VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation

Benefiting from language flexibility and compositionality, humans naturally intend to use language to command an embodied agent for complex tasks such as navigation and object manipulation. In this work, we aim to fill the blank of the last mile of embodied agents-object manipulation by following human guidance, e.g., "move the red mug next to the box while keeping it upright." To this end, we introduce an Automatic Manipulation Solver (AMSolver) system and build a Vision-and-Language Manipulation benchmark (VLMbench) based on it, containing various language instructions on categorized robotic manipulation tasks. Specifically, modular rule-based task templates are created to automatically generate robot demonstrations with language instructions, consisting of diverse object shapes and appearances, action types, and motion constraints. We also develop a keypoint-based model 6D-CLIPort to deal with multi-view observations and language input and output a sequence of 6 degrees of freedom (DoF) actions. We hope the new simulator and benchmark will facilitate future research on language-guided robotic manipulation. Rotation Constraints Translation Constraints Goal Position Constraints "Fully open the dishwasher and take out the red plate." Step 0: Open the door of dishwasher Step 1: Pull out the tray of dishwasher Step 2: Pick up the red plate "Fully open the door of fridge." "Fully pull out the bottom drawer of cabinet." "Pick up the red block and place it on the red circle.