[ad_1]
(And how to make your own 1:8 scale paper model robot model)
Author: Joan Lääne, Surveying and Mapping Specialist at Starship Technologies
At the beginning of the new school year in September every year, many first-year students are a little afraid of the unknown. It’s not only about starting school and the new friends they will meet, but also the journey they need to take every day. They must learn and remember how to navigate the world on their own and how to travel to and from the classroom. Parents can accompany their children to travel back and forth several times to make them more familiar with the path, usually pointing out some interesting landmarks along the way, such as tall or bright buildings or signs on the path, which can make this easier. Finally, the child Going to school and remembering the road will be trivial. The child will form a mental map of the world and how to navigate it.
Starship Technologies provides a convenient last mile delivery service, with sidewalk delivery robots sailing around the world every day. Our robot has completed more than 100,000 deliveries. In order to get from point A to point B, the robot needs to plan a route in advance, which in turn requires some kind of map. Although there are many publicly available map systems, such as Google Maps and OpenStreetMaps, their limitation is that they are designed with car navigation in mind and mainly focus on drawing car roads. Because these delivery robots drive on the sidewalk, they need an accurate map showing which places on the sidewalk are safe and where you can cross the road, just like a child needs a mental map on how to go to school safely and on time every day Same. So how is this map generated?
The first step in creating a map for the delivery robot is to detect the area of interest and generate a preliminary map (2D map) in the form of simple interconnecting lines on the satellite imagery. These lines represent sidewalks (green) and intersections (red) And the lane (purple) is shown in the picture below.
The system treats this map as a node graph, which can be used to generate a route from point A to point B. The system can identify the shortest and safest path the robot has to take, and calculate the distance and time it has to travel to drive this route. The advantage of this process is that all of this can be done remotely before any robot actually arrives on site.
The next step is to show the robot what the world looks like. Similar to the parent-child analogy, the robot needs to hold hands a little bit when exploring an area for the first time. When the robot drives for the first time, the camera and a large number of sensors on the robot collect data about the world around it. This includes thousands of lines from detecting edges of different features, such as buildings, street light poles, and roofs. Then, the server can create a 3D world map that the robot can use based on these lines offline. Like a child, the robot now has a world model with a guide rod, which can understand its position at any given time.
Since our robot needs to cover different areas at the same time to complete all deliveries, various maps need to be put together to create a unified 3D map of a given area to improve efficiency. The unified map is created piece by piece by processing different parts of the new area until the final map looks like a huge puzzle. The server will put this map together based on the line data previously collected by the robot. For example, if two robots detect the same roof, the software will calculate how it connects to the rest of the map. Each colored line in the image below represents a single map itinerary added to the map.
Before the robot can drive fully autonomously, the last step in the mapping process is to accurately calculate the position and width of the sidewalk. This is created by processing the camera image recorded by the robot as it explores the area as a reference and combining it with a 2D map previously created based on satellite imagery.
During this process, more detailed information will be added to the map to accurately define the safe area where the robot can travel.
Of course, the world around us is not static. The landscape, architecture and decoration change daily and seasonally, which changes the face of the world. How will this affect the robot’s mapping area? In fact, the robot’s software can handle small to medium changes in the mapping area very well. The 3D model is powerful enough and filled with such a large amount of data, so felling a tree here or demolishing a building there usually does not pose a challenge to the robot’s ability to locate its location or use a map. And, in addition, as the robot travels around every day, it will continue to collect more data to update the 3D map over time. But if an area is completely remodeled or new sidewalks are built, the solution is simple. The map must be updated with new data collected by the robot. After that, other robots can drive autonomously in the same area again, as if nothing had happened. Keeping the map updated is essential to keep the robot safe and autonomous driving.
Without a doubt, you can now see that I really like playing around with the concept of 3D space. Since I played the first 3D first-person shooter computer game (Wolfenstein 3D), the 3D world in the digital domain has become my interest. I wanted to make my own 3D world for computer games, so I found a way to edit existing game levels. Later, I also tried 3D computer modeling, which I found very interesting. With the popularity and affordability of 3D printers, I also started to physically print models. But long before that, during the school summer vacation, I like to make paper models of different buildings and vehicles. This is a simple and inexpensive way to create things with my own hands, but it is also interesting to see that a 2D layout on a piece of paper can be turned into a 3D model with a little cutting, folding and gluing. Basically, the paper art or “unfolding” of creating 3D objects is in a sense the opposite of mapping. It is creating a 2D layout of the surface of a 3D object.
Since I am passionate about paper art, I decided to make one for our Starship delivery robot. The purpose of making this model is to allow other people who may have the same passion as me to create their own version of the delivery robot. Creating a paper model is an interesting challenge, and once completed, it can also be a nice decoration. Like generating 3D maps for robots, making paper models requires precision, accuracy, and spatial thinking about how all the components fit together. Still have a little patience.
I have created some instructions for you to create your own paper art delivery robot, and I would love to see your efforts. Make your own paper model of the delivery robot, have fun and good luck!
Please post photos of your robots on Instagram and tag @StarshipRobots so that I can find them!
Please find the Starship delivery robot paper model and instructions here
© Starship Technologies. The design and the described technical aspects of the Starship® delivery robot are proprietary and protected by copyright and other intellectual property laws
[ad_2]
Source link
