We are often asked about the \u201crules of the road\u201d and how humans and technology should interact on the pavement. So I wanted to give you a little insight into how Starship robots navigate their communities. in the middle of the trip.<\/p>\n
First, let’s take a step back and look at the rules of the road. These have been around for decades and are what every road vehicle must follow, including self-driving cars. Among other things, you must keep your lane, direct before turning, and maintain a proper braking distance. On the other hand, the pavement is a different environment, so understanding its surroundings and identifying\/predicting pedestrian behavior is much more difficult for pedestrians, let alone robots!<\/p>\n
For the past eight years, Starship has been working to solve this challenge with robots. Learned how to behave on the pavement, used it well, and became accepted as part of the community.<\/p>\n And robots don’t just roam everywhere. Before launching the new Starship food delivery location, the pavement is pre-mapped so that the robot can stay within a designated area and know which routes it can or cannot take.<\/p>\n The robot then uses a combination of cameras, sensors, artificial intelligence and machine learning to navigate these routes and, importantly, avoid people, animals and obstacles.<\/p>\n Learn more about.<\/p>\n How will the robot react?<\/strong><\/p>\n When you encounter a Starship robot on the sidewalk, it will recognize someone in front of it and act accordingly.<\/p>\n Depending on the distance from the robot, it will either slow down and change course to move around or stop as quickly and safely as possible. On narrow sidewalks where two people cannot easily pass each other, the robot backs up and moves out of the way.<\/p>\n How<\/em> Did the robot cross the road?<\/strong><\/p>\n Crossing roads is the most complex for robots. This is the time when fast-moving vehicles can approach from different directions. Humans (for the most part) have an amazing ability to automatically (and unconsciously) analyze hundreds, if not thousands, of data points to determine whether it is safe to cross. I have. For example, the speed of the car, whether there is time to cross, etc. Robots have to make similar decisions, but humans haven’t evolved over hundreds of thousands of years. This is an incredibly difficult engineering task.<\/p>\n So if you’re a pedestrian crossing the road and you see a robot waiting, don’t worry. Just assess the situation and act when it is safe to cross. You don’t need to treat it specially, so please just cross it. A robot may even intersect with you!<\/p>\n However, if the robot is waiting at a traffic light or a pelican crosswalk, it would be helpful if you could press a button to change the signal. In doing so, you might even get a “thank you” from your robot! Going forward, this could quickly become a thing of the past. In some areas, our robots communicate with traffic light systems so you don’t even have to press a button. Delivery will be even faster!<\/p>\n The robot is stuck. What should I do?<\/strong><\/p>\n In some cases, the robot is waiting somewhere still. This isn’t uncommon for short periods of time \u2014 they’re probably just thinking, or taking a quick nap between deliveries…but don’t tell Mission Control about it!<\/p>\n Of course, sometimes robots get into a bit of trouble. Technology is always learning and improving, but sometimes you fall off a curb or get stuck in a tight space. Robots are always ready to help you!<\/p>\n Please enjoy the activities of the robots. Don’t forget to wave to them! \ud83d\udc4b\ud83c\udffb<\/p>\n team starship x<\/p>\n<\/div>\n![\"\"](\"https:\/\/miro.medium.com\/max\/640\/1*uqwn5hbG1np4lnCqjm_L3A.webp)
![\"\"](\"https:\/\/miro.medium.com\/max\/640\/1*-aovifQ6kPNiF4TICEJvXw.webp)