Generalist robots that can perform a range of different tasks in open-world settings must be able to not only reason about the steps needed to accomplish their goals, but also process complex instructions, prompts, and even feedback during task execution. Intricate instructions (e.g., "Could you make me a vegetarian sandwich?" or "I don't like that one") require not just the ability to physically perform the individual steps, but the ability to situate complex commands and feedback in the physical world. In this work, we describe a system that uses vision-language models in a hierarchical structure, first reasoning over complex prompts and user feedback to deduce the most appropriate next step to fulfill the task, and then performing that step with low-level actions. In contrast to direct instruction following methods that can fulfill simple commands ("pick up the cup"), our system can reason through complex prompts and incorporate situated feedback during task execution ("that's not trash"). We evaluate our system across three robotic platforms, including single-arm, dual-arm, and dual-arm mobile robots, demonstrating its ability to handle tasks such as cleaning messy tables, making sandwiches, and grocery shopping.

We would expect all of these stages to be relevant to varying degrees; the Isle of Man and the industries it is home to are no exception. Whilst some of these technologies may seem far away – and some of them still are – being ready for them will be a key differentiator for workplaces and governments alike. Automation and Robotics varies hugely by industry, sector, and country. There are a number of fields where these technologies are already fully implemented, especially where the removal of human input is for safety reasons; i.e. in dangerous situations such as hazardous environments. However, in a number of fields, this is still in its infancy and improvements can still easily be made – none more so than certain sections of professional services. Machine learning is embedded in several high-tech industries, and is starting to enter early adopter and mainstream usage in both the home and the workplace.