Getting the Agent a Vehicle- Python Plays GTA V





Hello and welcome to another self-driving cars tutorial, in this tutorial we're going to use the TensorFlow Object Detection API to see about commandeering a vehicle.

Up to this point, our code is:

# coding: utf-8
# # Object Detection Demo
# License: Apache License 2.0 (https://github.com/tensorflow/models/blob/master/LICENSE)
# source: https://github.com/tensorflow/models
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile

from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image
from grabscreen import grab_screen
import cv2

# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")


# ## Object detection imports
# Here are the imports from the object detection module.

from utils import label_map_util
from utils import visualization_utils as vis_util


# # Model preparation 
# What model to download.
MODEL_NAME = 'ssd_mobilenet_v1_coco_11_06_2017'
MODEL_FILE = MODEL_NAME + '.tar.gz'
DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'

# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'

# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join('data', 'mscoco_label_map.pbtxt')

NUM_CLASSES = 90

# ## Load a (frozen) Tensorflow model into memory.
detection_graph = tf.Graph()
with detection_graph.as_default():
  od_graph_def = tf.GraphDef()
  with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
    serialized_graph = fid.read()
    od_graph_def.ParseFromString(serialized_graph)
    tf.import_graph_def(od_graph_def, name='')


# ## Loading label map
# Label maps map indices to category names, so that when our convolution network predicts `5`, we know that this corresponds to `airplane`.  Here we use internal utility functions, but anything that returns a dictionary mapping integers to appropriate string labels would be fine
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES, use_display_name=True)
category_index = label_map_util.create_category_index(categories)


# ## Helper code
def load_image_into_numpy_array(image):
  (im_width, im_height) = image.size
  return np.array(image.getdata()).reshape(
      (im_height, im_width, 3)).astype(np.uint8)

# Size, in inches, of the output images.
IMAGE_SIZE = (12, 8)

with detection_graph.as_default():
  with tf.Session(graph=detection_graph) as sess:
    while True:
      #screen = cv2.resize(grab_screen(region=(0,40,1280,745)), (WIDTH,HEIGHT))
      screen = cv2.resize(grab_screen(region=(0,40,1280,745)), (800,450))
      image_np = cv2.cvtColor(screen, cv2.COLOR_BGR2RGB)
      # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
      image_np_expanded = np.expand_dims(image_np, axis=0)
      image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
      # Each box represents a part of the image where a particular object was detected.
      boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
      # Each score represent how level of confidence for each of the objects.
      # Score is shown on the result image, together with the class label.
      scores = detection_graph.get_tensor_by_name('detection_scores:0')
      classes = detection_graph.get_tensor_by_name('detection_classes:0')
      num_detections = detection_graph.get_tensor_by_name('num_detections:0')
      # Actual detection.
      (boxes, scores, classes, num_detections) = sess.run(
          [boxes, scores, classes, num_detections],
          feed_dict={image_tensor: image_np_expanded})
      # Visualization of the results of a detection.
      vis_util.visualize_boxes_and_labels_on_image_array(
          image_np,
          np.squeeze(boxes),
          np.squeeze(classes).astype(np.int32),
          np.squeeze(scores),
          category_index,
          use_normalized_coordinates=True,
          line_thickness=8)


      for i,b in enumerate(boxes[0]):
        #                 car                    bus                  truck
        if classes[0][i] == 3 or classes[0][i] == 6 or classes[0][i] == 8:
          if scores[0][i] >= 0.5:
            mid_x = (boxes[0][i][1]+boxes[0][i][3])/2
            mid_y = (boxes[0][i][0]+boxes[0][i][2])/2
            apx_distance = round(((1 - (boxes[0][i][3] - boxes[0][i][1]))**4),1)
            cv2.putText(image_np, '{}'.format(apx_distance), (int(mid_x*800),int(mid_y*450)), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255,255,255), 2)

            if apx_distance <=0.5:
              if mid_x > 0.3 and mid_x < 0.7:
                cv2.putText(image_np, 'WARNING!!!', (50,50), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0,0,255), 3)


      cv2.imshow('window',image_np)
      if cv2.waitKey(25) & 0xFF == ord('q'):
          cv2.destroyAllWindows()
          break

So the above code is used to determine if a vehicle is too close, we can still use part of this code, but our new objective is instead to find cars and...procure them.

There are a bunch of ways to do this, but the first that came to my mind was to take account of all of the vehicles in sight, and then head towards the closest car. If we're close enough to get in, we'll attempt to get in. Once we get in, we'll stop heading for cars.

To begin, from the above code, we're going to be working specifically in this chunk of code:

      for i,b in enumerate(boxes[0]):
        #                 car                    bus                  truck
        if classes[0][i] == 3 or classes[0][i] == 6 or classes[0][i] == 8:
          if scores[0][i] >= 0.5:
            mid_x = (boxes[0][i][1]+boxes[0][i][3])/2
            mid_y = (boxes[0][i][0]+boxes[0][i][2])/2
            apx_distance = round(((1 - (boxes[0][i][3] - boxes[0][i][1]))**4),1)
            cv2.putText(image_np, '{}'.format(apx_distance), (int(mid_x*800),int(mid_y*450)), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255,255,255), 2)

            if apx_distance <=0.5:
              if mid_x > 0.3 and mid_x < 0.7:
                cv2.putText(image_np, 'WARNING!!!', (50,50), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0,0,255), 3)

Our first order of business is to log all of the cars in the area. I am sure there's a better way, but I am just going to create a dictionary, storing vehicle locations and score by distance as the key. Then, we'll just sort the keys, and find the closest vehicle to approach. So, before the for i,b ... loop, we'll add:

      vehicle_dict = {}
      for i,b in enumerate(boxes[0]):

Next, I am going to change the rounding in our apx_distance to go to 3 places:

            apx_distance = round(((1 - (boxes[0][i][3] - boxes[0][i][1]))**4),3)

I am doing that so we are less likely to get duplicate distances. We still might, but it shouldn't be too problematic.

Now let's store vehicles to our dictionary:

            vehicle_dict[apx_distance] = [mid_x, mid_y, scores[0][i]]

Outside of the for loop, let's check our dictionary for vehicles, and head towards the closest:

      if len(vehicle_dict) > 0:
        closest = sorted(vehicle_dict.keys())[0]
        vehicle_choice = vehicle_dict[closest]
        print('CHOICE:',vehicle_choice)

        determine_movement(mid_x = vehicle_choice[0], mid_y = vehicle_choice[1], width=1280, height=705)

Our new block of code is:

      vehicle_dict = {}
      
      for i,b in enumerate(boxes[0]):
        #                 car                    bus                  truck
        if classes[0][i] == 3 or classes[0][i] == 6 or classes[0][i] == 8:
          if scores[0][i] >= 0.5:
            mid_x = (boxes[0][i][1]+boxes[0][i][3])/2
            mid_y = (boxes[0][i][0]+boxes[0][i][2])/2
            apx_distance = round(((1 - (boxes[0][i][3] - boxes[0][i][1]))**4),3)
            cv2.putText(image_np, '{}'.format(apx_distance), (int(mid_x*800),int(mid_y*450)), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255,255,255), 2)

            if apx_distance <=0.5:
              if mid_x > 0.3 and mid_x < 0.7:
                cv2.putText(image_np, 'WARNING!!!', (50,50), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0,0,255), 3)

            vehicle_dict[apx_distance] = [mid_x, mid_y, scores[0][i]]

      if len(vehicle_dict) > 0:
        closest = sorted(vehicle_dict.keys())[0]
        vehicle_choice = vehicle_dict[closest]
        print('CHOICE:',vehicle_choice)
        determine_movement(mid_x = vehicle_choice[0], mid_y = vehicle_choice[1], width=1280, height=705)

Now we just have one minor problem... determine_movement doesn't exist! We want this function to determine which way our agent should look and go towards. That's what we're going to cover in the next tutorial!

The next tutorial:






  • Reading game frames in Python with OpenCV - Python Plays GTA V
  • OpenCV basics - Python Plays GTA V
  • Direct Input to Game - Python Plays GTA V
  • Region of Interest for finding lanes - Python Plays GTA V
  • Hough Lines - Python Plays GTA V
  • Finding Lanes for our self driving car - Python Plays GTA V
  • Self Driving Car - Python Plays GTA V
  • Next steps for Deep Learning self driving car - Python Plays GTA V
  • Training data for self driving car neural network- Python Plays GTA V
  • Balancing neural network training data- Python Plays GTA V
  • Training Self-Driving Car neural network- Python Plays GTA V
  • Testing self-driving car neural network- Python Plays GTA V
  • A more interesting self-driving AI - Python Plays GTA V
  • Object detection with Tensorflow - Self Driving Cars in GTA
  • Determining other vehicle distances and collision warning - Self Driving Cars in GTA
  • Getting the Agent a Vehicle- Python Plays GTA V
  • Acquiring a Vehicle for the Agent - Python Plays GTA V