DeepUWB
收藏资源简介：
A dataset for UWB ranging error mitigation in indoor environments, built using Decawave EVB1000 devices and the firmware contiki-uwb. Additional information can be found in the attached file "readme.txt" or in the paper Robust Ultra-wideband Range Error Mitigation with Deep Learning at the Edge. [ readme.txt ] * Every sample has the following structure: || CIR (157 float values) ||<br> || Error [m] ||<br> || Room (int) ||<br> || Obstacle (10 bool values) ||<br> || Measured Range (UWB) [m] || * Room encoding: 0 -> cross-room measurements<br> 1 -> big room<br> 2 -> medium room<br> 3 -> small room<br> 4 -> outdoor * Obstacle encoding: (1-hot encoding) 1000000000 -> wall<br> 0100000000 -> polystyrene plate<br> 0010000000 -> plastic (trash bin and chair)<br> 0001000000 -> plywood plate<br> 0000100000 -> cardboard box<br> 0000010000 -> LCD TV<br> 0000001000 -> metal plate<br> 0000000100 -> wood door<br> 0000000010 -> glass plate<br> 0000000001 -> metal window * Reading Code: # Import libraries<br> import pandas as pd<br> import numpy as np # Extract dataset<br> dataset = pd.read_pickle('dataset.pkl') # Select specific obstacle configurations<br> ds = np.asarray(dataset.loc[dataset['Objects']=='011111111'][['CIR','Error']]) # Select specific rooms<br> ds = np.asarray(dataset.loc[dataset['Room']==1][['CIR','Error']]) # Select all samples<br> ds = np.asarray(dataset[['CIR','Error']]) # Get X,y for training <br> X = np.vstack(ds[:,0])<br> y = np.array(ds[:,1])
