2023

"No, to the Right" -- Online Language Corrections for Robotic Manipulation via Shared Autonomy

Cui, Yuchen, Karamcheti, Siddharth, Palleti, Raj et al.

Understand

Systems for language-guided human-robot interaction must satisfy two key desiderata for broad adoption: adaptivity and learning efficiency.

Unfortunately, existing instruction-following agents cannot adapt, lacking the ability to incorporate online natural language supervision, and even if they could, require hundreds of demonstrations to learn even simple policies.
In this work, we address these problems by presenting Language-Informed Latent Actions with Corrections (LILAC), a framework for incorporating and adapting to natural language corrections - "to the right," or "no, towards the book" - online, during execution.
We explore rich manipulation domains within a shared autonomy paradigm.

Built on

Understanding Natural Language Commands for Robotic Navigation and Mobile Manipulation. In Association for the Advancement of Artificial Intelligence (AAAI)
Stefanie Tellex, Thomas Kollar, Steven Dickerson, Matthew R Walter, Ashis Gopal Banerjee, Seth J Teller, and Nicholas Roy. 2011 · 2011
Earlier work this paper cites.
A joint model of language and perception for grounded attribute learning. In International Conference on Machine Learning (ICML) . 1671–1678
Cynthia Matuszek, Nicholas FitzGerald, Luke Zettlemoyer, Liefeng Bo, and Dieter Fox. 2012 · 2012
Earlier work this paper cites.
Weakly supervised learning of semantic parsers for mapping instructions to actions
Yoav Artzi and Luke Zettlemoyer. 2013 · 2013
Earlier work this paper cites.
A policy-blending formalism for shared control
Anca D Dragan and Siddhartha S Srinivasa. 2013 · 2013
Earlier work this paper cites.
Toward Interactive Grounded Language Acqusition. In Robotics: Science and Systems (RSS)
T. Kollar, J. Krishnamurthy, and Grant P. Strimel. 2013 · 2013
Earlier work this paper cites.
Robot Learning from Human Teachers. In Robot Learning from Human Teachers
S. Chernova and Andrea Lockerd Thomaz. 2014 · 2014
Earlier work this paper cites.
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In International Conference on Machine Learning (ICML) . 448–456
Sergey Ioffe and Christian Szegedy. 2015 · 2015
Earlier work this paper cites.
Adam: A method for stochastic optimization. In International Conference on Learning Representations (ICLR)
Diederik Kingma and Jimmy Ba. 2015 · 2015
Earlier work this paper cites.
Learning to Interpret Natural Language Commands through Human-Robot Dialog. In International Joint Conference on Artificial Intelligence (IJCAI)
Jesse Thomason, Shiqi Zhang, Raymond J. Mooney, and Peter Stone. 2015 · 2015
Earlier work this paper cites.
Gaussian Error Linear Units (GELUs)
Original
Dan Hendrycks and Kevin Gimpel. 2016 · 2016
Earlier work this paper cites.
Assistive teleoperation of robot arms via automatic time-optimal mode switching. In ACM/IEEE International Conference on Human Robot Interaction (HRI) . 35–42
Laura V Herlant, Rachel M Holladay, and Siddhartha S Srinivasa. 2016 · 2016
Earlier work this paper cites.
Accurately and Efficiently Interpreting Human-Robot Instructions of Varying Granularities. In Robotics: Science and Systems (RSS)
Dilip Arumugam, Siddharth Karamcheti, Nakul Gopalan, Lawson L. S. Wong, and Stefanie Tellex. 2017 · 2017
Earlier work this paper cites.
Real-time natural language corrections for assistive robotic manipulators
Alexander Broad, Jacob Arkin, Nathan D. Ratliff, Thomas M. Howard, and Brenna Argall. 2017 · 2017
Earlier work this paper cites.
Deep Reinforcement Learning from Human Preferences. In Advances in Neural Information Processing Systems (NeurIPS)
Paul Christiano, Jan Leike, Tom B. Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017 · 2017
Earlier work this paper cites.
Attention Is All You Need
Original
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017 · 2017
Earlier work this paper cites.

Similar

Autonomy in rehabilitation robotics: an intersection
Brenna D Argall. 2018 · 2018
Cited alongside, same era.
Batch Active Preference-Based Learning of Reward Functions. In Conference on Robot Learning (CoRL)
Erdem Biyik and Dorsa Sadigh. 2018 · 2018
Cited alongside, same era.
Active Reward Learning from Critiques. In International Conference on Robotics and Automation (ICRA) . 6907–6914
Yuchen Cui and Scott Niekum. 2018 · 2018
Cited alongside, same era.
Shared autonomy via hindsight optimization for teleoperation and teaming
Shervin Javdani, Henny Admoni, Stefania Pellegrinelli, Siddhartha S Srinivasa, and J Andrew Bagnell. 2018 · 2018
Cited alongside, same era.
A review of intent detection, arbitration, and communication aspects of shared control for physical human-robot interaction
Dylan P Losey, Craig G McDonald, Edoardo Battaglia, and Marcia K O’Malley. 2018 · 2018
Cited alongside, same era.
FiLM: Visual Reasoning with a General Conditioning Layer. In Association for the Advancement of Artificial Intelligence (AAAI)
Ethan Perez, Florian Strub, Harm D. Vries, Vincent Dumoulin, and Aaron C. Courville. 2018 · 2018
Cited alongside, same era.
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning. In International Conference on Learning Representations (ICLR)
Maxime Chevalier-Boisvert, Dzmitry Bahdanau, Salem Lahlou, Lucas Willems, Chitwan Saharia, Thien Huu Nguyen, and Yoshua Bengio. 2019 · 2019
Cited alongside, same era.
Guiding Policies with Language via Meta-Learning. In International Conference on Learning Representations (ICLR)
John D. Co-Reyes, Abhishek Gupta, Suvansh Sanjeev, Nick Altieri, John DeNero, Pieter Abbeel, and Sergey Levine. 2019 · 2019
Cited alongside, same era.
HG-DAgger: Interactive Imitation Learning with Human Experts. In International Conference on Robotics and Automation (ICRA) . 8077–8083
Michael Kelly, Chelsea Sidrane, K. Driggs-Campbell, and Mykel J. Kochenderfer. 2019 · 2019
Cited alongside, same era.
A Survey of Reinforcement Learning Informed by Natural Language. In International Joint Conference on Artificial Intelligence (IJCAI)
Jelena Luketina, Nantas Nardelli, Gregory Farquhar, Jakob Foerster, Jacob Andreas, Edward Grefenstette, Shimon Whiteson, and Tim Rocktäschel. 2019 · 2019
Cited alongside, same era.
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In Empirical Methods in Natural Language Processing (EMNLP)
Nils Reimers and Iryna Gurevych. 2019 · 2019
Cited alongside, same era.
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
Original
Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019 · 2019
Cited alongside, same era.

Then

Controlling Assistive Robots with Learned Latent Actions. In International Conference on Robotics and Automation (ICRA) . 378–384
Dylan P. Losey, Krishnan Srinivasan, Ajay Mandlekar, Animesh Garg, and Dorsa Sadigh. 2020 · 2020
Later among the works it cites.
Grounding Language in Play
Original
Corey Lynch and Pierre Sermanet. 2020 · 2020
Later among the works it cites.
Human-in-the-Loop Imitation Learning using Remote Teleoperation
Original
Ajay Mandlekar, Danfei Xu, Roberto Martín-Martín, Yuke Zhu, Li Fei-Fei, and Silvio Savarese. 2020 · 2020
Later among the works it cites.
Unnatural Language Processing: Bridging the Gap Between Synthetic and Natural Language Data
Original
Alana Marzoev, S. Madden, M. Kaashoek, Michael J. Cafarella, and Jacob Andreas. 2020 · 2020
Later among the works it cites.
Learning Online from Corrective Feedback: A Meta-Algorithm for Robotics. In Conference on Robot Learning (CoRL)
Matthew Schmittle, Sanjiban Choudhury, and Siddhartha S Srinivasa. 2020 · 2020
Later among the works it cites.
Language-Conditioned Imitation Learning for Robot Manipulation Tasks. In Advances in Neural Information Processing Systems (NeurIPS)
Simon Stepputtis, J. Campbell, Mariano Phielipp, Stefan Lee, Chitta Baral, and H. B. Amor. 2020 · 2020
Later among the works it cites.
ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning. In Conference on Robot Learning (CoRL)
Ryan Hoque, Ashwin Balakrishna, Ellen R. Novoseller, Albert Wilcox, Daniel S. Brown, and Ken Goldberg. 2021 · 2021
Later among the works it cites.
BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning. In Conference on Robot Learning (CoRL)
Eric Jang, Alex Irpan, Mohi Khansari, Daniel Kappler, Frederik Ebert, Corey Lynch, Sergey Levine, and Chelsea Finn. 2021 · 2021
Later among the works it cites.
Learning Human Objectives from Sequences of Physical Corrections. In International Conference on Robotics and Automation (ICRA) . 2877–2883
Mengxi Li, Alper Canberk, Dylan P. Losey, and Dorsa Sadigh. 2021 · 2021
Later among the works it cites.
Polymetis
Yixin Lin, Austin S. Wang, Giovanni Sutanto, Akshara Rai, and Franziska Meier. 2021 · 2021
Later among the works it cites.
Learning latent actions to control assistive robots
Dylan P. Losey, Hong Jun Jeon, Mengxi Li, Krishna Parasuram Srinivasan, Ajay Mandlekar, Animesh Garg, Jeannette Bohg, and Dorsa Sadigh. 2021 · 2021
Later among the works it cites.
CLIPort: What and Where Pathways for Robotic Manipulation. In Conference on Robot Learning (CoRL)
Mohit Shridhar, Lucas Manuelli, and Dieter Fox. 2021 · 2021
Later among the works it cites.
LaTTe: Language Trajectory TransformEr
Original
Arthur Fender C. Bucker, Luis F. C. Figueredo, Sami Haddadin, Ashish Kapoor, Shuang Ma, Sai Vemprala, and Rogerio Bonatti. 2022b · 2022
Later among the works it cites.
What Matters in Language Conditioned Robotic Imitation Learning Over Unstructured Data
Oier Mees, Lukás Hermann, and Wolfram Burgard. 2022 · 2022
Later among the works it cites.
Correcting Robot Plans with Natural Language Feedback. In Robotics: Science and Systems (RSS)
Pratyusha Sharma, Balakumar Sundaralingam, Valts Blukis, Chris Paxton, Tucker Hermans, Antonio Torralba, Jacob Andreas, and Dieter Fox. 2022 · 2022
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…

&#34;No, to the Right&#34; -- Online Language Corrections for Robotic Manipulation via Shared Autonomy

Understand

Built on

Similar

Then

Beyond the bibliography

Built on

Similar

Then

Beyond the bibliography

"No, to the Right" -- Online Language Corrections for Robotic Manipulation via Shared Autonomy