**VisuoSpatial Foresight** is a method for robotic fabric manipulation that leverages a combination of RGB and depth information to learn goal conditioned fabric manipulation policies for a variety of long horizon tasks.

Code for paper: H3DNet: 3D Object Detection Using Hybrid Geometric Primitives (ECCV 2020)

H3DNet

VisuoSpatial Foresight for Multi-Step, Multi-Task Fabric Manipulation

**Absolute Position Encodings** are a type of position embeddings for [[Transformer](https://paperswithcode.com/method/transformer)-based models] where positional encodings are added to the input embeddings at the bottoms of the encoder and decoder stacks. The positional encodings have the same dimension $d\_{model}$ as the embeddings, so that the two can be summed. In the original implementation, sine and cosine functions of different frequencies are used:

$$ \text{PE}\left(pos, 2i\right) = \sin\left(pos/10000^{2i/d\_{model}}\right) $$

$$ \text{PE}\left(pos, 2i+1\right) = \cos\left(pos/10000^{2i/d\_{model}}\right) $$

where $pos$ is the position and $i$ is the dimension. That is, each dimension of the positional encoding corresponds to a sinusoid. The wavelengths form a geometric progression from $2\pi$ to $10000 \dot 2\pi$. This function was chosen because the authors hypothesized it would allow the model to easily learn to attend by relative positions, since for any fixed offset $k$,  $\text{PE}\_{pos+k}$ can be represented as a linear function of $\text{PE}\_{pos}$.

Image Source: [D2L.ai](https://d2l.ai/chapter_attention-mechanisms/self-attention-and-positional-encoding.html)

Source	VisuoSpatial Foresight for Multi-Step, Multi-Task Fabric Manipulation
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com