Binary Neural Network in Robotic Manipulation: Flexible Object Manipulation for Humanoid Robot Using Partially Binarized Auto-Encoder on FPGA

by   Satoshi Ohara, et al.

A neural network based flexible object manipulation system for a humanoid robot on FPGA is proposed. Although the manipulations of flexible objects using robots attract ever increasing attention since these tasks are the basic and essential activities in our daily life, it has been put into practice only recently with the help of deep neural networks. However such systems have relied on GPU accelerators, which cannot be implemented into the space limited robotic body. Although field programmable gate arrays (FPGAs) are known to be energy efficient and suitable for embedded systems, the model size should be drastically reduced since FPGAs have limited on-chip memory. To this end, we propose “partially” binarized deep convolutional auto-encoder technique, where only an encoder part is binarized to compress model size without degrading the inference accuracy. The model implemented on Xilinx ZCU102 achieves 41.1 frames per second with a power consumption of 3.1W, which corresponds to 10x and 3.7x improvements from the systems implemented on Core i7 6700K and RTX 2080 Ti, respectively.



There are no comments yet.


page 1

page 3

page 6


A Particle Swarm Optimization-based Flexible Convolutional Auto-Encoder for Image Classification

Convolutional auto-encoders have shown their remarkable performance in s...

A Deep Convolutional Auto-Encoder with Pooling - Unpooling Layers in Caffe

This paper presents the development of several models of a deep convolut...

Evolutionary Bin Packing for Memory-Efficient Dataflow Inference Acceleration on FPGA

Convolutional neural network (CNN) dataflow inference accelerators imple...

Dynamic Manipulation of Flexible Objects with Torque Sequence Using a Deep Neural Network

For dynamic manipulation of flexible objects, we propose an acquisition ...

FSPool: Learning Set Representations with Featurewise Sort Pooling

We introduce a pooling method for sets of feature vectors based on sorti...

Translating Videos to Commands for Robotic Manipulation with Deep Recurrent Neural Networks

We present a new method to translate videos to commands for robotic mani...

BinaryCoP: Binary Neural Network-based COVID-19 Face-Mask Wear and Positioning Predictor on Edge Devices

Face masks have long been used in many areas of everyday life to protect...
This week in AI

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