Video oldindan ko‘rish uchun mavjud emas
Telegram'da ko‘rish
Making robots truly helpful and safe in our everyday lives: Latent-Space Reachability Analysis https://kensukenk.github.io/latent-safety/
A new approach called "Latent Safety Filters" allows robots to understand and prevent complex "failures." Imagine teaching a robot to pick up a bag of Skittles. Traditional safety systems might stop the robot from bumping into the table, but they wouldn't understand that pulling the bag up too quickly will cause the candy to spill everywhere.
The researchers equip the robot with a world model that learn to understand how the world works just by watching videos and trying things out. Think of it as the robot building a mental picture of the scene.
The "Safety Filter" then acts like a guardian angel for the robot's actions. It monitors what the robot is about to do and checks if it's heading towards a failure in its imagined world. It does this without needing to be told exactly how to be safe in every situation beforehand. It learns from experience and its "imagination."
A new approach called "Latent Safety Filters" allows robots to understand and prevent complex "failures." Imagine teaching a robot to pick up a bag of Skittles. Traditional safety systems might stop the robot from bumping into the table, but they wouldn't understand that pulling the bag up too quickly will cause the candy to spill everywhere.
The researchers equip the robot with a world model that learn to understand how the world works just by watching videos and trying things out. Think of it as the robot building a mental picture of the scene.
The "Safety Filter" then acts like a guardian angel for the robot's actions. It monitors what the robot is about to do and checks if it's heading towards a failure in its imagined world. It does this without needing to be told exactly how to be safe in every situation beforehand. It learns from experience and its "imagination."