Dynamics Learning with Cascaded Variational Inference for Multi-Step Manipulation

10/29/2019
by   Kuan Fang, et al.
10

The fundamental challenge of planning for multi-step manipulation is to find effective and plausible action sequences that lead to the task goal. We present Cascaded Variational Inference (CAVIN) Planner, a model-based method that hierarchically generates plans by sampling from latent spaces. To facilitate planning over long time horizons, our method learns latent representations that decouple the prediction of high-level effects from the generation of low-level motions through cascaded variational inference. This enables us to model dynamics at two different levels of temporal resolutions for hierarchical planning. We evaluate our approach in three multi-step robotic manipulation tasks in cluttered tabletop environments given high-dimensional observations. Empirical results demonstrate that the proposed method outperforms state-of-the-art model-based methods by strategically interacting with multiple objects.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 2

page 6

page 8

page 13

03/02/2021

Learning Robotic Manipulation Tasks through Visual Planning

Multi-step manipulation tasks in unstructured environments are extremely...
11/12/2018

Learning Latent Dynamics for Planning from Pixels

Planning has been very successful for control tasks with known environme...
12/14/2020

Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs

We present a visually grounded hierarchical planning algorithm for long-...
11/04/2021

Stein Variational Probabilistic Roadmaps

Efficient and reliable generation of global path plans are necessary for...
10/17/2020

Variational Dynamic for Self-Supervised Exploration in Deep Reinforcement Learning

Efficient exploration remains a challenging problem in reinforcement lea...
03/09/2020

Learning discrete state abstractions with deep variational inference

Abstraction is crucial for effective sequential decision making in domai...
03/01/2019

Multi-Object Representation Learning with Iterative Variational Inference

Human perception is structured around objects which form the basis for o...

Code Repositories

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.