라즈베리파이_Google Assistant (AI) 버튼 제어

1. 버튼 누르면 led 켜지게 하여 기본 틀 구성하기

DIY Hacking http://diyhacking.com/raspberry-pi-robot/

https://developmentdiary.tistory.com/482

https://developmentdiary.tistory.com/482

라즈베리파이 led 버튼

 

<1. 버튼(23)눌리면 led켜는 코드>

# -*- coding:utf-8 -*-  #한글 입력
#버튼 지속하기
import RPi.GPIO as GPIO #gpio라이브러르
import time     #sleep사용
 
GPIO.setmode(GPIO.BCM)  #gpio 모드 셋팅
 
GPIO.setup(23, GPIO.IN, pull_up_down=GPIO.PUD_UP)       #Button 입력 GPIO23
GPIO.setup(24, GPIO.OUT)                                #LED 출력GPIO24
 
try:
        a=False
        while True:
                button_state = GPIO.input(23)   #버튼 상태 확인
                if button_state == False:       #눌러진상태면
                        if a:
                                a=False
                        else:
                                a=True
                if a:
                        GPIO.output(24, True)   #출력
                else:
                        GPIO.output(24, False)
                time.sleep(0.15)
except KeyboardInterrupt:       #ctrl-c 누를시
    GPIO.cleanup()

실행 폴더로 이동하여

python LED_Button2.py

<2. +구글 스피치 API>

https://developers.google.com/assistant/sdk/guides/service/python/extend/handle-device-commands

Handle Commands  |  Google Assistant SDK  |  Google Developers

1 구글 어시스턴스 소스를 다운받는다.

git clone https://github.com/googlesamples/assistant-sdk-python

 

2 설치

#가상환경 나갔다가 다시 실행하기
> deactivate
> sudo reboot

#가상 환경 env로 접속
> source ~/env/bin/activate

#GPIO 인스톨
> pip install RPi.GPIO

(오류) buf = arr.tostring() 

오류 경로로 이동하여 buf = arr.tostring() 이것을 buf = arr.tobytes() 으로 바꿔줘야한다 파이선 버전때문에 생기는 오류

>해결

pip3 install pathlib2
$ pip install click
sudo pip install grpcio

https://pypi.org/project/grpcio/

grpcio

 

---

 

import RPi.GPIO as GPIO

    device_handler = device_helpers.DeviceRequestHandler('본인기기아이디')
    GPIO.setmode(GPIO.BCM)
    GPIO.setup(24, GPIO.OUT, initial=GPIO.LOW)

    @device_handler.command('action.devices.commands.OnOff')
    def onoff(on):
        if on:
            logging.info('Turning device on')
            GPIO.output(24, 1)
        else:
            logging.info('Turning device off')
            GPIO.output(24, 0)

이걸 붙여넣으라고 했다.(google : IoT 버튼 제어)

 

하지만 나는 엔터키 누르는 이부분을

> 버튼을 누르면 인식되고 대화가 끝나면 다시 불이꺼진채로 대기한다.

#원래코드

	with SampleAssistant(lang, device_model_id, device_id,
                         conversation_stream, display,
                         grpc_channel, grpc_deadline,
                         device_handler) as assistant:
        # If file arguments are supplied:
        # exit after the first turn of the conversation.
        if input_audio_file or output_audio_file:
            assistant.assist()
            return

        # If no file arguments supplied:
        # keep recording voice requests using the microphone
        # and playing back assistant response using the speaker.
        # When the once flag is set, don't wait for a trigger. Otherwise, wait.
        wait_for_user_trigger = not once
        while True:
            if wait_for_user_trigger:
                continue_conversation = assistant.assist()
                # wait for user trigger if there is no follow-up turn in
                # the conversation.
                wait_for_user_trigger = not continue_conversation

            # If we only want one conversation, break.
            if once and (not continue_conversation):
                print("end")
                break

이렇게 바꿨다.

 

> 1차 코드: 버튼 누르면 음성인식 시작 두번누르면 전송

#바뀐코드
GPIO.setmode(GPIO.BCM)  #gpio 모드 셋팅
 
GPIO.setup(23, GPIO.IN, pull_up_down=GPIO.PUD_UP)       #Button 입력 GPIO23
GPIO.setup(24, GPIO.OUT)                                #LED 출력GPIO24

	with SampleAssistant(lang, device_model_id, device_id,
                         conversation_stream, display,
                         grpc_channel, grpc_deadline,
                         device_handler) as assistant:
        # If file arguments are supplied:
        # exit after the first turn of the conversation.
        if input_audio_file or output_audio_file:
            assistant.assist()
            return

        # If no file arguments supplied:
        # keep recording voice requests using the microphone
        # and playing back assistant response using the speaker.
        # When the once flag is set, don't wait for a trigger. Otherwise, wait.
        wait_for_user_trigger = not once
        while True:
            if wait_for_user_trigger:
                #click.pause(info='Press Enter to send a new request...')
                a=False
                button_state = GPIO.input(23)   #버튼 상태 확인
                if button_state == False:       #눌러진상태면
                        if a:
                                a=False
                        else:
                                a=True
                if a:
                        GPIO.output(24, True)   #출력
                        continue_conversation = assistant.assist()
                        print("assist00000")
                        # wait for user trigger if there is no follow-up turn in
                        # the conversation.
                        wait_for_user_trigger = not continue_conversation
                        print("not continue")
                        a= False
                else:
                        GPIO.output(24, False)
                        print("i'm nothing")
                time.sleep(0.15)

            

            # If we only want one conversation, break.
            if once and (not continue_conversation):
                print("end")
                break

---

 

>2차 코드 : 바로 시작 / 음성인식 끝나면 /질문/ 완료 버튼 or 다시 음성인식 버튼

sound_pin = 18
led_pin =24
<버튼>
button_pin = 16 : right
button_pin = 12 : left

(가상환경 실행 코드)
source ~/env/bin/activate

#!/usr/bin/env python

# Copyright 2017 Google Inc. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#      http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""Google Cloud Speech API sample application using the streaming API.

NOTE: This module requires the additional dependency `pyaudio`. To install
using pip:

    pip install pyaudio

Example usage:
    python transcribe_streaming_mic.py
"""

# [START speech_transcribe_streaming_mic]
from __future__ import division
import os
import re
import sys

from google.cloud import speech

import pyaudio
from six.moves import queue
import RPi.GPIO as GPIO
import time
from playsound import playsound

os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = \
"*************본인 인증서 key .json"

# Audio recording parameters
RATE = 16000
CHUNK = int(RATE / 10)  # 100ms


class MicrophoneStream(object):
    """Opens a recording stream as a generator yielding the audio chunks."""

    def __init__(self, rate, chunk):
        self._rate = rate
        self._chunk = chunk

        # Create a thread-safe buffer of audio data
        self._buff = queue.Queue()
        self.closed = True

    def __enter__(self):
        self._audio_interface = pyaudio.PyAudio()
        self._audio_stream = self._audio_interface.open(
            format=pyaudio.paInt16,
            # The API currently only supports 1-channel (mono) audio
            # https://goo.gl/z757pE
            channels=1,
            rate=self._rate,
            input=True,
            frames_per_buffer=self._chunk,
            # Run the audio stream asynchronously to fill the buffer object.
            # This is necessary so that the input device's buffer doesn't
            # overflow while the calling thread makes network requests, etc.
            stream_callback=self._fill_buffer,
        )

        self.closed = False

        return self

    def __exit__(self, type, value, traceback):
        self._audio_stream.stop_stream()
        self._audio_stream.close()
        self.closed = True
        # Signal the generator to terminate so that the client's
        # streaming_recognize method will not block the process termination.
        self._buff.put(None)
        self._audio_interface.terminate()

    def _fill_buffer(self, in_data, frame_count, time_info, status_flags):
        """Continuously collect data from the audio stream, into the buffer."""
        self._buff.put(in_data)
        return None, pyaudio.paContinue

    def generator(self):
        while not self.closed:
            # Use a blocking get() to ensure there's at least one chunk of
            # data, and stop iteration if the chunk is None, indicating the
            # end of the audio stream.
            chunk = self._buff.get()
            if chunk is None:
                return
            data = [chunk]

            # Now consume whatever other data's still buffered.
            while True:
                try:
                    chunk = self._buff.get(block=False)
                    if chunk is None:
                        return
                    data.append(chunk)
                except queue.Empty:
                    break

            yield b"".join(data)


############################################################################3
############################################################################
#여기부터중요

def listen_print_loop(responses):
    """Iterates through server responses and prints them.

    The responses passed is a generator that will block until a response
    is provided by the server.

    Each response may contain multiple results, and each result may contain
    multiple alternatives; for details, see https://goo.gl/tjCPAU.  Here we
    print only the transcription for the top alternative of the top result.

    In this case, responses are provided for interim results as well. If the
    response is an interim one, print a line feed at the end of it, to allow
    the next result to overwrite it, until the response is a final one. For the
    final one, print a newline to preserve the finalized transcription.
    """
    global _data
    num_chars_printed = 0
    for response in responses:
        if not response.results:
            continue

        # The `results` list is consecutive. For streaming, we only care about
        # the first result being considered, since once it's `is_final`, it
        # moves on to considering the next utterance.
        result = response.results[0]
        if not result.alternatives:
            continue

        # Display the transcription of the top alternative.
        transcript = result.alternatives[0].transcript

        # Display interim results, but with a carriage return at the end of the
        # line, so subsequent lines will overwrite them.
        #
        # If the previous result was longer than this one, we need to print
        # some extra spaces to overwrite the previous result
        overwrite_chars = " " * (num_chars_printed - len(transcript))

        if not result.is_final:
            sys.stdout.write(transcript + overwrite_chars + "\r")
            sys.stdout.flush()

            num_chars_printed = len(transcript)

        else:
#             results {
            #   alternatives {
            #     transcript: "Let\'s go"
            #     confidence: 0.92365956
            #   }
            #   is_final: true
            #   result_end_time {
            #     seconds: 1
            #     nanos: 950000000
            #   }
            #   language_code: "ko-kr"
            # }
            # total_billed_time {
            #   seconds: 15
            # }
            print(transcript + overwrite_chars)

            # Exit recognition if any of the transcribed phrases could be
            # one of our keywords.
            if re.search(r"\b(exit|quit)\b", transcript, re.I):
                print("Exiting..")
                break
            _data=transcript + overwrite_chars
            print("_data"+_data)
            break

            num_chars_printed = 0


def main():
    #sound
    playsound("seach_voice.mp3")
    light()
    # See http://g.co/cloud/speech/docs/languages
    # for a list of supported languages.
    language_code = "ko-KR"  # a BCP-47 language tag

    client = speech.SpeechClient()
    config = speech.RecognitionConfig(
        encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
        sample_rate_hertz=RATE,
        language_code=language_code,
    )

    streaming_config = speech.StreamingRecognitionConfig(
        config=config, interim_results=True
    )

    with MicrophoneStream(RATE, CHUNK) as stream:
        audio_generator = stream.generator()
        requests = (
            speech.StreamingRecognizeRequest(audio_content=content)
            for content in audio_generator
        )

        responses = client.streaming_recognize(streaming_config, requests)

        # Now, put the transcription responses to use.
        listen_print_loop(responses)
        # print("문장받아왔음,res")
    melody()
    light()
    #button
    print("button click")
    playsound("button-voice.mp3")

#event1
button1_state = False
button1_state_change = False
def button1Pressed(channel):
    print("1")
    # #23 Right 1
    # if complete:
    #     exit()
    # else :
    #     main()


button2_state = False
button2_state_change = False
def button2Pressed(channel):
    print("2")
    #17 Left 2
    main()



def melody():
    sound_pin = 18
    GPIO.setup(sound_pin,GPIO.OUT)

    #pwm(핀번호, 헤르쯔 ##)
    #소리감도 0-100 %
    pwm = GPIO.PWM(sound_pin,1000.0)
    pwm.start(0)

    #sound
    melody =  [262,294,330,349,392,440,494,523]

    for note in range(0,6):
        pwm.ChangeFrequency(melody[note])
        pwm.ChangeDutyCycle(50)
        time.sleep(0.1)
        pwm.ChangeDutyCycle(0)

on = False
def light():
    print("light")
    #turn on / off
    global on
    led_pin = 24  
    GPIO.setmode(GPIO.BCM)
    #light on
    GPIO.setup(led_pin, GPIO.OUT)     
    on = True if not on else False
    if on:
        GPIO.output(led_pin, True)
    else :
        GPIO.output(led_pin, False)



if __name__ == "__main__":
    try:
        # init()
        button1_pin = 16
        button2_pin = 12

        GPIO.setwarnings(True)
        GPIO.setmode(GPIO.BCM)
        GPIO.setup(button1_pin, GPIO.IN, pull_up_down=GPIO.PUD_UP)     #Button1 입력 GPIO16
        GPIO.setup(button2_pin, GPIO.IN, pull_up_down=GPIO.PUD_UP)       #Button3 입력 GPIO4

        # GPIO.remove_event_detect(button1_pin)
        # GPIO.remove_event_detect(button2_pin)

        # GPIO.add_event_detect(button1_pin, GPIO.RISING, callback=button1Pressed)
        GPIO.add_event_detect(button2_pin, GPIO.RISING ,callback=button2Pressed)
        main()
        while True:
            GPIO.wait_for_edge(button1_pin, GPIO.FALLING)
            print("Button pressed! save",_data)
    except KeyboardInterrupt:
        # exit with CTRL+C
        print("CTRL+C used to end Program")
    finally:
        GPIO.cleanup()

 

<3.GPIO 오류>

- GPIO는 순서가 중요하고

- global로 변수 주면 오류나고

- 기능을 묶어 하나의 함수 안에 관리해주는게 가장 좋다. 필요할때마다 호출해서 사용한다.

- 버튼을 이벤트에 등록해서 쓸때는 변수 선언하는 것처럼 변수 아래에 이벤트 선언해놓고 

- 버튼 핀 셋팅은 up 일때가 잘 됐고

     GPIO.setup(button1_pin, GPIO.IN, pull_up_down=GPIO.PUD_UP) 

 - 이벤트 함수에서는 clballck = 함수이름 이런 형식으로 작성해야 오류가 안 났다

     GPIO.add_event_detect(button2_pin, GPIO.RISING ,callback=button2Pressed)

- 또 wait_for_edge 함수를 알았는데, 버튼이 눌릴 때 까지 기다려준다. 반응이 오면 다음으로 넘어간다

        while True:
            GPIO.wait_for_edge(button1_pin, GPIO.FALLING)
            print("Button pressed! save",_data)

- 그리고 GPIO 신호 초기화 잘 안 해주면 관련오류가 계속난다.

     GPIO.cleanup() # 이거 꼭 잘해주고

     GPIO.setwarnings(True) #이거 대부분 사람들 False로 하던데.. 잘 모르겠다

      GPIO.remove_event_detect(button1_pin) # 필수는 아님..