How do we program home robots to perform a wide variety of personalized everyday tasks?

Our aim is to learn to solve long-horizon decision-making problems in highly-variable, combinatorially-complex robotics domains given raw sensor input in the form of images. Previous work has shown that one way to achieve this aim is to learn a structured abstract transition model in the form of symbolic predicates and operators, and then plan within this model to solve novel tasks at test time. However, these learned models do not ground directly into pixels from just a handful of demonstrations. In this work, we propose to invent predicates that operate directly over input images by leveraging the capabilities of pretrained vision-language models (VLMs). Our key idea is that, given a set of demonstrations, a VLM can be used to propose a set of predicates that are potentially relevant for decision-making and then to determine the truth values of these predicates in both the given demonstrations and new image inputs. We build upon an existing framework for predicate invention, which generates feature-based predicates operating on object-centric states, to also generate visual predicates that operate on images. Experimentally, we show that our approach -- pix2pred -- is able to invent semantically meaningful predicates that enable generalization to novel, complex, and long-horizon tasks across two simulated robotic environments.

Language instructions and demonstrations are two natural ways for users to teach robots personalized tasks. Recent progress in Large Language Models (LLMs) has shown impressive performance in translating language instructions into code for robotic tasks. However, translating demonstrations into task code continues to be a challenge due to the length and complexity of both demonstrations and code, making learning a direct mapping intractable. This paper presents Demo2Code, a novel framework that generates robot task code from demonstrations via an extended chain-of-thought and defines a common latent specification to connect the two. Our framework employs a robust two-stage process: (1) a recursive summarization technique that condenses demonstrations into concise specifications, and (2) a code synthesis approach that expands each function recursively from the generated specifications. We conduct extensive evaluation on various robot task benchmarks, including a novel game benchmark Robotouille, designed to simulate diverse cooking tasks in a kitchen environment.

CyberGuy explains a new grill powered by AI that can cook a burger in under a minute. Have you ever wondered what it would be like to have a robot cook your burger for you? Well, you might not have to wait too long to find out. A robotic startup called Aniai has developed a revolutionary device that can cook eight juicy burgers in less than a minute, or up to 200 patties an hour. It's called the Alpha Grill, and it's not your ordinary burger-flipping robot.

Companies have been trying out automatons to serve food in restaurants, make home deliveries or do chores in stores, partly in hopes of easing the worker shortage. Among the disenchanted, FedEx Corp. said last month it was powering down Roxo, its last-mile delivery robot, to prioritize several "nearer-term opportunities," a spokeswoman said. Inc. said it was ending field tests of Scout, its home-delivery robot, after learning that some aspects of its "unique delivery experience" weren't "meeting customers' needs," a company spokeswoman said. And over the summer, DoorDash Inc. said it was shutting down its Chowbotics business -- best known for Sally, the salad-making robot -- roughly 18 months after buying it. "While we gained valuable insights into how to better serve this market, we concluded our current approach was not meeting our very high thresholds for continued investment," a DoorDash spokesman said.

Among the disenchanted, FedEx Corp. said last month it was powering down Roxo, its last-mile delivery robot, to prioritize several "nearer-term opportunities," a spokeswoman said. Inc. said it was ending field tests of Scout, its home-delivery robot, after learning that some aspects of its "unique delivery experience" weren't "meeting customers' needs," a company spokeswoman said. And over the summer, DoorDash Inc. said it was shutting down its Chowbotics business--best known for Sally, the salad-making robot--roughly 18 months after buying it. "While we gained valuable insights into how to better serve this market, we concluded our current approach was not meeting our very high thresholds for continued investment," a DoorDash spokesman said. Companies have entertained hopes that the growing variety of robots could help them not only weather the worker shortage, but speed up labor-intensive tasks, improve customer service by reducing the number of things the human workers have to do, and as an added bonus, position their brands as innovative and forward-leaning.

From cupcakes to pizzas, a range of weird and wondering vending machines have opened in recent years. Now, a burger vending machine has opened in Jersey City, serving up fresh burgers in six minutes for just $6.99 (£5.30). Its developers describe the vending machine as a'restaurant in miniature', and say it follows a similar process to what chefs use to cook up burgers in traditional restaurants. 'RoboBurger is like having a personal chef for 6 minutes, that dedicates all its attention to making your burger, with the perfectly grilled patty, and a crispy, fresh toasted bun,' they said. A burger vending machine has opened in Jersey City, serving up fresh burgers in six minutes for just $6.99 (£5.30)

"Which is more important: the patty or the buns?" The age-old causality dilemma has taken different forms for centuries--from the chicken-or-egg paradox to online debates weighing anime versus manga. It's also one that he uses to show that betraying fans' expectations and convincing players to engage with narratives are two different story elements that can coexist. "The patty is more important, huh? I see," remarks Taro in a recent interview with WIRED.

It is the night before the weekly shop. I look in the fridge and consider my three tomatoes, the sweet potato and the asparagus. Normally, I'd take this as my cue to nip to the fish and chip shop. However, I'm trying out Plant Jammer, an app that promises to rustle up a recipe based on whatever food you have lying around, using artificial intelligence. It searches three million recipes to find often-paired items.