Procedure Planning in Instructional Videos
arXiv:1907.01172
Abstract
In this paper, we study the problem of procedure planning in instructional videos, which can be seen as a step towards enabling autonomous agents to plan for complex tasks in everyday settings such as cooking. Given the current visual observation of the world and a visual goal, we ask the question "What actions need to be taken in order to achieve the goal?". The key technical challenge is to learn structured and plannable state and action spaces directly from unstructured videos. We address this challenge by proposing Dual Dynamics Networks (DDN), a framework that explicitly leverages the structured priors imposed by the conjugate relationships between states and actions in a learned plannable latent space. We evaluate our method on real-world instructional videos. Our experiments show that DDN learns plannable representations that lead to better planning performance compared to existing planning approaches and neural network policies.
arXiv comment14 pages, 7 figures
References in corpus (10)
- HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
- Learning Latent Dynamics for Planning from Pixels
- Video (language) modeling: a baseline for generative models of natural videos
- Towards Automatic Learning of Procedures from Web Instructional Videos
- Stochastic Adversarial Video Prediction
- Learning Plannable Representations with Causal InfoGAN
- Universal Planning Networks
- Semi-supervised Vocabulary-informed Learning
- Time-Agnostic Prediction: Predicting Predictable Video Frames
- Open Vocabulary Scene Parsing