Visual Servoing for Pose Control of Soft Continuum Arm in a Structured Environment

This repository contains the official code for the paper "Visual Servoing for Pose Control of Soft Continuum Arm in a Structured Environment", accepted for publication at RA-L + RoboSoft 2022.

Usage

The repository consists of 2 folders:

1. Model - This folder contains the TensorFlow implementation for predicting the absolute actuation values of the soft arm given image input.
2. Utils - This folder contains python code for finding out the positional and rotational error between the predicted and true actuations and plotting the histograms.

Dataset

We have made our dataset public here. You can also run this code on your custom data collected.