Robohub.org
 

Hello Pepper: Getting started to program robots on Android


by
03 August 2016



share this:
The Future of Social Robotics, by Nicolas Rigaud. Source: Margaret Maynard-Reid/Medium

The Future of Social Robotics, by Nicolas Rigaud. Source: Margaret Maynard-Reid/Medium

I didn’t get to meet Pepper the humanoid Robot at Google I/O but I watched the video afterwards: A new development frontier: Android + Pepper the interactive robot. Love the robots’ dance! I was super excited to hear that Pepper will become available in the U.S. later this year, and Android developers can now program robots!

A few weeks after I/O, I attended a Seattle Java User Group meetup. That evening I met Pepper in person, and I learned about the Future of Social Robotics from Nicolas Rigaud (slides here).

Equipped with microphones, cameras, sensors and an intelligence to perceive emotions, Pepper was designed for social interactions. He has an Android tablet on his chest which is very convenient for displaying image, video and texts. Pepper is 4 feet tall (1.2 meters) and can connect to the network with either Wi-Fi or Ethernet. Pepper is multi-lingual in English, French, Japanese and Chinese.

Source: Margaret Maynard-Reid/Medium

Source: Margaret Maynard-Reid/Medium

I wanted to learn more about Pepper. So I followed the instructions from the Pepper SDK for Android and was able to quickly get set up and create my first robot Application with Android Studio.

Since I already have Android Studio installed, all I had to do was to install the Pepper SDK plugin before creating my first “Hello World” robot application. You can follow the official Getting Started guide for detailed instructions, and here I’m sharing with you a brief summary of the steps I took (note I already had JDK and Android Studio installed):

  1. In Android Studio, install the Pepper SDK plugin; then the Robot SDK Manager icon appears on the Android Studio main tool bar
  2. Click the Robot SDK Manager icon to get the Robot SDK and tools
  3. Creating my first robot application
  • First create a regular Android application with minSDK = API 22 Android 5.1 Lollipop.
  • Then click File > New > Robot Application. Then notice these changes:

These two robot development related icons in Android Studio become enabled: Emulator and Connect/Disconnect. The 4th icon Wakeup is still grayed out since I don’t have a real robot to connect to.

Source: Margaret Maynard-Reid/Medium

Source: Margaret Maynard-Reid/Medium

The Android project structure gets updated to the Robot Project Structure. Dependencies are automatically added in build.gradle file:

compile 'com.aldebaran:libqi-java-android:sdk-2016-05-16'
compile 'com.aldebaran:qisdk:0.7'
compile 'com.aldebaran:qichatplayer:1.0.1'
  • I set CPU/ABI as x86 and checked “Use Host GPU” under Run/Debug Configuration/AVD option. Make sure to launch the emulator by clicking on the Robot Emulator icon, instead of using a virtual device from the Android Studio AVD Manager.
  • When the Robot emulator launches, the Robot Viewer also gets launched.

Without an actual robot I was still able to follow the first 3 of the tutorialsSay “Hello, world!”, Go to one meter forward and Mimic the elephant.

I will share more as I continue to learn about Pepper. Hopefully in the near future, we all can make apps that work with Pepper the humanoid robot.



tags: ,


Margaret Maynard-Reid is an Android Developer currently building apps that showcase how we can leverage machine learning.
Margaret Maynard-Reid is an Android Developer currently building apps that showcase how we can leverage machine learning.





Related posts :



Robot Talk Episode 120 – Evolving robots to explore other planets, with Emma Hart

  09 May 2025
In the latest episode of the Robot Talk podcast, Claire chatted to Emma Hart from Edinburgh Napier University about algorithms that 'evolve' better robot designs and control systems.

Robot Talk Episode 119 – Robotics for small manufacturers, with Will Kinghorn

  02 May 2025
In the latest episode of the Robot Talk podcast, Claire chatted to Will Kinghorn from Made Smarter about how to increase adoption of new tech by small manufacturers.

Multi-agent path finding in continuous environments

  01 May 2025
How can a group of agents minimise their journey length whilst avoiding collisions?

Interview with Yuki Mitsufuji: Improving AI image generation

  29 Apr 2025
Find out about two pieces of research tackling different aspects of image generation.

Robot Talk Episode 118 – Soft robotics and electronic skin, with Miranda Lowther

  25 Apr 2025
In the latest episode of the Robot Talk podcast, Claire chatted to Miranda Lowther from the University of Bristol about soft, sensitive electronic skin for prosthetic limbs.

Interview with Amina Mević: Machine learning applied to semiconductor manufacturing

  17 Apr 2025
Find out how Amina is using machine learning to develop an explainable multi-output virtual metrology system.

Robot Talk Episode 117 – Robots in orbit, with Jeremy Hadall

  11 Apr 2025
In the latest episode of the Robot Talk podcast, Claire chatted to Jeremy Hadall from the Satellite Applications Catapult about robotic systems for in-orbit servicing, assembly, and manufacturing.

Robot Talk Episode 116 – Evolved behaviour for robot teams, with Tanja Kaiser

  04 Apr 2025
In the latest episode of the Robot Talk podcast, Claire chatted to Tanja Katharina Kaiser from the University of Technology Nuremberg about how applying evolutionary principles can help robot teams make better decisions.



 

Robohub is supported by:




Would you like to learn how to tell impactful stories about your robot or AI system?


scicomm
training the next generation of science communicators in robotics & AI


©2025.05 - Association for the Understanding of Artificial Intelligence


 












©2025.05 - Association for the Understanding of Artificial Intelligence