Keywords: Vision and Language, Robotics, Multimodal Learning
TL;DR: VLMbench is the first benchmark that compositional designs for vision-and-language reasoning and categorizes the manipulation tasks from the perspectives of task constraints.
Abstract: 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.
Supplementary Material: pdf
Dataset Url: https://sites.google.com/ucsc.edu/vlmbench/home
License: The codes and dataset are under MIT license.
Author Statement: Yes
Contribution Process Agreement: Yes
In Person Attendance: Yes