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

Autonomous Exploration and Simultaneous Object Search Using Aerial Robots​


This video accompanies our submission on "Autonomous Exploration and Simultaneous Object Search Using Aerial Robots" submitted at IEEE AEROCONF 2018

Dataset for download is available through this link. 
Dataset release for the Aerospace Conference 2018 paper titled "Autonomous Exploration and Simultaneous Object Search Using Aerial Robots".

This dataset contains stereo images, synchronized IMU measurements, odometry, occupancy map and corresponding visualizations for planning steps. The provided dataset was collected during the experiment of our system using an on-board computer running Ubuntu 14.04 and ROS Jade. A list of main published topics and their brief description are provided as below:
  • /cam0/image_raw, /cam1/image_raw: left and right camera images
  • /cam0/image_rect: a rectified image from left camera used for object detection
  • /imu0: IMU data from UM7 sensor
  • /rovio/odometry_body: odometry and pose estimates by visual inertial sensors
  • /bestPlanningPath: visualization markers show the best path generated from the exploration planner
  • /nbvplanner/octomap_occupied: object occupied voxels of the octomap colorized by its property in path planning algorithm (red: voxels that are occupied by objects of interest but haven't explored sufficiently in terms of resolution, green: object occupied voxels that are reobserved in sufficient resolution, blue: normal voxel)
  • /darknet_ros/bounding_boxes: bounding boxes topic presents locations of rectangular windows in pixel which cover detected objects from YOLO classification algorithm in image coordinate
  • /darknet_ros/detection_image: image annotated with bounding boxes to visualize detection results from YOLO classification algorithm

Dataset in rosbag format can be visualized using 3D visualization tool for ROS i.e. rviz. Please note ROS Jade was used at our end for collection and visualization, a different version of ROS may have different checksum for visualization markers which may cause them not to display correctly. We also provide a .rviz configuration file for easy visualization.
Proudly powered by Weebly