Fetching the paper…

Reading the bibliography…

2020

Self-Supervised Goal-Conditioned Pick and Place

Devin, Coline, Rowghanian, Payam, Vigorito, Chris et al.

Original
PDF
Post on X

Understand

Robots have the capability to collect large amounts of data autonomously by interacting with objects in the world.

However, it is often not obvious \emph{how} to learning from autonomously collected data without human-labeled supervision.
In this work we learn pixel-wise object representations from unsupervised pick and place data that generalize to new objects.
We introduce a novel framework for using these representations in order to predict where to pick and where to place in order to match a goal image.

Self-Supervised Goal-Conditioned Pick and Place · Around

Built on

Dimensionality reduction by learning an invariant mapping
Raia Hadsell, Sumit Chopra, and Yann LeCun · 2006
Earlier work this paper cites.
Form2fit: Learning shape priors for generalizable assembly from disassembly
Original
Kevin Zakka, Andy Zeng, Johnny Lee, and Shuran Song · 2008
Earlier work this paper cites.
Describing textures in the wild
M. Cimpoi, S. Maji, I. Kokkinos, S. Mohamed, , and A. Vedaldi · 2014
Earlier work this paper cites.
Adam: A method for stochastic optimization
Original
Diederik P Kingma and Jimmy Ba · 2014
Earlier work this paper cites.

Similar

Dense object nets: Learning dense visual object descriptors by and for robotic manipulation
Original
Peter R Florence, Lucas Manuelli, and Russ Tedrake · 2018
Cited alongside, same era.
Grasp2vec: Learning object representations from self-supervised grasping
Original
Eric Jang, Coline Devin, Vincent Vanhoucke, and Sergey Levine · 2018
Cited alongside, same era.
Learning instance segmentation by interaction
Deepak Pathak, Yide Shentu, Dian Chen, Pulkit Agrawal, Trevor Darrell, Sergey Levine, and Jitendra Malik · 2018
Cited alongside, same era.
Time-contrastive networks: Self-supervised learning from video
Pierre Sermanet, Corey Lynch, Yevgen Chebotar, Jasmine Hsu, Eric Jang, Stefan Schaal, Sergey Levine, and Google Brain · 2018
Cited alongside, same era.

Then

Self-supervised sim-to-real adaptation for visual robotic manipulation
Original
Rae Jeong, Yusuf Aytar, David Khosid, Yuxiang Zhou, Jackie Kay, Thomas Lampe, Konstantinos Bousmalis, and Francesco Nori · 2019
Later among the works it cites.
Depth by poking:learning to estimate depth from self-supervised grasping
A. Kuefler B. Goodrich and W. Richards · 2020
Closest in time.
Visual task progress estimation with appearance invariant embeddings for robot control and planning
Original
Guilherme Maeda, Joni Vaatinen, and Hironori Yoshida · 2020
Closest in time.
Learning rope manipulation policies using dense object descriptors trained on synthetic depth data
Original
Priya Sundaresan, Jennifer Grannen, Brijen Thananjeyan, Ashwin Balakrishna, Michael Laskey, Kevin Stone, Joseph E Gonzalez, and Ken Goldberg · 2020
Closest in time.

Beyond the bibliography

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

Open on alphaXiv

alphaXiv is searching for related work…