mlsanityData to 14 Oct 2026

Evaluating Continual Learning on a Home Robot

arXiv 2306.02413 ↗First posted 4 Jun 2023cs.RO cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Robots in home environments need to be able to learn new skills continuously as data becomes available, becoming ever more capable over time while using as little real-world data as possible. However, traditional robot learning approaches typically assume large amounts of iid data, which is inconsistent with this goal. In contrast, continual learning methods like CLEAR and SANE allow autonomous agents to learn off of a stream of non-iid samples; they, however, have not previously been demonstrated on real robotics platforms. In this work, we show how continual learning methods can be adapted for use on a real, low-cost home robot, and in particular look at the case where we have extremely small numbers of examples, in a task-id-free setting. Specifically, we propose SANER, a method for continuously learning a library of skills, and ABIP (Attention-Based Interaction Policies) as the backbone to support it. We learn four sequential kitchen tasks on a low-cost home robot, using only a handful of demonstrations per task.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 46 of its 59 references that are in the map. First posted on arXiv 4 Jun 2023.

Builds on

46 of 59 references.

References · 46

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  4. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  5. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  6. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  7. 2016Progressive Neural Networkscited by 1,361
  8. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
  9. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
  10. 2018Experience Replay for Continual Learningcited by 1,095
  11. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 883
  12. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 742
34 more
  1. 2021CLIPort: What and Where Pathways for Robotic Manipulationcited by 622
  2. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 551
  3. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 511
  4. 2020Transporter Networks: Rearranging the Visual World for Robotic Manipulationcited by 344
  5. 2017CORe50: a New Dataset and Benchmark for Continuous Object Recognitioncited by 289
  6. 2021Where2Act: From Pixels to Actions for Articulated 3D Objectscited by 182
  7. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 170
  8. 2022Human-to-Robot Imitation in the Wildcited by 161
  9. 2021The Surprising Effectiveness of Representation Learning for Visual Imitationcited by 154
  10. 2018Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learningcited by 128
  11. 2016Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfercited by 127
  12. 2021Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisationcited by 122
  13. 2019A continual learning survey: Defying forgetting in classification taskscited by 118
  14. 2020The Ingredients of Real-World Robotic Reinforcement Learningcited by 117
  15. 2021Continual World: A Robotic Benchmark For Continual Reinforcement Learningcited by 116
  16. 2019MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policiescited by 108
  17. 2016Sim-to-Real Robot Learning from Pixels with Progressive Netscited by 94
  18. 2017Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learningcited by 90
  19. 2021VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objectscited by 80
  20. 2022Deep Learning Approaches to Grasp Synthesis: A Reviewcited by 72
  21. 2021The Design of Stretch: A Compact, Lightweight Mobile Manipulator for Indoor Human Environmentscited by 40
  22. 2022Modular Lifelong Reinforcement Learning via Neural Compositioncited by 40
  23. 2021CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agentscited by 38
  24. 2022Building a Subspace of Policies for Scalable Continual Learningcited by 28
  25. 2022Few-Shot Continual Active Learning by a Robotcited by 25
  26. 2021CRIL: Continual Robot Imitation Learning via Generative and Prediction Modelcited by 24
  27. 2021SKID RAW: Skill Discovery from Raw Trajectoriescited by 22
  28. 2022Lifelong Reinforcement Learning with Modulating Maskscited by 22
  29. 2020Tell me what this is: Few-Shot Incremental Object Learning by a Robotcited by 18
  30. 2020Transferable Task Execution from Pixels through Deep Planning Domain Learningcited by 17
  31. 2022Beyond Supervised Continual Learning: a Reviewcited by 11
  32. 2022Self-Activating Neural Ensembles for Continual Reinforcement Learningcited by 7
  33. 2021Episodic Memory Model for Learning Robotic Manipulation Taskscited by 2
  34. 2021A Simple Approach to Continual Learning by Transferring Skill Parameterscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 0; 2025: 1; 2026: 2.

5 papers.

  1. 2023HomeRobot: Open-Vocabulary Mobile Manipulationcited by 106
  2. 2023LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discoverycited by 67
  3. 2025A Survey of Continual Reinforcement Learningcited by 18
  4. 2026Rethinking Quantum Continual Learning with Quantum Fisher Informationcited by 0
  5. 2026Continual Graph Multi-Agent Reinforcement Learningcited by 0