Lesson List

Welcome

Learn how to simulate your first robotic environment with Gazebo, the most common simulation engine used by Roboticists around the world.

What is a Robot

Search and Sample Return

Project - Search and Sample Return

Career Support Overview

Get Help from Peers and Mentors

Explores – Biologically Inspired Robots

Questions on Robotics Careers

Intro to Kinematics

Forward and Inverse Kinematics

Project: Robotic Arm: Pick & Place

Project 1: Build My World

Explores – Human Robot Interaction Robot Ethics

Product Pitch

Perception Overview

Introduction to 3D Perception

Introduction to 3D Perception

Calibration, Filtering, and Segmentation

Clustering for Segmentation

Object Recognition

3D Perception Project

Explores – Soft Robotics

Explores – Robot Grasping

Introduction to Controls

Introduction to Controls

Quadrotor Control using PID

Explores Swarm Robotics

Networking in Robotics

Intro to Neural Networks

Intro to Neural Networks

TensorFlow for Deep Learning

Deep Neural Networks

Convolutional Neural Networks

Fully Convolutional Networks

Lab Semantic Segmentation

Project Follow Me

Term 1 Outro

Introduction to C++ for Robotics

C++ for Robotics

Introduction to Term 2

The Jetson TX2

Interacting with Robotics Hardware

Lab Hardware Hello World

Robotics Sensor Options

Inference Development

Inference Applications in Robotics

Project Robotic Inference

Project: Robotic Inference

Introduction to Localization

Learn how Gaussian filters can be used to estimate noisy sensor readings, and how to estimate a robot’s position relative to a known map of the environment with Monte Carlo Localization (MCL).

Kalman Filters

Lab Kalman Filters

Monte Carlo Localization

Build MCL in C++

GraphSLAM

Project Where Am I

Project: Where Am I?

Introduction to Mapping and SLAM

Learn how to create a Simultaneous Localization and Mapping (SLAM) implementation with ROS packages and C++. You’ll achieve this by combining mapping algorithms with what you learned in the localization lessons.

Occupancy Grid Mapping

Grid-based FastSLAM

Project Map My World Robot

Project: Map My World Robot

Intro to Path Planning and Navigation

Learn different Path Planning and Navigation algorithms. Then, combine SLAM and Navigation into a home service robot that can autonomously transport objects in your home!

Classic Path Planning

Lab Path Planning

Sample-Based and Probabilistic Path Planning

Research in Navigation

Project: Home Service Robot

Project: Home Service Robot

Project Details

Intro to RL for Robotics

RL Basics

Q-Learning Lab

Deep RL

DQN Lab

Deep RL Manipulator

Project Deep RL Arm Manipulation

Project: Deep RL Arm Manipulation

Job Search

Find your dream job with continuous learning and constant effort

Refine Your Entry-Level Resume

Craft Your Cover Letter

Optimize Your GitHub Profile

Develop Your Personal Brand

Go to course home
01. What is a Robot

Explore the Simulator

Unity Environment

We used the Unity game engine to build the simulated environment you’ll be navigating through in this project. Unity offers a free personal license and is largely open-source, making it a great option for a program like this. It works across Linux, OS X and Windows platforms.

You don’t need to know anything more about Unity to use the simulator, but if you want to learn more or get started building your own environments check out their website! The code we used to build the environment for this project is all open-source and you can check out the code in this repository.

 

Download and Launch the Simulator

The first step of the project is to download the simulator and familiarize yourself with how it works. Use the links below to get the simulator version that’s appropriate for your operating system.

MacOS Simulator Build
Linux Simulator Build
Windows Simulator Build

When you launch (double click on) the simulator you will have the option to set the resolution and graphics quality. You could choose lower resolution / quality for faster rendering. Be sure to check the box next to Windowed so the simulator doesn’t take up the full screen. Click on the input tab to change the keyboard input definitions; this may be necessary if you are on a non-U.S. keyboard. The next time you launch, these settings will be restored. Click Play to launch the simulator!

Once you click Play you’ll see a screen that looks like the one below. Choose Training Mode to be able to manually drive the rover around in the environment. You’ll notice the app takes over your mouse immediately. You can use the Esc key to get your mouse back.

Manual Controls

Experiment in Training Mode with the various manual functions.

  • Throttle, brake and steering: wsad letters or arrow keys (can also steer with mouse)
  • Toggle mouse function between camera perspective and steering: esc key
  • Change the viewing perspective: tab key or mouse
  • Change zoom on the viewing camera: mouse scroll
  • Reset viewing camera zoom: middle mouse button (MMB)
  • Activate the robot arm to pick up a sample: left mouse button (LMB) or enter key (only works when is near objective = yes)

Have a look around and explore the environment!

Note: Unity vs. Gazebo

Later in this program you’ll be using the Gazebo simulation environment because of the powerful physics engine it offers and its seamless integration with the Robot Operating System or ROS, which you’ll learn about in the next lessons. Unity, however, offers much more photorealistic image quality than Gazebo, which can be a major advantage for computer vision applications. In this program we provide you with exposure to both Unity and Gazebo because both are powerful tools and each has its own unique advantages.

Simulation is a huge part of robotics development and several teams (including our own) are working to make the connection between ROS and Unity much more fluid. As such, going forward as a roboticist, you can expect to get even more exposure to working with game engines in simulation.

Previous
Next