The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
The growth of 3D visualization devices, such as holograms and virtual reality, is followed by the increase of demand for 3D models. One cheap and straightforward way of creating them is by photogrammetry. However, taking the necessary photographs is tedious and imprecise, because many different shooting angles and heights are required. Also, there may be need of doing models of objects placed on hazardous...
This poster discusses the implementation and technical choices of a proof of concept experience demonstrating interactive virtual characters for immersive mixed reality (MR) applications. Our interactive virtual characters are made believable through their visual appearance, physical interaction with the environment, dynamic behavior to the user and both real and virtual stimuli, and by being able...
In this paper, we propose a safe navigation algorithm for non-holonomic flying robots. To detect the static and moving obstacles, a sensor network, which consists of some time-of-flight cameras, is deployed in a three dimensional environment. The robot or a server obtains the real-time measurements of the environment from the cameras and calculates a temporarily safe robot path from the robot's current...
We present a novel approach for collision-free global navigation for continuous-time multi-agent systems with general linear dynamics. Our approach is general and can be used to perform collision-free navigation in 2D and 3D workspaces with narrow passages and crowded regions. As part of pre-computation, we compute multiple bridges in the narrow or tight regions in the workspace using kinodynamic...
In this paper, an image-based segmentation method to improve autonomous robot navigation in the forest is presented. The detection is supported by a filtered image generated from a stereo-based pre-processing which is a byproduct of our obstacles detection system. To cope with the large variability of forest paths, the classifier is dynamically adapted to the current situation and the segmentation...
A stereo vision based autonomous navigation method for 3-DOF systems is presented in this paper. It is able to tackle the learning and recognition problem of generic scenes in an unstructured environment, providing motion-planning capability to control all the 3 DOFs of a robotic system. In this method, 3 spatial constraints are generated from a single visual recognition to estimate the robot pose...
In this paper, a monocular vision based autonomous flight and obstacle avoidance system for a commercial quadrotor is presented. The video stream of the front camera and the navigation data measured by the drone is sent to the ground station laptop via wireless connection. Received data processed by the vision based ORB-SLAM to compute the 3D position of the robot and the environment 3D sparse map...
Mobile Robot Navigation techniques are important for path calculation towards a target, avoiding collisions in an unknown environment. The existing robot navigation techniques conclude a diverse spectrum of applications in 2D space. But navigation solutions in 3D space have been hardly addressed by the researchers for a combination of a mobile platform and a robot arm. This paper proposes a novel...
We present an end-to-end method for active object classification in cluttered scenes from RGB-D data. Our algorithms predict the quality of future viewpoints in the form of entropy using both class and pose. Occlusions are explicitly modeled in predicting the visible regions of objects, which modulates the corresponding discriminatory value of a given view. We implement a one-step greedy planner and...
This paper deals with the reactive control of an autonomous mobile robot which should move safely in a unknown three-dimensional(3D) environment to reach a desired goal. In order to proceed with the problem, we propose a hybrid approach based on fuzzy logic controller (FLC) for goal seeking behavior and Deformable Virtual Zone (DVZ) reactive algorithm to address 3D obstacles avoidance. We suggest...
In this paper, we consider the problem of formation building in a 3D space for a group of mobile robots defined by the three degrees of freedom kinematics equations with the constraints on the mobile robots' angular and linear velocities. We present a decentralized control law for the robots so that they move in a given geometric configuration from any initial position. Simulation results demonstrate...
This paper proposes a robust 3D-map building process for a mobile robot using a LRF (Laser Range Finder). Instead of the expensive and bulky 3D-laser scanner, the LRF can be utilized and installed on the mobile robot for the map building and the autonomous navigation. The scanning operations are performed while the mobile robot is moving on the ground without stops. To filter out the high-frequency...
This paper presents a ground vehicle capable of exploiting haptic cues to learn navigation affordances from depth cues. A simple pan-tilt telescopic antenna and a Kinect sensor, both fitted to the robot's body frame, provide the required haptic and depth sensory feedback, respectively. With the antenna, the robot determines whether an object is traversable by the robot. Then, the interaction outcome...
Autonomous airborne systems have generated a lot of interest in civilian and military applications. The operation of such systems involves routing and navigation toward targets and obstacle avoidance. In this paper, these problems were tackled and solutions were applied to land-based robots as well as a quad-rotor aerial system. The quad-rotor flight path navigation and routing was programmed based...
A technique for merging 3D octree based occupancy grid maps is proposed and implemented. Octrees are a memory efficient way to represent a 3D environment by recursively subdividing space at multiple depths in a tree structure. The use of of an octree representation of a 3D environment allows large environments to be mapped while limiting the amount of memory used in comparison to other techniques...
This paper proposes a robust 3D (dimension) map building system for a mobile robot using a LRF (Laser Range Finder). Instead of the expensive and bulky 3D laser scanner, the LRF can be utilized and installed on the mobile robot for the map building and the autonomous navigation. This research, the scanning operations are performed while the mobile robot moved on the slanted surface and ground without...
The goal of cooperative rescue robot teams in urban search and rescue (USAR) missions is for the rescue robots to effectively work together in order to minimize the overall exploration time it takes to search disaster scenes and find as many victims as possible. To achieve this goal, task allocation and execution amongst the team members must be considered. In this paper, a unique hierarchical reinforcement...
Surgical navigation is a crucial concept in computer assisted surgery. The use of robots in the surgery room largely benefits from this concept recent developments, namely with the use of non-invasive and radiation free imaging systems, like ultrasound (US). This paper presents the algorithms and software tools developed for US based orthopedic surgery navigation. In the second part of the paper are...
In order for humanoid robots to work actively around humans, they are expected to move autonomously in public spaces. For achieving such mobile intelligence, so many researches have been conducted so far. However, most of them deal with only elements for constructing necessary mobile intelligence. While moving around public spaces, composite recognition including self-motion recognition, moving objects'...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.