How Starship Delivery Robots Know Where They Are Going | Joan Lane | Starship Technologies


Joan Lane

(Plus how to make your own 1: 8 scale papercraft robot model)

By: Joan Lane, Mapping Specialist, Starship Technologies

Every September when the new school year begins, many first graders get a little scared of the unknown. It’s not just about starting school and meeting new people, it’s about the journey they have to make every day. They must learn and remember how to navigate the world and how to get out of their classroom on their own. This can be facilitated by a parent who can accompany their child on the first few trips to get acquainted with the path, usually pointing to some interesting landmarks along the path, such as tall or bright buildings or path signs. . Eventually it would be trivial for the child to go to school and remember the path. The child will create a mental map of the world and how to navigate it.

Starship Technologies offers a convenient last mile delivery service where a fleet of pavement delivery robots navigate the world every day. Our robot has completed over 100,000 deliveries. To get from point A to point B, robots need to plan a path ahead, which requires some sort of map. Although there are already many publicly available mapping systems such as Google Maps and OpenStreetMap, they have limitations that are designed with vehicle navigation in mind and mostly focus on vehicle road mapping. Since these delivery robots travel on the sidewalk, they need an accurate map of where it is safe to travel on the sidewalk and where to cross the road, just like a mental map of how a child should go to school safely and on time every day. So how is this map created?

The first step in creating a map for delivery robots is to locate the place of interest and create a preliminary map (2D map) on top of the satellite image representing sidewalks (green), crossings (red) and driveways in the form of simple interconnected lines. (Purple) as illustrated in the picture below.

The system treats this map as a node graph and can be used to create a route from point A to point B. The system can detect the shortest and safest path for a robot and calculate the distance and time it will take. To run this route. The advantage of this process is that it can all be done remotely before any robot physically comes to the site.

The next step is to show the robots what the earth looks like. Like parent-child similarities, robots need to hold hands a bit when exploring an area for the first time. When the robot first drives, the robot’s camera and numerous sensors collect information about the world around it. It includes thousands of lines that come from edge identification of various features, for example buildings, street light poles and roofs. The server can then create a 3D world map offline from these lines that the robot can use. Like a child, the robot now has a model of the world with a guide post and can understand where it is at any time.

Since our robots need to cover different areas at the same time to complete all their deliveries, we need to combine different maps to create an integrated 3D map of a given area in order to be efficient. The consolidated map is created by processing different parts of the new area into pieces until the map finally looks like a giant complete jigsaw puzzle. The server will compile this map based on the line data previously collected by the robot. For example, if the same roof is detected by two robots, the software finds out how it connects to the rest of the map. Each colored line in the image below represents a single part of the mapping trip added to the map.

The final step in the mapping process is to calculate exactly where and how wide the sidewalk is before the robots can drive fully autonomously. It explores the area as a reference, as well as processing robotic recorded camera images while incorporating previously created 2D maps based on satellite imagery.

During this process, more details are added to the map to accurately define safe areas for robots to drive.

Of course, the world around us is not stable. Landscape, construction and renovation change daily and season, which changes the look of the world. How can this affect areas mapped for robots? In fact, the robot’s software handles small to medium changes in the mapped area quite well. 3D models are strong enough and filled with so much data that even if a tree is cut down here or a building torn down there, the position of the robot usually does not challenge its ability to localize or use maps. And, as the robot moves daily, it collects more data that is used to update 3D maps over time. But if an area is completely rebuilt, or new sidewalks are created, the solution is simple. The map must be updated using new data collected by a robot. Then, other robots could drive autonomously in the same area again as if nothing had happened. Keeping maps up to date is crucial for robots to drive safely and autonomously.

As you can tell right now, I really enjoy playing with the concept of 3 dimensional space. Ever since I played the first 3D first person shooter computer game (Wolfenstein 3D), the world of 3D in the digital domain has become my hobby. I wanted to create my own 3D world for computer games, so I found a way to edit existing game levels. Later, I tried my hand at 3D computer modeling, which was interesting to me. With the popularity and affordability of 3D printers, I have also started printing models physically. But long before that, during the summer holidays at school, I liked to design different buildings and vehicle papers. It was an easy and inexpensive way to make something with my own hands, yet it was also interesting to see how a 2D layout on a piece of paper, with little cuts, folds and glue, could turn into a 3D model. Basically, creating a papercraft or “unveiling” a 3D object is the opposite of mapping in one sense. This is creating a 2D layout of the surface of a 3D object.

Since I have a passion for papercraft I decided to create one for our Starship Delivery Robot. The goal of creating this model is to enable others who can enjoy the same passion for creating their own versions of our delivery robots. Creating a paper model is a fun challenge, and once done it creates a beautiful decorative item. Creating a papercraft model, like creating a 3D map for a robot, requires precision, precision, and spatial thinking about how all the parts fit together. Also a good bit of patience.

I have created some guidelines for you to create your own papercraft delivery robot and I want to see your efforts. Have fun and good luck creating your own delivery robot paper model!

Please post a picture of your robots on Instagram and tag StarshipRobots so I can find them!

Find Starship Delivery Robot Papercraft models and instructions Here

Starship Technologies. Starship® Delivery robot design and description technology aspect is protected by ownership and copyright and other intellectual property laws.



Source link

Leave a Reply

Your email address will not be published. Required fields are marked *