2019Online Deep Reinforcement Learning for Autonomous UAV Navigation and Exploration of Outdoor Environmentscited by 4
  26. 2016Towards Lifelong Self-Supervision: A Deep Learning Direction for Roboticscited by 3
  27. 2019Online Deep Learning for Improved Trajectory Tracking of Unmanned Aerial Vehicles Using Expert Knowledgecited by 3
  28. 2019Adaptive Probabilistic Vehicle Trajectory Prediction Through Physically Feasible Bayesian Recurrent Neural Networkcited by 3
  29. 2020Adaptive Neural Trajectory Tracking Control for Flexible-Joint Robots with Online Learningcited by 3
  30. 2018Simulated Autonomous Driving in a Realistic Driving Environment using Deep Reinforcement Learning and a Deterministic Finite State Machinecited by 2
  31. 2019Incremental Learning of Motion Primitives for Pedestrian Trajectory Prediction at Intersectionscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 12; 2024: 21; 2025: 13; 2026: 7.

56 papers.

Sort:

By area:

  1. 2024Towards Lifelong Learning of Large Language Models: A Surveycited by 64
  2. 2024Recent Advances of Foundation Language Models-based Continual Learning: A Surveycited by 46
  3. 2022Transfer without Forgettingcited by 44
  4. 2023The Ideal Continual Learner: An Agent That Never Forgetscited by 35
  5. 2023Brain-inspired learning in artificial neural networks: a reviewcited by 26
  6. 2022Continual Object Detection: A review of definitions, strategies, and challengescited by 25
  7. 2024A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trendscited by 16
  8. 2024Continual Learning on Graphs: A Surveycited by 12
  9. 2023Cost-effective On-device Continual Learning over Memory Hierarchy with Mirocited by 10
  10. 2024Continual Learning for Smart City: A Surveycited by 9
  11. 2025Prototype-Based Continual Learning with Label-free Replay Buffer and Cluster Preservation Losscited by 9
  12. 2024LoRanPAC: Low-rank Random Features and Pre-trained Models for Bridging Theory and Practice in Continual Learningcited by 8
38 more
  1. 2024Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applicationscited by 8
  2. 2025PLAN: Proactive Low-Rank Allocation for Continual Learningcited by 7
  3. 2024Replay Consolidation with Label Propagation for Continual Object Detectioncited by 6
  4. 2024How green is continual learning, really? Analyzing the energy consumption in continual training of vision foundation modelscited by 5
  5. 2024On the Convergence of Continual Federated Learning Using Incrementally Aggregated Gradientscited by 5
  6. 2022Exploring the Intersection between Neural Architecture Search and Continual Learningcited by 4
  7. 2023CoSDA: Continual Source-Free Domain Adaptationcited by 4
  8. 2024Exploring the Stability Gap in Continual Learning: The Role of the Classification Headcited by 4
  9. 2025Long-Term Planning Around Humans in Domestic Environments with 3D Scene Graphscited by 4
  10. 2025Reinforced Interactive Continual Learning via Real-time Noisy Human Feedbackcited by 3
  11. 2025iPINNER: An Iterative Physics-Informed Neural Network with Ensemble Kalman Filtercited by 3
  12. 2026Revisiting Weight Regularization for Low-Rank Continual Learningcited by 3
  13. 2024Constructing Enhanced Mutual Information for Online Class-Incremental Learningcited by 2
  14. 2024TiROD: Tiny Robotics Dataset and Benchmark for Continual Object Detectioncited by 2
  15. 2024Hierarchical Subspaces of Policies for Continual Offline Reinforcement Learningcited by 2
  16. 2025EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental Learningcited by 2
  17. 2023Towards Robust Continual Learning with Bayesian Adaptive Moment Regularizationcited by 1
  18. 2024Outlier-Robust Long-Term Robotic Mapping Leveraging Ground Segmentationcited by 1
  19. 2024Algorithm Design for Continual Learning in IoT Networkscited by 1
  20. 2025Ranking-aware Continual Learning for LiDAR Place Recognitioncited by 1
  21. 2025Hypothesis on the Functional Advantages of the Selection-Broadcast Cycle Structure: Global Workspace Theory and Dealing with a Real-Time Worldcited by 1
  22. 2025PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learningcited by 1
  23. 2025Learning with Preserving for Continual Multitask Learningcited by 1
  24. 2026Continual Learning of Domain-Invariant Representationscited by 1
  25. 2023A sliced-Wasserstein distance-based approach for out-of-class-distribution detectioncited by 0
  26. 2023Delta-Patching: A Framework for Rapid Adaptation of Pre-trained Convolutional Networks without Base Performance Losscited by 0
  27. 2023Mole Recruitment: Poisoning of Image Classifiers via Selective Batch Samplingcited by 0
  28. 2023SRIL: Selective Regularization for Class-Incremental Learningcited by 0
  29. 2023Rotation Augmented Distillation for Exemplar-Free Class Incremental Learning with Detailed Analysiscited by 0
  30. 2023Continual Cross-Dataset Adaptation in Road Surface Classificationcited by 0
  31. 2023Continual Learning with Deep Streaming Regularized Discriminant Analysiscited by 0
  32. 2024Efficient Parameter Mining and Freezing for Continual Object Detectioncited by 0
  33. 2024Towards stable training of parallel continual learningcited by 0
  34. 2024State-of-the-art in Robot Learning for Multi-Robot Collaboration: A Comprehensive Surveycited by 0
  35. 2024Smart E-commerce Recommendations with Semantic AIcited by 0
  36. 2024Slowing Down Forgetting in Continual Learningcited by 0
  37. 2025OpenHAIV: A Framework Towards Practical Open-World Learningcited by 0
  38. 2025Robust and continuous machine learning of usage habits to adapt digital interfaces to user needscited by 0

50 most cited of 56 All 56 (JSON)