Search

Search Results

• Hopping Rover Navigation Method for Rugged Environments

  1-6.

  Gabor Kovacs

  Yasuharu Kunii

  Hideki Hashimoto

  Views:

  314

  In this paper a navigation method is presented for space exploration robots using hopping motion in environments with large elevation differences. A monocular camera system is used to reconstruct the flight trajectory and environment around the robot using Structure from Motion while traveling. The created environmental point cloud is projected to 2D to create a variable resolution image and image processing is used to find the most suitable position for the next landing based on normals with the help of gradient maps and error estimation. The method is evaluated in a simulation environment against the previously used protrusion based method to show that the proposed system can extend the operation of the robot to terrains with large elevation differences while still successfully avoid obstacles and dangerous areas.

• Navigation of Differential Drive Mobile Robot on Predefined, Software Designed Path

  1-5.

  Áron Papp

  László Szilassy

  József Sárosi

  Views:

  161

  This paper will be presenting the process of mobile robot movement controlling, from the task of collecting sensor data until the problem of controlling data to the servo motor controllers. In details, the first part will show the mechanism of converting CAD data to routes, and the processing of the navigation data read from the sensors and calculated from former controlling commands. The second part will explain the processing of navigation data, the applying of the actual robot position and orientation on the predefined virtual path and the production of the controller's input variables. The Fuzzy controller and the rule base will be introduced in the third part.

• A Review Regarding Deep Learning Technology in Mobile Robots

  1-5.

  Vlad Ovidiu Mihalca

  Flaviu Birouaș

  Florin Avram

  Arnold Nilgesz

  Views:

  113

  Deep Learning usage is spread across many fields of application. This paper presents details from a selected variety of works published in recent years to illustrate the versatility of the Deep Learning techniques, their potential in current and future research and industry applications as well as their state-of-the-art status in vision tasks, where their efficiency is experimentally proven to near 100% accuracy. The presented applications range from navigation to localization, object recognition and more advanced interactions such as grasping.

• Rigged hand model for the Blender Game Engine

  1-7.

  B. Katalin Szabó

  Views:

  498

  In a lot of virtual reality applications, it is necessary to display and animate the user's hand in the virtual world. In game engines, armatures are often used for modeling parts or the whole of the human body. The process of creating the armature and assigning parts of the mesh representing flesh and skin to the “bones” of the armature is called rigging. After performing rigging, moving the armature will result in the movement of the mesh, thus the virtual hand (or other object) is animated. The Blender Game Engine (BGE) is one of the few open-source game engines available. The paper gives a detailed description of the process of successfully building a complex rigged hand model for the BGE and gives guidance for driving this hand model with input data from the Leap Motion hand movement detector. The rigged hand model has been implemented, using the hand mesh from the LibHand library and an armature specifically built to match the hand representation of the Leap Motion. The model will be used for navigation and interaction in the virtual model of a power plant control room.

• Home Compatible Omnidirectional Hovercraft Robot

  1-7.

  Gergely Nagymáté

  Zita V. Farkas

  Views:

  115

  As robots slowly integrate into home environments, synthesis of navigation, maneuverability and human acceptance is inevitable. This paper introduces a holonomic hovercraft design and the associated omnidirectional controlling algorithm. Hovercraft capabilities were investigated and discussed though design recommendations in relation to a robot compatible environment. The main aim of the design was to achieve better maneuverability, enhanced capabilities of overcoming obstacles, and the elimination of the drift phenomena that is a characteristic of conventional underactuated hovercraft designs, where rear rotor drive exerts thrust in one direction. Due to own inertia and the low friction of the air cushion, the hovercraft slips out in the original direction. Beyond solving this drift problem, another key feature of our design is the capability to be controlled in a global reference frame regardless of its orientation and desired trajectory with the help of a holonomic thruster drive. Orientation control is also implemented by turning the base of the thrusters. The design was implemented on a remote controlled hovercraft robot and proved to have a superior maneuverability over conventional hovercraft designs, thus our research greatly contributes to future human-robot cooperation in the living environment.