Update index.html

docs/index.html

@@ -26,13 +26,14 @@ <h1>MOPA: Modular Object Navigation with PointGoal Agents </h1>
                 <a href="https://www.tommasocampari.com/" target="_blank">Tommaso Campari<sup>2,3</sup></a>
                 <a href="https://unnat.github.io/" target="_blank">Unnat Jain<sup>4</sup></a>
                 <a href="https://msavva.github.io/ target=" _blank"">Manolis Savva<sup>1</sup></a>
-                <a href="https://angelxuanchang.github.io/" target="_blank">Angel X. Chang<sup>1</sup></a>
+                <a href="https://angelxuanchang.github.io/" target="_blank">Angel X. Chang<sup>1,5</sup></a>
             </div>
 
             <div class="col-lg-12 col-md-12 col-sm-12 col-xs-12 text-center">
                 <span><sup>1</sup>Simon Fraser University, &nbsp; <sup>2</sup>University of Padova, &nbsp;
                     <sup>3</sup>FBK,
-                    &nbsp; <sup>4</sup>Meta AI </span>
+                    &nbsp; <sup>4</sup>Meta AI,
+                    &nbsp; <sup>5</sup>Amii </span>
             </div>
 
             <div class="col-lg-12 col-md-12 col-sm-12 col-xs-12 text-center">
@@ -58,27 +59,7 @@ <h1>MOPA: Modular Object Navigation with PointGoal Agents </h1>
                     <h2>Abstract</h2>
                     <div class="col-lg-12 col-md-12 col-sm-12 col-xs-12 text-justify">
                         <p>
-                            Our work focuses on the Multi-Object Navigation (MultiON) task, where an agent needs to
-                            navigate to
-                            multiple objects in a given sequence. We systematically investigate the inherent modularity
-                            of this
-                            task by dividing our approach to contain four modules: (a) an object detection module
-                            trained to
-                            identify objects from RGB images, (b) a map building module to build a semantic map of the
-                            observed
-                            objects, (c) an exploration module enabling the agent to explore its surroundings, and
-                            finally (d) a
-                            navigation module to move to identified target objects. We focus on the navigation and the
-                            exploration modules in this work. We show that we can effectively leverage a PointGoal
-                            navigation
-                            model in the MultiON task instead of learning to navigate from scratch. Our experiments show
-                            that a
-                            PointGoal agent-based navigation module outperforms analytical path planning on the MultiON
-                            task. We
-                            also compare exploration strategies and surprisingly find that a random exploration strategy
-                            significantly outperforms more advanced exploration methods. We additionally create MultiON
-                            2.0, a
-                            new large-scale dataset as a test-bed for our approach.
+                            We propose a simple but effective modular approach MOPA (Modular ObjectNav with PointGoal agents) to systematically investigate the inherent modularity of the object navigation task in Embodied AI. MOPA consists of four modules: (a) an object detection module trained to identify objects from RGB images, (b) a map building module to build a semantic map of the observed objects, (c) an exploration module enabling the agent to explore the environment, and (d) a navigation module to move to identified target objects. We show that we can effectively reuse a pretrained PointGoal agent as the navigation model instead of learning to navigate from scratch, thus saving time and compute. We also compare various exploration strategies for MOPA and find that a simple uniform strategy significantly outperforms more advanced exploration methods.
                         </p>
                     </div>