Python Based Hand Pose Controlled Mecanum

Example Description
Learn how to use the Hand Gesture Classifier of the Machine Learning Environment to make a machine-learning model that identifies hand gestures and makes the Mecanum move accordingly.

This project demonstrates how to use Machine Learning Environment to make a machinelearning model that identifies the hand gestures and makes the Mecanum move accordingly.

We are going to use the Hand Classifier of the Machine Learning Environment. The model works by analyzing your hand position with the help of 21 data points. We will add in total 8 different classes to operate the different motions of the Mecanum Robot with the help of the ML Environment of the Pictoblox Software.

Hand Gesture Classifier Workflow

Follow the steps below:

  1. Open PictoBlox and create a new file.
  2. Select the coding environment as appropriate Coding Environment.
  3. Select the “Open ML Environment” option under the “Files” tab to access the ML Environment.
  4. Click on “Create New Project“.
  5. A window will open. Type in a project name of your choice and select the “Hand Gesture Classifier” extension. Click the “Create Project” button to open the Hand Pose Classifier window.
  6. You shall see the Classifier workflow with two classes already made for you. Your environment is all set. Now it’s time to upload the data.

Class in Hand Gesture Classifier

There are 2 things that you have to provide in a class:

  1. Class Name: It’s the name to which the class will be referred as.
  2. Hand Pose Data: This data can either be taken from the webcam or by uploading from local storage.

Note: You can add more classes to the projects using the Add Class button.
Adding Data to Class

You can perform the following operations to manipulate the data into a class.

  1. Naming the Class: You can rename the class by clicking on the edit button.
  2. Adding Data to the Class: You can add the data using the Webcam or by Uploading the files from the local folder.
    1. Webcam:
Note: You must add at least 20 samples to each of your classes for your model to train. More samples will lead to better results.
Training the Model

After data is added, it’s fit to be used in model training. In order to do this, we have to train the model. By training the model, we extract meaningful information from the hand pose, and that in turn updates the weights. Once these weights are saved, we can use our model to make predictions on data previously unseen.

The accuracy of the model should increase over time. The x-axis of the graph shows the epochs, and the y-axis represents the accuracy at the corresponding epoch. Remember, the higher the reading in the accuracy graph, the better the model. The range of the accuracy is 0 to 1.

Testing the Model

To test the model, simply enter the input values in the “Testing” panel and click on the “Predict” button.

The model will return the probability of the input belonging to the classes.

Export in Python Coding

Click on the “Export Model” button on the top right of the Testing box, and PictoBlox will load your model into the Python Coding Environment if you have opened the ML Environment in the Python Coding.


Logic

The mecanum will move according to the following logic:

  1. When the forward gesture is detected – Mecanum will move forward.
  2. When the backward gesture is detected – Mecanum will move backwards.
  3. When the Lateral Left gesture is detected – Mecanum will move towards the left direction laterally with the help of its omnidirectional wheels.
  4. When the Lateral Right gesture is detected – Mecanum will move towards the right direction laterally with the help of its omnidirectional wheels.
  5. When the Stop gesture is detected – Mecanum will stop moving.
  6. When the Normal Left gesture is detected – Mecanum will rotate in the left direction.
  7. When the Normal Right gesture is detected – Mecanum will rotate in the right direction.
  8. When the Circular Motion gesture is detected – Mecanum will move in a lateral arc.

Code

The following code appears in the Python Editor of the selected sprite.

####################imports####################
# Do not change

import numpy as np
import tensorflow as tf
import time

# Do not change
####################imports####################

#Following are the model and video capture configurations
# Do not change

model=tf.keras.models.load_model(
    "num_model.h5",
    custom_objects=None,
    compile=True,
    options=None)
pose = Posenet()                                                    # Initializing Posenet
pose.enablebox()                                                    # Enabling video capture box
pose.video("on",0)                                                  # Taking video input
class_list=['Forward','Backward','Stop','LateralRight','LateralLeft','NormalRight','NormalLeft','CircularMotion']                  # List of all the classes
meca=Mecanum(1,2,7,8)
def runmecanum(predicted_class):
  if pose.ishanddetected():
    if predicted_class=="Forward":
      meca.runtimedrobot("forward",100,2)
    if predicted_class=="Backward":
      meca.runtimedrobot("backward",100,2)
    if predicted_class=="Stop":
      meca.stoprobot()
    if predicted_class=="LateralRight":
      meca.runtimedrobot("lateral right",100,2)
    if predicted_class=="LateralLeft":
      meca.runtimedrobot("lateral left",100,2)
    if predicted_class=="NormalRight":
      meca.runtimedrobot("circular right",100,1)
    if predicted_class=="NormalLeft":
      meca.runtimedrobot("circular left",100,1)
    if predicted_class=="CircularMotion":
      meca.runtimedrobot("lateral arc",100,1)
    
# Do not change
###############################################

#This is the while loop block, computations happen here
# Do not change

while True:
  pose.analysehand()                                             # Using Posenet to analyse hand pose
  coordinate_xy=[]
    
    # for loop to iterate through 21 points of recognition
  for i in range(21):
    if(pose.gethandposition(1,i,0)!="NULL"  or pose.gethandposition(2,i,0)!="NULL"):
      coordinate_xy.append(int(240+float(pose.gethandposition(1,i,0))))
      coordinate_xy.append(int(180-float(pose.gethandposition(2,i,0))))
    else:
      coordinate_xy.append(0)
      coordinate_xy.append(0)
            
  coordinate_xy_tensor = tf.expand_dims(coordinate_xy, 0)        # Expanding the dimension of the coordinate list
  predict=model.predict(coordinate_xy_tensor)                    # Making an initial prediction using the model
  predict_index=np.argmax(predict[0], axis=0)                    # Generating index out of the prediction
  predicted_class=class_list[predict_index]                      # Tallying the index with class list
  print(predicted_class)
  runmecanum(predicted_class)
  # Do not change

Logical Code

def runmecanum(predicted_class):
  if pose.ishanddetected():
    if predicted_class=="Forward":
      meca.runtimedrobot("forward",100,2)
    if predicted_class=="Backward":
      meca.runtimedrobot("backward",100,2)
    if predicted_class=="Stop":
      meca.stoprobot()
    if predicted_class=="LateralRight":
      meca.runtimedrobot("lateral right",100,2)
    if predicted_class=="LateralLeft":
      meca.runtimedrobot("lateral left",100,2)
    if predicted_class=="NormalRight":
      meca.runtimedrobot("circular right",100,1)
    if predicted_class=="NormalLeft":
      meca.runtimedrobot("circular left",100,1)
    if predicted_class=="CircularMotion":
      meca.runtimedrobot("lateral arc",100,1)

Output

Forward-Backward Motions:

Lateral Right-Left Motions:

Circular Right-Left Motions:

Lateral Arc Motion:

Table of Contents