How Starship Delivery Robots Know Where They Go by Joan Lääne | Stellar ship technology


(plus how to make your own paper robot model in 1: 8 scale)

by: Joan Lääne, Mapping Specialist, Starship Technologies

Every September, when the new school year begins, many first-graders are a little afraid of the unknown. Not only for starting school and new people to meet, but also for the journey they have to take every day. They need to learn and remember how to navigate the world and the path to and from the classroom on their own. This can be facilitated by a parent who can accompany their child on the first few trips back and forth to get them better acquainted with the road, usually pointing out some interesting landmarks along the way, such as tall or bright buildings or road signs. the path. In the end, the child will be trivial to go to school and remember the way. The child will have formed a mental map of the world and how to navigate in it.

Starship Technologies provides a convenient last mile delivery service with a fleet of sidewalk delivery robots that move around the world every day. Our robots have made over 100,000 deliveries. To get from point A to point B, the robots must plan a route ahead, which in turn requires a map. Although there are already many publicly available mapping systems such as Google Maps and OpenStreetMaps, they have the limitation that they are designed with car navigation in mind and focus mostly on road mapping. Because these delivery robots travel on sidewalks, they need an exact map of where it is safe to travel on sidewalks and where to cross streets, just as a child needs a mental map of how to get to school safely and on time every day. So how is this card generated?

The first step in creating a delivery robot map is to study the area of ​​interest and generate a preliminary map (2D map) on satellite images in the form of simple interconnected lines representing sidewalks (green), intersections (red) and alleys (purple). as shown in the image below.

The system treats this map as a node graph and it can be used to generate a route from point A to point B. The system can identify the shortest and safest way for the robot to go, as well as calculate the distance and the time it will take to drive on this route. The advantage of this process is that everything can be done remotely before the robots physically arrive on site.

The next step involves showing the robots what the world looks like. Like the parent-child analogy, robots need a little handshake when they first explore an area. When the robot first drives, the robot’s cameras and multiple sensors collect data about the world around it. They include thousands of lines that come from detecting edges of various characteristics, such as buildings, street lighting poles and roofs. The server can then create an offline 3D map of the world from these rows that the robot can use. Like a child, the robot already has a model of the world with leadership positions and can understand where it is at any given moment.

Because our robots have to cover different areas at once, in order to complete all their deliveries, in order to be effective, we need to assemble different maps to create a single 3D map of a given area. The merged map is created piece by piece by processing the different pieces of the new area, while in the end the map looks like a huge completed puzzle. The server will collect this card based on the linear data that the robot has previously collected. For example, if the same roof was detected by two robots, then the software determines how it connects to the rest of the card. Each colored line in the image below represents a separate piece of mapping added to the map.

The last step in the mapping process, before the robots can move completely autonomously, is to calculate exactly where and how wide the sidewalk is. This is created by processing the images from the camera recorded by the robot while exploring the area as a starting point, as well as by including a pre-created 2D map based on satellite images.

During this process, more details are added to the map to pinpoint safe areas where robots can drive.

Of course, the world around us is not static. There are daily and seasonal changes in the landscape, constructions and renovations that change the way the world looks. How can this affect the mapped areas 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 full of so much data that a tree cut down here or a building knocked down there is usually not a challenge to the robot’s ability to locate its position or use the map. In addition, as the robot moves every day, it continues to collect more data, which is used to update 3D maps over time. But if an area is completely redesigned or new sidewalks are built, then the solution is simple. The map must be updated using new data collected by a robot. Then other robots can drive autonomously again in the same area as if nothing had happened. Updating maps is crucial to keeping robots moving safely and autonomously.

As you can say without a doubt so far, I really like to play with the concepts of three-dimensional space. Ever since I played the first 3D computer game for first-person shooting (Wolfenstein 3D), the world of 3D in the digital field has become my interest. I wanted to create my own 3D worlds for computer games, so I found ways to edit existing game levels. Later I tried 3D computer modeling, which I found interesting. With the popularity and availability of 3D printers, I began to physically print models. But long before that, during summer vacations at school, I loved to make models of different buildings and vehicles out of paper. It was an easy and inexpensive way to create something with my own hands, but it was also interesting to see how a 2D layout on a sheet of paper, with a little cutting, folding and gluing, could be turned into a 3D model. In principle, creating paper on a 3D object or “unfolding” is in a sense the opposite of mapping. It creates a 2D layout on the surface of a 3D object.

Since I have a passion for writing, I decided to create one for our Starship delivery robots. The purpose of creating this model is to enable others who might enjoy the same passions as me to create their own version of our delivery robots. Creating a paper model is a fun challenge and once done it makes it a nice decorative element. As with generating 3D maps for the robot, making a paper model requires precision, accuracy and spatial thinking about how all the parts fit together. Also a little patience.

I have created some instructions for you to create your own paper delivery robot and I would like to see your efforts. Have fun and good luck by making your own paper delivery robot model!

Please post a photo of your robot on Instagram and tag @StarshipRobots so I can find them!!

Please find the model and instructions of the Starship delivery robot here

© Starship Technologies. The design of the Starship® delivery robot and the aspect of the described technologies are property and are protected by copyright and other intellectual property laws.


Source link

Leave a Reply

Your email address will not be published.