Author Archives: isl_admin

MINIK Robots

MinikRobots

 

 

 

 

 

Minik robots  have been designed and developed in ISL. There are  5 Minik robots.

They are differential type and have motion mechanisms.

History:

  • Fall 2016:
    • Low level motion control: Updated Arduino-based systems.
  • Spring 2017:
    • The first version of vision system is integrated.
  • Fall 2018:
    • Their vision system has been updated.
    • Their processors are Rasperry Pi 3.

These robots are used in EE451 as part of final Project.

EE 451 Final Project Videos

2016-2017:

Group 1

Group 2

Group 3

Group 4

Group 5

 

2017-2018:

Group 2

Group 4

Group 6

Group 7

Group 9

Group 10

 

2018-2019:

Group 1

Group 2

Group 3

Group 4

Group 5

 

UAV – UGV Cooperation

This work focuses on the design and development of quadrotors that are capable of autonomous landing on a stationary platform. This problem is motivated by the fact that quadrotors have to land frequently to charge their batteries, as maximum flight time is rather short with the current state-of-art. In this work, we particularly consider three different quadrotor systems including the quadrotor constructed in our Intelligent Systems Laboratory, the ISL quadrotor. The ISL quadrotor is endowed with a camera attached to a gimbal stabilizing the view for visual sensing, a laser range sensor for measuring the altitude, PIXHAWK flight controller and a Raspberry Pi 3 (RPi3) as an onboard computer for autonomous operation. The software is designed and developed in Robot Operating System (ROS) and includes control, visual processing and serial communication with the flight controller. The code is designed to be multi-threaded as have the quadrotor be capable of doing visual processing concurrently with flight control. The dynamic modeling of the quadrotor is based on one of the commonly used models. For the landing task, position, altitude, and velocity controllers based on proportional and derivative (PD) control are developed. Position information is provided by visual feedback through detecting the marker on the landing platform. The developed approaches are first tested on the Gazebo simulation environment. We also conduct similar landing experiments on the ISL quadrotor for different wind, light, and initial altitude conditions and observe that the quadrotor is able to land autonomously within approximately 80 cm error range on a stationary platform that is marked by a 50cm $\times$ 50cm ArUco marker. The designed quadrotor is also capable of tracking a platform that is moving with a slow linear velocity.
diyquadrotor1 marker23

For more info, pls contact Mustafa Mete.

Place Learning from Others

The number of service robots increases every year and thus, service robotics has become a popular research topic among researchers. As a core ability, a service robot needs to sense human presence and follow the instructor along the environment. The robot needs to adapt its movement in order not to crash any obstacles or people along the way. While moving, the robot should be able to distinguish different places (e.g rooms in an indoor application) by observing visual properties.  Throughout this study, we aim to build a mobile robot that have these abilities. The robot will use RGB-D sensors for environmental awareness and human tracking. In parallel, the robot will  employ the  topological spatial cognition model (Karaoguz & Bozma, 2016). As such,  place learning will be accomplished as guided by the human.

flowModel

For more info, pls contact Serhat Iscan

Multirobot Navigation & Coordination

Through a series of projects, we have been investigating multirobot navigation and coordination. Such problems arise in a range of tasks including  search-rescue operations, construction, industrial applications, surveillance, team games, exploration and  unmanned vehicles.

Isomorphic Adjacency:  In many multirobot tasks, the goal is to realize a given planar topology. If all the robots are identical, then we have shown the problem can be expressed as finding an isomorphic adjacency matrix.  We have then presented a new approach to solving the resulting combinatorial problem as consisting of two stages.

D. Şenel, H. I. Bozma, and F. Öztürk, “Finding optimal isomorphic goal adjacency,” in 2016 IEEE International Conference on Robotics and Automation (ICRA), 2016, pp. 4650-4655. 

For more info, pls contact Deniz Şenel.

Coordinated realization:  Coordinated realization arises when the robots are required to move to a set of  positions that are specified by their relative positions only. In this project, our goal is to develop a systematic approach than enables coordinated realization.

Coordinated navigation:    Coordinated navigation arises when the robots are required to move to given local locations. We have constructed an essential navigation function that guarantees collision-free motion of each robot to its destination from almost all initial free placements.

S. C. Karagoz, H. I. Bozma, and D. E. Koditschek, “Coordinated navigation of multiple independent disk-shaped robots,” IEEE Transactions on Robotics, vol. 30, iss. 6, pp. 1289-1304, 2014. 

Autonomous Navigation

Navigation is one of the fundamental problems in the robotics. It can be defined as controlling the movement of a vehicle from one place to another.  In the case of previously available maps the problem becomes relatively easier, but still poses considerable challenges for real-time operation of the robot. Alternatively, if the robot is in an unknown environment and needs to explore it, then it must be accompanied by map building and exploration strategies.  The goal of this project is to consider navigation – in both known and unknown environments.

navigation2

For more info, pls contact Kadir Türksoy.

This project is supported in part by Tübitak-EEEAG.

Semantic Spatial Cognition

 

We are interested in semantic spatial cognition. This is a complex process and involves many processes.

Place recognition and learning: The goal here is to understand how  places are represented, detected and recognized.  Appearance plays key role in place detection and recognition as geometric or odometric data may not be always available.  For this, we have developed the Topological Spatial Cognition (TSC) model (Karaoguz & Bozma, 2016).

 

Continue reading