# Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challenges

arXiv: https://arxiv.org/abs/1907.00182 · HTML: https://mlsanity.com/paper/1907.00182/

## Key facts

- Cited by 93 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2019.

## Built on by (most cited first, 30 of 93)

- [Online Continual Learning in Image Classification: An Empirical Survey](https://mlsanity.com/paper/2101.10423/) (2021)
- [Avalanche: an End-to-End Library for Continual Learning](https://mlsanity.com/paper/2104.00405/) (2021)
- [RECALL: Replay-based Continual Learning in Semantic Segmentation](https://mlsanity.com/paper/2108.03673/) (2021)
- [Continual Pre-Training Mitigates Forgetting in Language and Vision](https://mlsanity.com/paper/2205.09357/) (2022)
- [Continual Learning of Natural Language Processing Tasks: A Survey](https://mlsanity.com/paper/2211.12701/) (2022)
- [Towards Lifelong Learning of Large Language Models: A Survey](https://mlsanity.com/paper/2406.06391/) (2024)
- [Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulation](https://mlsanity.com/paper/2305.02231/) (2023)
- [Recent Advances of Continual Learning in Computer Vision: An Overview](https://mlsanity.com/paper/2109.11369/) (2021)
- [Self-Supervised Training Enhances Online Continual Learning](https://mlsanity.com/paper/2103.14010/) (2021)
- [A survey of multimodal deep generative models](https://mlsanity.com/paper/2207.02127/) (2022)
- [Recent Advances of Foundation Language Models-based Continual Learning: A Survey](https://mlsanity.com/paper/2405.18653/) (2024)
- [Distilled Replay: Overcoming Forgetting through Synthetic Samples](https://mlsanity.com/paper/2103.15851/) (2021)
- [Non-IID data and Continual Learning processes in Federated Learning: A long road ahead](https://mlsanity.com/paper/2111.13394/) (2021)
- [World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges](https://mlsanity.com/paper/2301.05832/) (2023)
- [Concept drift detection and adaptation for federated and continual learning](https://mlsanity.com/paper/2105.13309/) (2021)
- [Sample Condensation in Online Continual Learning](https://mlsanity.com/paper/2206.11849/) (2022)
- [EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use case](https://mlsanity.com/paper/2104.11914/) (2021)
- [Graph Lifelong Learning: A Survey](https://mlsanity.com/paper/2202.10688/) (2022)
- [SpikeDyn: A Framework for Energy-Efficient Spiking Neural Networks with Continual and Unsupervised Learning Capabilities in Dynamic Environments](https://mlsanity.com/paper/2103.00424/) (2021)
- [CLEVA-Compass: A Continual Learning EValuation Assessment Compass to Promote Research Transparency and Comparability](https://mlsanity.com/paper/2110.03331/) (2021)
- [How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition](https://mlsanity.com/paper/2207.07730/) (2022)
- [Brain-inspired learning in artificial neural networks: a review](https://mlsanity.com/paper/2305.11252/) (2023)
- [CRIL: Continual Robot Imitation Learning via Generative and Prediction Model](https://mlsanity.com/paper/2106.09422/) (2021)
- [Low-rank extended Kalman filtering for online learning of neural networks from streaming data](https://mlsanity.com/paper/2305.19535/) (2023)
- [Is Class-Incremental Enough for Continual Learning?](https://mlsanity.com/paper/2112.02925/) (2021)
- [Unsupervised Continual Semantic Adaptation through Neural Rendering](https://mlsanity.com/paper/2211.13969/) (2022)
- [Rethinking Exemplars for Continual Semantic Segmentation in Endoscopy Scenes: Entropy-based Mini-Batch Pseudo-Replay](https://mlsanity.com/paper/2308.14100/) (2023)
- [Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation](https://mlsanity.com/paper/2109.00525/) (2021)
- [Continual Learning for Peer-to-Peer Federated Learning: A Study on Automated Brain Metastasis Identification](https://mlsanity.com/paper/2204.13591/) (2022)
- [F-SIOL-310: A Robotic Dataset and Benchmark for Few-Shot Incremental Object Learning](https://mlsanity.com/paper/2103.12242/) (2021)

## Abstract (arXiv)

Continual learning (CL) is a particular machine learning paradigm where the data distribution and learning objective changes through time, or where all the training data and objective criteria are never available at once. The evolution of the learning process is modeled by a sequence of learning experiences where the goal is to be able to learn new skills all along the sequence without forgetting what has been previously learned. Continual learning also aims at the same time at optimizing the memory, the computation power and the speed during the learning process. An important challenge for machine learning is not necessarily finding solutions that work in the real world but rather finding stable algorithms that can learn in real world. Hence, the ideal approach would be tackling the real world in a embodied platform: an autonomous agent. Continual learning would then be effective in an autonomous agent or robot, which would learn autonomously through time about the external world, and incrementally develop a set of complex skills and knowledge. Robotic agents have to learn to adapt and interact with their environment using a continuous stream of observations. Some recent approaches aim at tackling continual learning for robotics, but most recent papers on continual learning only experiment approaches in simulation or with static datasets. Unfortunately, the evaluation of those algorithms does not provide insights on whether their solutions may help continual learning in the context of robotics. This paper aims at reviewing the existing state of the art of continual learning, summarizing existing benchmarks and metrics, and proposing a framework for presenting and evaluating both robotics and non robotics approaches in a way that makes transfer between both fields easier.