Seventh Symposium on Indoor Flight Issues

The 2015 Symposium on Indoor Flight Issues was held during August 2015 at the American Venue in Atlanta, Georgia, USA, and in November 2015 at the Asia/Pacific Venue in Beijing, China. The Symposium on Indoor Flight Issues at the American venue was enhanced this year by the inclusion of a presentation critique by the Center for Career Discovery and Development at the Georgia Institute of Technology. Not only were the presentations evaluated professionally, but an open discussion on resumé-writing and job application/interview skills was conducted with the teams. Links to the .pdf versions of the Symposium papers are provided below:
2015 Amity University IARC Entry
Ishaan Sharma, Manoj Chaudhary
Amity University Rajasthan
Rajasthan, India
AMIBOT for International Arial Robotics Competition is ready to stand and complete the Mission 7 with its unique and latest technology to avoid collusion with the air as well as ground traffic without talking help of GPS or SLAM Technology. AMIBOT is using Milliwaves Radar which is used in Automobiles to detect and avoid collusion. Milliwaves works on the line of sight and are blocked by building walls and attenuated by foliage. This MilliWave Radar is used to navigate the AMIBOT in the competition arena. It is added with the vision module using Pixy Camera that will give AMIBOT an eye to get comfortable with the environment and Increase its precision and still keeping it fully autonomous. AMIBOT is made keeping in mind the safety and stability of the drone.
UAV of BITS Pilani, Dubai Campus for the International Aerial Robotics Competition 2015
Syed Zeeshan Ahmed, Ganesh Ram R.K., Rochal Saxena, Aashish Dugar, Ketul Patel, Ayanava Sarkar, Shreya Jain, Vikhyat Rawla , Saptadeep Debnath, Geet Capoor, Dr.V.Kalaichelvi, Prof. Dr. R. N. Saha
Birla Institute of Technology and Science, Pilani – Dubai Campus
Dubai, United Arab Emirates
This paper describes IFOR (Intelligent Flying Object for Reconnaissance) an autonomous aerial vehicle that has been developed by BITS Pilani, Dubai Campus students. The vehicle can localize and navigate in environments independent of external navigation aids such as GPS or large stationary points of reference (e.g. walls) for SLAM algorithms. Downward-facing cameras and optical flow via Px4Flow is used to localize and stabilize the attitude (pitch, roll and yaw) and altitude of the vehicle using PID controllers. It also identifies the autonomous ground robots by the forward-facing camera and avoids obstacle ground robots by setting the area near the paths of obstacle ground robots as hazardous area.
CAUC’s Aerial Robot for IARC 2015
Lu Huo, Yongzheng Shi, Long Zhao, Yunhao Zhang, Nan Jiang, Xiaoli Wang, Zeyan Yan
Civil Aviation University of China
Tianjin, Shandong, China
In this paper, the technical details of a Quadrotor system are presented, and it can avoid the obstacles to make ground robots attain the desired position, without rely on any external navigation aids. The navigation system is composed of a small computer and some sensors. We obtain absolute position estimation by a monocular visual odometry framework. A motion detector is introduced to implement rapid tracking. Furthermore, we build a motion predicting model to find strategy of tracking and interception.
Comb Studio’s Autonomous Aircraft for the IARC 2015
Wu Qi, Liu Ning-jun, Wu Kun, Wang Ting-ting, Zhang Dong-yao, Yan Kun, Ma Yan, Lin Qing
Beihang University
Beijing, China
This paper describes the details of an autonomous aircraft capable of exploring cluttered indoor areas and interacting with object in the environment without relying on external navigational aids. An integrated visual navigation method providing relative position, velocity, and attitude information is introduced. Multi-ground-object are detected by HOG-Based SVM. Mission planning section applies the velocity-obstacle method to program for the vehicle drive away ten ground robot to a set sideline. The vehicle is intended to be Beihang University Comb Studio’s entry for the International Aerial Robotics Competition in 2015.
Development of 'ERAU Raven II' Quad-Rotor System for the IARC 2015
Grady Delp, Nick Middlebrooks
Embry-Riddle Aeronautical University
Daytona Beach, Florida, United States
This paper describes the details of an autonomous aircraft capable of exploring cluttered indoor areas and interacting with object in the environment without relying on external navigational aids. An integrated visual navigation method providing relative position, velocity, and attitude information is introduced. Multi-ground-object are detected by HOG-Based SVM. Mission planning section applies the velocity-obstacle method to program for the vehicle drive away ten ground robot to a set sideline. The vehicle is intended to be Beihang University Comb Studio’s entry for the International Aerial Robotics Competition in 2015.
HITCSC's Technical Report for IARC 2015
He Hualin, Li Yibei, Wu Qifeng, Liang Zhuang
Harbin Institute of Technology
Harbin, Heilongjiang, China
This paper reports the detail scheme and progress of HITCSC Team. An autonomous aircraft equipped with DJI autopilot, Odroid XU3 onboard computer and vision cameras is designed to interact with ground robots and cruise around the arena. A kind of vision positioning algorithm based on the camera formation and image processing technology is developed to provide relative position of target robots, and navigate vehicles in the arena. A flexible platform built on Linux OS is established to maintain the whole system. Large amount of experiences are designed to ensure the robustness of flight stabilize system and adaptability of vision positioning system.
Autonomous Quadrotor for the IARC 2015
Yongseng Ng, Keekiat Chua, Chengkhoon Tan, Weixiong Shi, Chautiong Yeo
Temasek Polytechnic
Singapore, Singapore
This paper describe the technical details of an autonomous quadrotor developed by Temasek Polytechnic robotics and automation team(TPRAC) to take part in 2015 International Aerial Robotics Competition(IARC). The unmanned aerial vehicle (UAV) is capable of autonomous navigation in an indoor environment without the help of GPS or large external physical point of reference. It can also demonstrate target identification of static and moving objects at airborne. Using sensors, controllers and mechanical system from current technology, we put together an UAV with the aim of fulfilling the tasks required of competition.
Multirotor Aircraft Developed By Kennesaw State University to Compete in the 2015 IARC
Nick Schulz, Syed Ali, Brandon Hopewell, Charles Pagano, David Haffner, Haris Jafri
Kennesaw State University
Marietta, Georgia, United States
For Mission 7 of the International Aerial Robotics Competition, the Kennesaw State University Aerial Robotics Team has developed a multirotor aerial vehicle capable of stable interest based autonomous flight. Using its on-board sensor array, the multirotor can locate and interact with other robotic vehicles in order to accomplish the objectives. Additionally, the robust 3D-printed design allows the multirotor to safely withstand collisions with obstacles and other aerial vehicles encountered during the mission.
Simon Fraser University IARC Competition Journal Paper
Christopher Nsimbe, Alireza Alidousti, Luke Mulder, Dev Bhullar, Refayet Siam, Kush Chhatbar, Kathleen Moriarty, Chander Siddarth, Abiman Mahendra, Evgeny Kuznetsov
Simon Fraser University
Burnaby, British Columbia, Canada
We present a vision-based autonomous solution to this year’s International Aerial Robotics Competition (IARC) challenge. Data from our vision system is filtered for different kinds of information: static objects of the environment, and moving targets. The major static object of the environment is the grid on the arena. The features of static objects from the filtered vision data are fed into our local position estimate algorithm that relies of optical flow of these static features. We apply a Monte Carlo algorithm that gives us a rough estimate of where we are in the global (arena) grid. Information about our moving targets is fed into the target identification loop that characterizes the state of the targets. This information is used by the decision making program to plan and execute actions to affect the movement of the targets.
Multi-Object Tracking in Indoor Flight Environments
Logan Camacho, Stephany Demmler
University of Central Florida
Orlando, Florida, United States
This paper details the development and construction of a quadrotor unmanned aerial vehicle that is capable of tracking and guiding multiple randomly moving ground vehicles to the designated location. The University of Central Florida’s autonomous vehicle VINCENT was designed to compete in the 7th Mission of the International Aerial Robotics Competition. VINCENT utilizes computer vision, optical flow analysis, and priority assignment programming in order to operate fully autonomously for the duration of its flight.
Unmanned Quadrotor Helicopter of NUAA for 2015 IARC
Sun Yili, Tan Qingyan, Ma Kun, Li Kangwei, Li Teng
Nanjing University
Nanjing, Jiangsu, China
The Nanjing University of Aeronautics and Astronautics team designs and develops an unmanned quadrotor helicopter to complete the seventh IARC mission. The unmanned quadrotor helicopter is designed to autonomously fly in the arena without GPS, interacting with the ground robots, and sensing and avoiding the presence of moving special ground robots. Pixhawk Autopilot is a high-performance autopilot-on-module suitable for fixed wing, multi-rotors, helicopters, cars, boats and other robotic platform that can move. In the case without GPS, orientation and navigation of quadrotor helicopter is based on vision and optical flow sensor, through catching and tracing the ground robots and the lines of arena. Besides, to herd the ground robots toward the green side of the arena such that as many as possible cross over the green line in the shortest amount of time, optimization control algorithm is used to quadrotor helicopter.
Autonomous Quadrotor for the 2015 IARC by Team Elikos
Andre Phu-Van Nguyen, Alexandre Borowczyk, Antoine Mignon, Antonio Sanniravong
École Polytechnique de Montréal
Montréal, Quebec, Canada
The aim of this paper is to present a system design for a fully autonomous micro-aerial vehicle capable of demonstrating behavior for the completion of the IARC mission 7. While outdoor navigation methods have been extensively researched and demonstrated in the past, the system we hereby present shall be able to demonstrate indoor navigation capabilities with the use of GNC sensors, a lidar, and cameras with a heavy emphasis on computer vision for localization.
PCC's Autonomous Air Vehicle System for IARC 2015
Frank Manning, Yanitzin Todd, Tim Worden
Pima Community College
Tucson, Arizona, United States
The Pima Community College UAV Club has designed an air vehicle system to compete in the International Aerial Robotics Competition (IARC). The rules require an autonomous air vehicle to herd a group of 10 ground robots while avoiding collisions with a second group of 4 obstacle robots. All 14 ground-based robots are themselves autonomous and move according to their own internal algorithms, including responses to external collisions and magnetic fields. The air vehicle is designed to use machine vision as well as lidar and sonar scanning to sense the positions of ground robots, and to navigate relative to a 20 m x 20 m arena. The arena is marked with a known grid pattern.
Design of Autonomous Aerial Robot System
Min-Fan Ricky Lee, Cheng-Chia Lee, Meng-Ying Chuang, Tai-Lin Chin, Yu-Chuan Huang, Chieh-Sheng Lin, Ya-De Chen, Xiao-Fei Lu, Pei-Cheng Chung
National Taiwan University of Science and Technology
Taipei, Taiwan
A hierarchical and distributed UAV system is proposed including hardware, software and appearance design. For the hardware part, a quadcopter is adopted as the UAV locomotion platform. APM (ArduPilot Mega) is used for the low level flight pose control. An arduino embedded system plays the role of the interface between the onboard low level controller and the ground high level controller. Onboard sensors include compass, magnetometer, IMU (gyroscope and accelerometer), barometer, sonar and two CCD cameras. For the software part, a fuzzy logic control system is proposed for the high level autonomous navigation. The optical flow, Lucas-Kanade approach, is exploited for the localization of the UAV and the ground mobile robot through the images provided by the bottom camera. The optical flow, Gunnar Farneback approach, is applied for obstacle avoidance with the frontal camera. In particular, an innovative UAV appearance is designed and built. The aerodynamic and UAV propeller protection are the primary design considerations while not affecting the onboard sensing and motion.
BaiLu of Xiamen University
No authors listed
Xiamen University
Xiamen, Fujian, China
IARC Mission 7 is a highly complicated task for aerial robots, requiring them to be intelligent and robust enough, which demand much effort on both the hardware and the software. After careful analysis of the mission we determined that the research should be focused on flight control and visual navigation.
Autonomous Quadrotor for the 2015 International Aerial Robotics Competition
Alec Ten Harmsel, Sajan Patel
Universiy of Michigan
Ann Arbor, Michigan, United States
Unmanned Aerial Vehicles (UAVs) are becoming more popular for both professional and casual uses, but are restricted to open areas and require GPS for navigation. Vehicles capable of flying in environments without relying on GPS will pave the way toward redefining currently outdated and expensive methods of structural inspection, search and rescue, and law enforcement operations that often take place in areas with limited GPS availability. Michigan Autonomous Aerial Vehicles (MAAV) designs and builds lightweight quadrotor UAVs capable of stable, autonomous flight without GPS. MAAV’s vehicle will compete in the 2015 International Aerial Robotics Competition (IARC) where it will demonstrate its ability to autonomously manage a herd of ground vehicles in an open environment. Using a combination of control, computer vision, and path planning algorithms, it will herd ground robots over the goal line in the required time.
Super Squadron Technical Paper for IARC
Dr. Dalbir Singh, R.S. Kumar, C. Aasish, Angekin Jemi, Blessen John, Cyril Anthony, Kunal Naik, Prasanna Linci, Ranjitha, Razeen Ridhwan
Hindustan University
Chennai, Tamil Nadu, India
The Team Recon from India present an indigenously developed Super Squadron an autonomous quadcopter designed for the 7th mission of the AUVSI International Aerial Robotics Competition (IARC). This paper describes the technical details of a quadrotor system to be used as an aerial robot for interaction with ground robots and demonstrate the mission requirements. The Super Squadron exhibits the required behaviors of autonomous flight for interaction with multiple objects on ground to recognize, track and navigate in a sterile environment with no external navigational aids. The objective of multiple object tracking would be achieved using HOG - based SVM. The algorithm runs on an ARM Processor with depth camera and the autonomous navigation is done by using optical flow with higher resolution. The instant sensing by aerial robots and interaction between aerial and ground robots would be achieved - by depth sensor and a custom developed ANN and through the use of effective path based algorithms.
© Copyright 2017 International Aerial Robotics Competition