VirtualHome: Simulating Household Activities via Programs
arXiv:1806.07011
Abstract
In this paper, we are interested in modeling complex activities that occur in a typical household. We propose to use programs, i.e., sequences of atomic actions and interactions, as a high level representation of complex tasks. Programs are interesting because they provide a non-ambiguous representation of a task, and allow agents to execute them. However, nowadays, there is no database providing this type of information. Towards this goal, we first crowd-source programs for a variety of activities that happen in people's homes, via a game-like interface used for teaching kids how to code. Using the collected dataset, we show how we can learn to extract programs directly from natural language descriptions or from videos. We then implement the most common atomic (inter)actions in the Unity3D game engine, and use our programs to "drive" an artificial agent to execute tasks in a simulated household environment. Our VirtualHome simulator allows us to create a large activity video dataset with rich ground-truth, enabling training and testing of video understanding models. We further showcase examples of our agent performing tasks in our VirtualHome based on language descriptions.
CVPR 2018 (Oral)
References in corpus (15)
- Efficient Estimation of Word Representations in Vector Space
- Sequence to Sequence Learning with Neural Networks
- Skip-Thought Vectors
- AI2-THOR: An Interactive 3D Environment for Visual AI
- Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books
- Virtual Worlds as Proxy for Multi-Object Tracking Analysis
- CARLA: An Open Urban Driving Simulator
- Building Generalizable Agents with a Realistic and Rich 3D Environment
- Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding
- Playing for Data: Ground Truth from Computer Games
- MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments
- Latent Predictor Networks for Code Generation
- HoME: a Household Multimodal Environment
- Temporal Relational Reasoning in Videos
- Unsupervised Semantic Parsing of Video Collections
Cited by in corpus (6)
- VRKitchen: an Interactive 3D Virtual Environment for Task-oriented Learning
- Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence
- Environments for Lifelong Reinforcement Learning
- Probing Emergent Semantics in Predictive Agents via Question Answering
- ArraMon: A Joint Navigation-Assembly Instruction Interpretation Task in Dynamic Environments
- A Dataset for Tracking Entities in Open Domain Procedural Text