How Starship Delivery Robots know where they are going | by Joan Lääne | Starship Technologies
(more how to make your own 1: 8 scale paper robot model)
by: Joan Lääne, Mapping Specialist, Starship Technologies
Every year in September, when the new school year begins, many first graders are a little afraid of the unknown. Not only about going back to school and the new people they will meet, but also about the journey they have to take each day. They must learn and remember how to navigate the world and the path to and from their classroom on their own. This can be facilitated by a parent who can accompany their child on the first round trips to familiarize them with the path, usually pointing out some interesting landmarks along the way, such as tall or lighted buildings or signs on the path. path. Eventually, it will be trivial for the child to go to school and remember the way. The child will have formed a mental map of the world and how to navigate it.
Starship Technologies provides a convenient last mile delivery service with fleets of sidewalk delivery robots that roam the world every day. Our robots have made more than 100,000 deliveries. To get from point A to point B, robots have to plan a route in advance, which in turn requires some sort of map. Even though there are already many publicly available mapping systems such as Google Maps and OpenStreetMaps, they have the limitation of being designed for car navigation and mainly focus on car road mapping. Since these delivery robots move on sidewalks, they need an accurate map of where it is safe to move on sidewalks and where to cross streets, just like a child needs a map. to get to school safely and on time every day. So how is this map generated?
The first step in creating a map for delivery robots is to locate the area of interest and generate a preliminary map (2D map) above the satellite imagery in the form of simple interconnected lines representing the sidewalks (green), crossings (red) and alleys. (purple) as shown in the image below.
The system treats this map as a graph of nodes and can be used to generate a route from point A to point B. The system can identify the shortest and safest path for the robot to take and also calculate the route. distance and time it would take. to navigate this route. The advantage of this process is that everything can be done remotely before the robots physically arrive at the site.
The next step is to show the robots what the world is like. Similar to the parent-child analogy, robots need a bit of a hand grip the first time they explore an area. When the robot rolls for the first time, cameras and a multitude of sensors on the robot collect data about the world around it. These include thousands of lines that come from sensing the edges of different 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 then use. Like the child, the robot now has a model of the world with guide poles and can understand where it is at any time.
Since our robots have to cover different areas at the same time to make all their deliveries, to be effective, different maps need to be put together to create a unified 3D map of a given area. The unified map is created piece by piece by processing the different pieces of the new area until the map finally looks like a huge completed puzzle. The server will assemble this card based on the row data that the robot collected previously. For example, if the same roof was detected by two robots, the software determines how it connects with the rest of the board. Each colored line in the image below represents a single part of a map trip added to the map.
The last step in the mapping process, before the robots can drive fully autonomously, is to calculate exactly where and how wide the sidewalk is. This is created by processing the camera images that the robot recorded while exploring the area as a reference as well as incorporating the 2D map created previously based on the satellite imagery.
During this process, more details are added to the map to precisely define the safe zones where the robots can drive.
Of course, the world around us is not static. There are daily and seasonal changes in the landscape, constructions and renovations, which change the way the world looks. How can this affect the areas mapped for robots? In fact, the robot’s software handles small to medium changes in the mapped area quite well. 3D models are robust enough and filled with such amounts of data that a tree cut down here or a building destroyed there usually doesn’t pose a problem with the robot’s ability to locate its position or use the map. Additionally, as the robot moves each day, it continues to collect more data which is used to update 3D maps over time. But if an area is completely remodeled or new sidewalks are built, the solution is simple. The map needs to be updated with new data collected by a robot. Then, other robots can again drive autonomously in the same area as if nothing had happened. Keeping maps up to date is crucial for robots to drive safely and independently.
As you can no doubt tell by now, I really enjoy playing with the concepts of 3-dimensional space. Since playing the first 3D first-person shooter video game (Wolfenstein 3D), the world of digital 3D has become one of my interests. I wanted to create my own 3D worlds for computer games, so I found ways to modify the existing game levels. Later, I also tried my hand at 3D computer modeling, which I found interesting. With the popularization and accessibility of 3D printers, I also started to physically print models. But long before that, during the summer school holidays, I loved making paper models of different buildings and vehicles. 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 piece of paper, with a little bit of cutting, folding and gluing, can turn into a 3D model. Basically, papercrafting a 3D object or “unfolding” is, in a sense, the reverse of mapping. It creates the 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 robots. The goal of making this model is to allow 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’s also a nice decorative item. As with generating 3D maps for the robot, making a papercraft model requires precision, precision, and spatial thinking about how all of the pieces fit together. A good bit of patience too.
I have created some instructions for you to make your own papercraft delivery robot and would love to see your efforts. Have fun and good luck making your own delivery robot paper model!
Please post a photo of your robot on Instagram and tag @StarshipRobots so I can find them!
Please find the Starship Delivery Robot papercraft model and instructions here
© Starship Technologies. The design of the Starship® delivery robot and the appearance of the technologies described are proprietary and protected by copyright and other intellectual property laws.
Please feel free to contact us for more detail about us, visiting our Contact page.