Evaluating Continual Learning on a Home Robot

Sam Powers, Abhinav Gupta, Chris Paxton
Proceedings of The 2nd Conference on Lifelong Learning Agents, PMLR 232:493-512, 2023.

Abstract

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, continuous 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 continuous 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 \model{} (Attention-Based PointNet) 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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v232-powers23a, title = {Evaluating Continual Learning on a Home Robot}, author = {Powers, Sam and Gupta, Abhinav and Paxton, Chris}, booktitle = {Proceedings of The 2nd Conference on Lifelong Learning Agents}, pages = {493--512}, year = {2023}, editor = {Chandar, Sarath and Pascanu, Razvan and Sedghi, Hanie and Precup, Doina}, volume = {232}, series = {Proceedings of Machine Learning Research}, month = {22--25 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v232/powers23a/powers23a.pdf}, url = {https://proceedings.mlr.press/v232/powers23a.html}, abstract = {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, continuous 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 continuous 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 \model{} (Attention-Based PointNet) 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.} }
Endnote
%0 Conference Paper %T Evaluating Continual Learning on a Home Robot %A Sam Powers %A Abhinav Gupta %A Chris Paxton %B Proceedings of The 2nd Conference on Lifelong Learning Agents %C Proceedings of Machine Learning Research %D 2023 %E Sarath Chandar %E Razvan Pascanu %E Hanie Sedghi %E Doina Precup %F pmlr-v232-powers23a %I PMLR %P 493--512 %U https://proceedings.mlr.press/v232/powers23a.html %V 232 %X 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, continuous 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 continuous 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 \model{} (Attention-Based PointNet) 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.
APA
Powers, S., Gupta, A. & Paxton, C.. (2023). Evaluating Continual Learning on a Home Robot. Proceedings of The 2nd Conference on Lifelong Learning Agents, in Proceedings of Machine Learning Research 232:493-512 Available from https://proceedings.mlr.press/v232/powers23a.html.

Related Material