Added new paragraphs and pushing sim image

Author: steph1111

_includes/post-custom-rs-march-25.html

@@ -122,15 +122,37 @@
         </h3>
         <div class="text has-text-justified">
             <p>
-                Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do
-                eiusmod tempor incididunt ut labore et
-                dolore magna aliqua. Ut enim ad minim veniam, quis nostrud
-                exercitation ullamco laboris nisi ut aliquip
-                ex ea commodo consequat. Duis aute irure dolor in reprehenderit
-                in voluptate velit esse cillum dolore eu
-                fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
-                proident, sunt in culpa qui officia
-                deserunt mollit anim id est laborum.
+                Computer vision acts as the eyes of a robot,
+                allowing it to perceive its surroundings and coordinate
+                the data through integrated software and hardware to its other
+                components. We have set up an NVIDIA Jetson as the primary
+                computing platform for our project, this will allow us to
+                leverage its GPU acceleration to run our own version of the
+                YOLOV5 model for real-time object detection. We have been
+                working on building a lot of OpenCV tools that will help us with
+                preprocessing tasks such as image filtering, noise reduction,
+                and edge detection. This will improve the quality of our input
+                data for the model. Our plan is to tweak and further develop a
+                custom trained YOLOV5 model by gathering our own data from real
+                world data collection and testing within the real world. To
+                gather this data we will be using stereo vision footage from our
+                ZED 2i camera and preprocessing the data with OpenCV, then using
+                the data to fine tune the model to account for water distortion,
+                object occlusions, and lighting inconsistencies. By combining
+                the Jetsons hardware acceleration, OpenCV's tools, and YOLOV5
+                object detection capabilities, we will deploy a highly efficient
+                and robust visual processing system that will be capable of
+                real-time inference within dynamic underwater scenarios.
+                <br>
+                Due to the surge in AI popularity, our progress on computer
+                vision has faced significant delays as we struggled to acquire a
+                Jetson Orin Nano, our preferred board for vision processing. In
+                the meantime, we borrowed a Jetson Nano, but this introduced
+                another challenge—the board officially supports only Ubuntu
+                18.04, while our ROS Humble software stack requires Ubuntu
+                22.04. One of our members has been working on upgrading the
+                system and has successfully installed Ubuntu 20.04, bringing us
+                a step closer to compatibility.
             </p>
         </div>
 
@@ -140,15 +162,13 @@
         </h3>
         <div class="text has-text-justified">
             <p>
-                Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do
-                eiusmod tempor incididunt ut labore et
-                dolore magna aliqua. Ut enim ad minim veniam, quis nostrud
-                exercitation ullamco laboris nisi ut aliquip
-                ex ea commodo consequat. Duis aute irure dolor in reprehenderit
-                in voluptate velit esse cillum dolore eu
-                fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
-                proident, sunt in culpa qui officia
-                deserunt mollit anim id est laborum.
+                With basic navigation implemented, our goals are set towards
+                completing the computer vision and path planning systems.
+                Computer Vision is absolutely necessary for localization, and is
+                by far the most crucial component we are missing. The addition
+                of path planning algorithms will allow for the creation of more
+                complex paths that can minimize distance while avoiding
+                obstacles in unmapped terrain.
             </p>
         </div>
 
@@ -312,15 +332,15 @@
             <div
                 class="column has-text-justified-desktop has-justified-tablet has-justified-fullhd has-text-justified-widescreen">
                 <p>
-                    Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed
-                    do eiusmod tempor incididunt ut labore
-                    et dolore magna aliqua. Ut enim ad minim veniam, quis
-                    nostrud exercitation ullamco laboris nisi ut
-                    aliquip ex ea commodo consequat. Duis aute irure dolor in
-                    reprehenderit in voluptate velit esse
-                    cillum dolore eu fugiat nulla pariatur. Excepteur sint
-                    occaecat cupidatat non proident, sunt in
-                    culpa qui officia deserunt mollit anim id est laborum.
+                    The Cabrillo Robotics Club recently participated in MESA Day
+                    at the University of California, Santa Cruz, an event that
+                    brought together over 250 middle and high school students
+                    from Santa Cruz and neighboring. Throughout the day,
+                    students engaged in hands-on activities and connected with
+                    industry professionals and STEM organizations, including our
+                    club. We showcased our SeaHawk II and LazerShark robots and
+                    led an interactive bristle bot activity in which students
+                    got to build and race simple bots.
                 </p>
             </div>
             <div
@@ -360,7 +380,7 @@
                 allowing us to use their facilities to machine our electrical
                 housing.
 
-                Lastly, we thank Cabrillo Engineering Department alum Mark
+                Lastly, we thank Cabrillo Engineering Department alumnus Mark
                 Cowell for funding our RoboSub competition registration.
 
                 There are many other organizations and individuals we have to