You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
- 3D Vision: Object and Scene representations for manipulation.
@@ -90,7 +90,7 @@ Structured biases upend contemporary methods in all four dimensions, pointing to
90
90
91
91
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.
{% include figure.liquid path="assets/img/res-vcdn.gif" class="img-fluid rounded z-depth-1" zoomable=true %}
96
96
</div>
@@ -108,7 +108,7 @@ Causal understanding is one of key pillars of my current and future agenda. A si
108
108
Data-driven methods help RL in exploration and reward specification. Robot learning, however, is limited by modest-sized real data.
109
109
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.
110
110
111
-
<divclass="row mt-3">
111
+
<divclass="row mt-3 align-items-center">
112
112
<div class="col-sm mt-3 mt-md-0">
113
113
{% include figure.liquid path="assets/img/res-rt-alps.gif" class="img-fluid rounded z-depth-1" zoomable=true %}
114
114
</div>
@@ -130,7 +130,7 @@ Access to data brings new algorithmic opportunities to robotics, as it did in vi
130
130
Procedural reasoning, such as in robotics, needs both skills and their structured composition for interaction planning towards a higher-order objective.
131
131
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.
132
132
133
-
<divclass="row mt-3">
133
+
<divclass="row mt-3 align-items-center">
134
134
<div class="col-sm mt-3 mt-md-0">
135
135
{% include figure.liquid path="assets/img/res-ntp-small.gif" class="img-fluid rounded z-depth-1" zoomable=true %}
136
136
</div>
@@ -145,65 +145,11 @@ However, manual composition of skills via a finite state-machine design is both
145
145
146
146
The algorithmic ideas have been motivated by problems in mobility and manipulation in robotics, and have been evaluated on various physical robot platforms.
147
147
148
-
<divclass="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 %}
0 commit comments