Autonomous Robots Lab
  • Home
  • News
  • Research
    • Autonomous Navigation and Exploration
    • Fixed-Wing UAVs
    • Agile and Physical Interaction Control
    • Localization and 3D Reconstruction
    • Subterranean Robotics
    • Collision-tolerant Aerial Robots
    • Marine Robotics
    • Intelligent Mobility >
      • Student Projects
      • Electric Bus Datasets
    • Robotics for Nuclear Sites
    • Degerminator
    • Autonomous Robots Arena
    • Code
    • Media
    • Research Presentations
    • Projects
  • Publications
  • Group
    • People
    • Research Collaborators
    • Positions
  • Education
    • Introduction to Aerial Robotics >
      • Online Textbook >
        • Modeling >
          • Frame Rotations and Representations
          • Multirotor Dynamics
        • State Estimation >
          • Inertial Sensors
          • Batch Discrete-Time Estimation
          • The Kalman Filter
        • Flight Control >
          • PID Control
          • LQR Control
          • Linear Model Predictive Control
        • Motion Planning >
          • Holonomic Vehicle BVS
          • Dubins Airplane
          • Collision-free Navigation
          • Structural Inspection Path Planning
        • Simulation Tools >
          • Simulations with SimPy
          • MATLAB & Simulink
          • RotorS Simulator >
            • RotorS Simulator Video Examples
      • Lecture Slides
      • Literature and Links
      • RotorS Simulator
      • Student Projects
      • Homework Assignments
      • Independent Study
      • Video Explanations
      • Syllabus
      • Grade Statistics
    • Autonomous Mobile Robot Design >
      • Lecture Slides
      • Semester Projects
      • Code Repository
      • Literature and Links
      • RotorS Simulator
      • Video Explanations
      • Resources for Semester Projects
      • Syllabus
    • Robotics for DDD Applications
    • CS302 - Data Structures
    • Student Projects >
      • Robot Competitions
      • Undergraduate Researchers Needed
      • ConstructionBots - Student Projects
    • EiT TTK4854 - Robotic Ocean Waste Removal
    • Aerial Robotic Autonomy >
      • Breadth Topics
      • Deep-dive Topics
      • Literature
    • Robotics Seminars
    • Robotics Days
    • Outreach >
      • Drones Demystified! >
        • Lecture Slides
        • Code Repository
        • Video Explanations
        • RotorS Simulator
        • Online Textbook
      • Autonomous Robots Camp >
        • RotorS Simulator
      • Outreach Student Projects
    • BadgerWorks >
      • General Study Links
      • Learn ROS
      • SubT-Edu
  • Resources
    • Autonomous Robots Arena
    • Robot Development Space
  • Contact

BadgerWorks

High-risk, High-reward Research for Undergraduates
Picture
What is BadgerWorks? The goal of “BadgerWorks: High-risk Research for Undergraduates” is to develop an undergraduate student-organization for ground-breaking robotics and AI research, an organization tailored to undertaking great challenges and moon-shot projects. BadgerWorks aims to be the place for highly-motivated students to build their skill, the environment in which the most difficult but also most rewarding problems are attempted to be solved. As such, BadgerWorks can have significant impact in the excellence of our University and offers outstanding educational, research and career building experiences. 
What is BadgerWorks working on? BadgerWorks is organized around thematic long-term moonshot-like projects. Currently, the BadgerWorks activities are organized around one major topic,, namely the development of new concepts for Subterranean Robotics. In that framework we question if we can and what it takes to make robots able to operate autonomously in the underground environment? Can they enter cave networks, explore and map them? Can we develop small robots capable of opening (boring) tunnels and creating complex underground networks much like many animals do? What innovations in vehicle design, sensing, control, planning and reinforcement learning techniques are required? The goal is to assemble a multi-disciplinary team of 5 undergraduates to conduct fundamental research in relation to these problems. Two core milestones are considered, namely that of navigation in cluttered underground cave-type environments and b) the ability of drilling a hole of a size such that the robot can burry itself underground.

"Aardvark" Leg-Wheel Robot

As a first step in that direction we have been working to develop the "Aardvark" Leg-Wheel Robot (LWR). A 3D visualization of the envisioned robotic system is shown on the right, while preliminary results with respect to its ability to climb stairs are shown in the linked video. 

In further detail, the Aardvark LWR robot utilizes four independently actuated motors that drive a pentagon-shaped "leg-wheel" and thus is tailored to rough terrain and especially to climb stairs. Aardvark integrates, at its current design, a stereo visual-inertial localization system and a 2D LiDAR system - both interfaced by an onboard Intel i7 processor. The team of students working on Aardvark are currently designing its control law and perform a series of improvements with respect to its design. Furthermore, we seek to deploy a set of machine learning algorithms for automated object detection and then combine this information with the real-time mapping capabilities of the robot to estimate the position of objects in the environment. Finally, we aim to allow Aardvark to ferry a small aerial robot and support its autonomous take-off and landing from its structure.

To help us further develop Aardvark, SICK - a LiDAR company - has welcomed our participation in the TiM$10kChallenge which offers the opportunity to students to go after a $10k award given a successful robot design. We invite students to contact us and become members of our team, members of BadgerWorks (either in the role of an undergraduate or a graduate mentor) and thus gain significant experiences and contribute into a challenging robot design. Participation in the project allows to be part of the team that will compete for the $10k student award from SICK, while simultaneously being part of our CERBERUS project for the DARPA Subterranean Challenge. If you have interest, please contact us at kalexis@unr.edu
Picture
How do we work at BadgerWorks? In principle, BadgerWorks emphasizes on the self-organization and knowledge development among students. For that purpose students are encouraged to organize their own lectures, coding workshops, hackathons and other such activities for collaborative knowledge development and sharing of know-how. However, further to this basic direction, students in BadgerWorks are supervised by members of the Autonomous Robots Lab both at the individual and at the team level. In addition, a series of activities are organized by the lab in relation to BadgerWorks including specialized seminars, lab presentations, workshops to explain key robotic methods and software and more.
What resources do we have available? BadgerWorks is hosted at the facilities of the Autonomous Robots Lab at the Applied Research Facility (ARF) building. Members of BadgerWorks have access to a) the Autonomous Robots Arena for comprehensive robot testing and evaluation, and b) the robot development equipment of our lab. You have the benefit of being assigned a dedicated space and the ability to access and use world-class research infrastructure.
How do I get involved? Please send an e-mail at kalexis@unr.edu. Some of us will meet and discuss with you to get you immediately involved!
Can I combine it with my studies? Yes! Directed and independent studies perfectly fit the scope of work and vision of BadgerWorks. Contact kalexis@unr.edu to arrange accordingly.

Indicative Student Projects

  • Reactive Collision Avoidance for Aerial Robots Navigating in Underground Environments [Download]
  • Collision Resilient Navigation for Aerial Robots in Confined Environments [Download]
  • Fusion of UWB Range Data with Visual-Inertial Localization for Aerial Robots Navigation in Underground Settings [Download]
  • Fusion of Sonar, Camera and LiDAR Data for Enhancing the Perception Capabilities of Underground Robots [Download]
  • Single Image Depth Prediction using Deep Neural Networks for Aerial Robots in Underground Environments [Download]
Picture
Download a relevant presentation reflecting some activities of our lab (May 2018 - Video)

Software to get you started

ROS-ready Ubuntu Virtual Machine
  • Ubuntu version: Ubuntu 16.04 LTS
  • ROS version: Kinetic
  • username: badgerworks
  • password: badgerworks
  • Includes built RotorS Simulator and Visual Saliency-aware Exploration Path Planning packages
    • Path: ~/catkin_ws
  • Ensure USB access to the VM if you want to use a gamepad
  • Ensure internet access to the VM
  • You will need a system with GPU-based 3D Acceleration.
  • Example of out-of-the-box functionality - Video
Picture
Repository of Code Examples
  • Code examples for BadgerWorks and Courses provided by our lab
  • Link: https://github.com/unr-arl/autonomous_mobile_robot_design_course
  • Indicative examples included
    • Control Systems (e.g., MPC, PID)
    • State Estimation (Bayes, Kalman Filter, EKF)
    • Path Planning (RRT, RRT*, Inspection Planning, Exploration)
    • Perception (SLAM, Feature Extraction, Object Detection)
    • Dynamics (Simulation of Quadrotor)
    • Hardware interfacing (camera, IMU, RGB-D sensors)
  • Languages used: C++, Python, MATLAB
Picture

Study links

• Introduction to Aerial Robotics course (UNR). Click here.
• Autonomous Mobile Robot Design course (UNR). Click here.


Open-Source Code

• Code Repository of the Autonomous Mobile Robots Design course. Click here.
• GitHub repositories of the Autonomous Robots Lab. Click here.

More

• CMU Robotics Seminars. Click here.
• General study links. Click here.

BadgerWorks Knowledge Bank

Perception & Estimation
Picture
Perception & Estimation #1: Bayesian estimation, Kalman Filter, Extended Kalman Filter
Path Planning
Picture
Path Planning #1: Collision-free navigation, Exploration, Coverage
Picture
Path Planning #2: Exploration and Inspection Planning (overlap with #1)
Picture
Path Planning #3: Polynomial Trajectory Planning for Quadrotor Flight
Picture
Path Planning #4: Graph Search - Dijkstra, A*, Voronoi Graphs
Picture
Path Planning #5: Collaborative Visual Area Coverage
Control
Picture
Control Systems #1: Introduction to control systems, stability, PID, LQR


Proudly powered by Weebly