MIT Launches GenSim Project: Using Large Language Models to Create New Tasks for Robots

The 'GenSim' project at MIT CSAIL expands the range of simulation tasks that robots can be trained on by utilizing large language models (LLMs) such as GPT-4 to automatically generate new tasks or detailed descriptions of the required behaviors at each step. The GenSim system features both goal-oriented and exploratory modes, generating task descriptions and the necessary code for simulating behaviors through LLMs. It then optimizes this code using a task library to ultimately create simulations capable of teaching robots how to perform new tasks.