Skip to content

Commit d71c13a

Browse files
committed
image layout
fix image spacing and layout (not ideal but much better
1 parent a242d70 commit d71c13a

1 file changed

Lines changed: 22 additions & 76 deletions

File tree

_pages/research.md

Lines changed: 22 additions & 76 deletions
Original file line numberDiff line numberDiff line change
@@ -1,8 +1,8 @@
11
---
22
layout: page
3-
title: Research Agenda
3+
title: research
44
permalink: /research/
5-
description:
5+
description: PAIR research thrusts
66
nav: true
77
nav_order: 3
88
display_categories: [work, fun]
@@ -14,39 +14,39 @@ PAIR group blends ideas in _Causality_, _Perception_, and _Reinforcement Learnin
1414

1515
As a group we pride ourselves on building and applying learning algorithms on different real robot platforms.
1616

17-
<div class="row mt-3">
17+
<div class="row mt-3 align-items-center justify-content-around">
1818
<div class="col-sm mt-3 mt-md-0">
19-
{% include figure.liquid path="assets/img/res-planning-robot1-small.gif" class="img-fluid rounded z-depth-1" zoomable=true width="70%" %}
19+
{% include figure.liquid path="assets/img/res-planning-robot1-small.gif" class="img-fluid rounded z-depth-1 mx-auto d-block" zoomable=true %}
2020
</div>
2121
<div class="col-sm mt-3 mt-md-0">
22-
{% include figure.liquid path="assets/img/res-cavin.gif" class="img-fluid rounded z-depth-1" zoomable=true width="70%" %}
22+
{% include figure.liquid path="assets/img/res-cavin.gif" class="img-fluid rounded z-depth-1 mx-auto d-block" zoomable=true %}
2323
</div>
2424
<div class="col-sm mt-3 mt-md-0">
25-
{% include figure.liquid path="assets/img/res-multimodal-test.gif" class="img-fluid rounded z-depth-1" zoomable=true %}
25+
{% include figure.liquid path="assets/img/res-multimodal-test.gif" class="rounded z-depth-1 mx-auto d-block" zoomable=true %}
2626
</div>
2727
</div>
2828
<div class="caption">
2929
Personal & Service Robotics
3030
</div>
3131

32-
<div class="row mt-3">
32+
<div class="row mt-3 align-items-center justify-content-around">
3333
<div class="col-sm mt-3 mt-md-0">
34-
{% include figure.liquid path="assets/img/res-cutting.gif" class="img-fluid rounded z-depth-1" zoomable=true width="70%" %}
34+
{% include figure.liquid path="assets/img/res-cutting.gif" class="img-fluid rounded z-depth-1 mx-auto d-block" zoomable=true %}
3535
</div>
3636
<div class="col-sm mt-3 mt-md-0">
37-
{% include figure.liquid path="assets/img/res-suturing.gif" class="img-fluid rounded z-depth-1" zoomable=true width="70%" %}
37+
{% include figure.liquid path="assets/img/res-suturing.gif" class="img-fluid rounded z-depth-1 mx-auto d-block" zoomable=true %}
3838
</div>
3939
<div class="col-sm mt-3 mt-md-0">
40-
{% include figure.liquid path="assets/img/res-acubot.gif" class="img-fluid rounded z-depth-1" zoomable=true %}
40+
{% include figure.liquid path="assets/img/res-acubot.gif" class="img-fluid rounded z-depth-1 mx-auto d-block" zoomable=true %}
4141
</div>
4242
</div>
4343
<div class="caption">
4444
Surgical & Healthcare Robotics
4545
</div>
4646

47-
<div class="row mt-3">
47+
<div class="row mt-3 align-items-center justify-content-around">
4848
<div class="col-sm mt-3 mt-md-0">
49-
{% include figure.liquid path="assets/img/res-laikago-skateboard.gif" class="img-fluid rounded z-depth-1" zoomable=true %}
49+
{% include figure.liquid path="assets/img/res-laikago-skateboard.gif" class="img-fluid rounded z-depth-1 " zoomable=true %}
5050
</div>
5151
<div class="col-sm mt-3 mt-md-0">
5252
{% include figure.liquid path="assets/img/res-laikago-dr.gif" class="img-fluid rounded z-depth-1" zoomable=true %}
@@ -71,15 +71,15 @@ Structured biases upend contemporary methods in all four dimensions, pointing to
7171
- Algorithms: [C-Learning](https://arxiv.org/abs/2011.12363), [LEAF](http://arxiv.org/abs/2005.10934), [OCEAN](http://arxiv.org/abs/2008.07087)
7272
- Architectures: [Deep-Dense nets in RL](https://sites.google.com/view/d2rl/home)
7373

74-
<div class="row mt-3">
74+
<div class="row mt-3 justify-content-around align-items-center">
7575
<div class="col-sm-3 mt-3 mt-md-0">
76-
{% include figure.liquid path="assets/img/res-tog.png" class="img-fluid rounded z-depth-1" zoomable=true %}
76+
{% include figure.liquid path="assets/img/res-tog.png" class="img-fluid rounded z-depth-1 mx-auto d-block" zoomable=true %}
7777
</div>
7878
<div class="col-sm-3 mt-3 mt-md-0">
79-
{% include figure.liquid path="assets/img/res-laser-intro.jpg" class="img-fluid rounded z-depth-1" zoomable=true %}
79+
{% include figure.liquid path="assets/img/res-laser-intro.jpg" class="img-fluid rounded z-depth-1 mx-auto d-block" zoomable=true %}
8080
</div>
8181
<div class="col-sm-5 mt-3 mt-md-0">
82-
{% include figure.liquid path="assets/img/res-clearning.gif" class="img-fluid rounded z-depth-1" zoomable=true %}
82+
{% include figure.liquid path="assets/img/res-clearning.gif" class="img-fluid rounded z-depth-1 mx-auto d-block" zoomable=true %}
8383
</div>
8484
</div>
8585
- 3D Vision: Object and Scene representations for manipulation.
@@ -90,7 +90,7 @@ Structured biases upend contemporary methods in all four dimensions, pointing to
9090

9191
Causal understanding is one of key pillars of my current and future agenda. A simulator is a generative world model, and similarly follows a system of structural mechanisms. However, model learning focuses solely on statistical dependence, while Causal Models go beyond it to build representations that support intervention, planning, and modular reasoning. These methods provide a concrete step towards bridging vision and robotics through sub-goal inference and counterfactual imagination.
9292

93-
<div class="row mt-3">
93+
<div class="row mt-3 justify-content-around align-items-center">
9494
<div class="col-sm-9 mt-3 mt-md-0">
9595
{% include figure.liquid path="assets/img/res-vcdn.gif" class="img-fluid rounded z-depth-1" zoomable=true %}
9696
</div>
@@ -108,7 +108,7 @@ Causal understanding is one of key pillars of my current and future agenda. A si
108108
Data-driven methods help RL in exploration and reward specification. Robot learning, however, is limited by modest-sized real data.
109109
Access to data brings new algorithmic opportunities to robotics, as it did in vision and language. However, it also poses challenges due to static nature of data and covariate shifts.
110110

111-
<div class="row mt-3">
111+
<div class="row mt-3 align-items-center">
112112
<div class="col-sm mt-3 mt-md-0">
113113
{% include figure.liquid path="assets/img/res-rt-alps.gif" class="img-fluid rounded z-depth-1" zoomable=true %}
114114
</div>
@@ -130,7 +130,7 @@ Access to data brings new algorithmic opportunities to robotics, as it did in vi
130130
Procedural reasoning, such as in robotics, needs both skills and their structured composition for interaction planning towards a higher-order objective.
131131
However, manual composition of skills via a finite state-machine design is both tedious and unscalable. Thus the need for inductive bias is intensified for cognitive reasoning. I have developed imitation guided policy learning in abstract spaces for hierarchically structure tasks.
132132

133-
<div class="row mt-3">
133+
<div class="row mt-3 align-items-center">
134134
<div class="col-sm mt-3 mt-md-0">
135135
{% include figure.liquid path="assets/img/res-ntp-small.gif" class="img-fluid rounded z-depth-1" zoomable=true %}
136136
</div>
@@ -145,65 +145,11 @@ However, manual composition of skills via a finite state-machine design is both
145145

146146
The algorithmic ideas have been motivated by problems in mobility and manipulation in robotics, and have been evaluated on various physical robot platforms.
147147

148-
<div class="row mt-3">
149-
<div class="col-sm mt-3 mt-md-0">
150-
{% include figure.liquid path="assets/img/real-robots-garg.png" class="img-fluid rounded z-depth-1" width="75%" zoomable=true %}
148+
<div class="row mt-3 align-items-center justify-content-around">
149+
<div class="col-sm-8 mt-3 mt-md-0">
150+
{% include figure.liquid path="assets/img/real-robots-garg.png" class="img-fluid rounded z-depth-1" zoomable=true %}
151151
</div>
152152
</div>
153153
- Personal & Service Robotics: [Tool Use](https://sites.google.com/view/task-oriented-grasp), [Task Planning](https://www.youtube.com/watch?v=OdqJuvAHvGE), [Assembly](https://www.youtube.com/watch?v=NwMukXa8kys&feature=youtu.be), [Pick & place](https://ai.stanford.edu/mech-search/multistep), [Laundry Layout](https://roboturk.stanford.edu/realrobotdataset#tasks), [Assistive Teleoperation](http://arxiv.org/abs/1909.09674), [Mechanical Search](http://arxiv.org/abs/1903.01588)
154154
- Surgical & Healthcare: [Debridement](https://youtu.be/beVWB6NtAaA), [Suturing](https://youtu.be/z1ehShXFToc), [Cutting](https://youtu.be/l6gQg2VbGcc), [Extraction](https://www.youtube.com/watch?v=YiPq9t0tR3U), [Radiotherapy](https://www.youtube.com/watch?v=Kk_wHiu8nGg&feature=youtu.be)
155155
- Legged Robotics: [Contact Planning](https://news.developer.nvidia.com/contact-adaptive-controller-locomotion), [Domain Randomization](https://www.pair.toronto.edu/understanding-dr)
156-
157-
<!-- pages/projects.md -->
158-
159-
{% comment %}
160-
161-
<div class="projects">
162-
{% if site.enable_project_categories and page.display_categories %}
163-
<!-- Display categorized projects -->
164-
{% for category in page.display_categories %}
165-
<a id="{{ category }}" href=".#{{ category }}">
166-
<h2 class="category">{{ category }}</h2>
167-
</a>
168-
{% assign categorized_projects = site.projects | where: "category", category %}
169-
{% assign sorted_projects = categorized_projects | sort: "importance" %}
170-
<!-- Generate cards for each project -->
171-
{% if page.horizontal %}
172-
<div class="container">
173-
<div class="row row-cols-1 row-cols-md-2">
174-
{% for project in sorted_projects %}
175-
{% include projects_horizontal.liquid %}
176-
{% endfor %}
177-
</div>
178-
</div>
179-
{% else %}
180-
<div class="row row-cols-1 row-cols-md-3">
181-
{% for project in sorted_projects %}
182-
{% include projects.liquid %}
183-
{% endfor %}
184-
</div>
185-
{% endif %}
186-
{% endfor %}
187-
{% else %}
188-
<!-- Display projects without categories -->
189-
{% assign sorted_projects = site.projects | sort: "importance" %}
190-
<!-- Generate cards for each project -->
191-
{% if page.horizontal %}
192-
<div class="container">
193-
<div class="row row-cols-1 row-cols-md-2">
194-
{% for project in sorted_projects %}
195-
{% include projects_horizontal.liquid %}
196-
{% endfor %}
197-
</div>
198-
</div>
199-
{% else %}
200-
<div class="row row-cols-1 row-cols-md-3">
201-
{% for project in sorted_projects %}
202-
{% include projects.liquid %}
203-
{% endfor %}
204-
</div>
205-
{% endif %}
206-
{% endif %}
207-
</div>
208-
209-
{% endcomment %}

0 commit comments

Comments
 (0)