Merge pull request #105 from pointW/haojie

Haojie's update

content/publication/haojie_IJRR/index.md

@@ -6,11 +6,11 @@ authors:
 - Arshi Tangri
 - Robin Walters
 - Robert Platt
-date: "2023-12-22T00:00:00Z"
+date: "2024-01-02T00:00:00Z"
 doi: ""
 
 # Schedule page publish date (NOT publication's date).
-publishDate: "2023-12-22T00:00:00Z"
+publishDate: "2024-01-02T00:00:00Z"
 
 # Publication type.
 # Legend: 0 = Uncategorized; 1 = Conference paper; 2 = Journal article;
@@ -19,8 +19,8 @@ publishDate: "2023-12-22T00:00:00Z"
 publication_types: ["2"]
 
 # Publication name and optional abbreviated publication name.
-publication: In *International Journal of Robotics Research 2023*
-publication_short: In *IJRR 2023*
+publication: In *International Journal of Robotics Research 2024*
+publication_short: In *IJRR 2024*
 
 abstract: Robotic pick and place tasks are symmetric under translations and rotations of both the object to be picked and the desired place pose. For example, if the pick object is rotated or translated, then the optimal pick action should also rotate or translate. The same is true for the place pose; if the desired place pose changes, then the place action should also transform accordingly. A recently proposed pick and place framework known as Transporter Net captures some of these symmetries, but not all. This paper analytically studies the symmetries present in planar robotic pick and place and proposes a method of incorporating equivariant neural models into Transporter Net in a way that captures all symmetries. The new model, which we call Equivariant Transporter Net, is equivariant to both pick and place symmetries and can immediately generalize pick and place knowledge to different pick and place poses. We evaluate the new model empirically and show that it is much more sample efficient than the non-symmetric version, resulting in a system that can imitate demonstrated pick and place behavior using very few human demonstrations on a variety of imitation learning tasks.
 # Summary. An optional shortened abstract.

content/publication/haojie_fourtran/index.md

@@ -20,8 +20,8 @@ publishDate: "2024-03-15T00:00:00Z"
 publication_types: ["1"]
 
 # Publication name and optional abbreviated publication name.
-publication: In *ICLR 2023*
-publication_short: In *ICLR 2023*
+publication: In *ICLR 2024*
+publication_short: In *ICLR 2024*
 
 abstract: Many complex robotic manipulation tasks can be decomposed as a sequence of pick and place actions. Training a robotic agent to learn this sequence over many different starting conditions typically requires many iterations or demonstrations, especially in 3D environments. In this work, we propose Fourier Transporter (FourTran), which leverages the two-fold SE(d)xSE(d)  symmetry in the pick-place problem to achieve much higher sample efficiency. FourTran is an open-loop behavior cloning method trained using expert demonstrations to predict pick-place actions on new configurations. FourTran is constrained by the symmetries of the pick and place actions independently. Our method utilizes a fiber space Fourier transformation that allows for memory-efficient computation. Tests on the RLbench benchmark achieve state-of-the-art results across various tasks..
 

content/publication/haojie_imagine/cite.bib

@@ -0,0 +1,8 @@
+@inproceedings{
+huang2024imagination,
+title={{IMAGINATION} {POLICY}: Using Generative Point Cloud Models for Learning Manipulation Policies},
+author={Haojie Huang and Karl Schmeckpeper and Dian Wang and Ondrej Biza and Yaoyao Qian and Haotian Liu and Mingxi Jia and Robert Platt and Robin Walters},
+booktitle={8th Annual Conference on Robot Learning},
+year={2024},
+url={https://openreview.net/forum?id=56IzghzjfZ}
+}

content/publication/haojie_imagine/index.md

@@ -0,0 +1,71 @@
+---
+title: "IMAGINATION POLICY: Using Generative Point Cloud Models for Learning Manipulation Policies"
+authors:
+- Haojie Huang
+- Karl Schmeckpeper
+- Dian Wang
+- Ondrej Biza
+- Yaoyao Qian
+- Haotian Liu
+- Mingxi Jia
+- Robert Platt
+- Robin Walters
+date: "2024-09-10T00:00:00Z"
+doi: ""
+
+# Schedule page publish date (NOT publication's date).
+publishDate: "2024-09-10T00:00:00Z"
+
+# Publication type.
+# Legend: 0 = Uncategorized; 1 = Conference paper; 2 = Journal article;
+# 3 = Preprint / Working Paper; 4 = Report; 5 = Book; 6 = Book section;
+# 7 = Thesis; 8 = Patent
+publication_types: ["1"]
+
+# Publication name and optional abbreviated publication name.
+publication: In *Conference on Robot Learning 2024*
+publication_short: In *CoRL 2024*
+
+abstract: Humans can imagine goal states during planning and perform actions to match those goals. In this work, we propose IMAGINATION POLICY, a novel multi-task key-frame policy network for solving high-precision pick and place tasks. Instead of learning actions directly, IMAGINATION POLICY generates point clouds to imagine desired states which are then translated to actions using rigid action estimation. This transforms action inference into a local generative task. We leverage pick and place symmetries underlying the tasks in the generation process and achieve extremely high sample efficiency and generalizability to unseen configurations. Finally, we demonstrate state-of-the-art performance across various tasks on the RLbench benchmark compared with several strong baselines and validate our approach on a real robot.
+
+# Summary. An optional shortened abstract.
+summary: 
+
+tags:
+- Source Themes
+featured: true
+
+links:
+- name: Website
+  url: https://haojhuang.github.io/imagine_page/
+url_code: https://haojhuang.github.io/imagine_page/
+url_pdf: https://openreview.net/forum?id=56IzghzjfZ
+url_video: https://www.youtube.com/playlist?list=PLtEvDdcT-Ai-Pn9Rx3Lph1ml1xzhTpcRj
+
+# Featured image
+# To use, add an image named `featured.jpg/png` to your page's folder. 
+image:
+  caption: 'Image credit: [**Unsplash**](https://unsplash.com/photos/pLCdAaMFLTE)'
+  focal_point: ""
+  preview_only: false
+
+# Associated Projects (optional).
+#   Associate this publication with one or more of your projects.
+#   Simply enter your project's folder or file name without extension.
+#   E.g. `internal-project` references `content/project/internal-project/index.md`.
+#   Otherwise, set `projects: []`.
+projects:
+- internal-project
+
+# Slides (optional).
+#   Associate this publication with Markdown slides.
+#   Simply enter your slide deck's filename without extension.
+#   E.g. `slides: "example"` references `content/slides/example/index.md`.
+#   Otherwise, set `slides: ""`.
+slides:
+---
+
+
+<!-- Markdown & HTML begins here  -->
+
+<meta http-equiv = "refresh" content = " 0.01 ; url = https://haojhuang.github.io/imagine_page"/>