Visually Grounding Instruction for History-Dependent Manipulation

16 Dec 2020 • Hyemin Ahn • Obin Kwon • Kyoungdo Kim • Dongheui Lee • Songhwai Oh

This paper emphasizes the importance of robot's ability to refer its task history, when it executes a series of pick-and-place manipulations by following text instructions given one by one. The advantage of referring the manipulation history can be categorized into two folds: (1) the instructions omitting details or using co-referential expressions can be interpreted, and (2) the visual information of objects occluded by previous manipulations can be inferred... (read more)

PDF Abstract

Results from the Paper

Edit

Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

METHOD	TYPE
GAN Least Squares Loss	Loss Functions
Residual Connection	Skip Connections
Tanh Activation	Activation Functions
ReLU	Activation Functions
PatchGAN	Discriminators
Convolution	Convolutions
Instance Normalization	Normalization
Cycle Consistency Loss	Loss Functions
Sigmoid Activation	Activation Functions
Leaky ReLU	Activation Functions
Batch Normalization	Normalization
Residual Block	Skip Connection Blocks
CycleGAN	Generative Models

METHOD

TYPE

GAN Least Squares Loss