We present a human-centered designed social drone aiming to be used in human crowd environment. Based on design studies and focus groups, we created prototype of with shape, face voice for interaction. the proxemic study, comparing required distance from humans could comfortably accept compared what they would require nonsocial drone. The shaped greeting added decreased acceptable markedly, as did or previous pet ownership, maleness. also explored proximity sphere around based validation...

Recent research has focused on how to facilitate interaction between humans and robots, giving rise the field of human robot interaction. A related area is human-drone (HDI), investigating drones can be expanded in novel meaningful ways. In this work, we explore use as companions a home environment. We present three consecutive studies addressing user requirements design space companion drones. Following user-centered approach, stages include online questionnaire, workshops, simulated...

“Flight Time” and the “Scope of mission” play major roles in using UAVs as they affect most industrial activities. Once battery has depleted, UAV to land on ground human interaction is needed change with a fully charged one. Nowadays, several automatic swapping systems are catching interest research. This research presents novel concept an Inverted Docking Station that allows quadrotor attach ceiling during battery-swapping process. The proposed design consist docking station, positioning...

The ability of robots to understand human characteristics and make themselves socially accepted by humans are important issues if smooth collision avoidance between is be achieved. When discussing avoidance, robot should not only physical components such as position, but also social body pose, face orientation proxemics (personal space during motion). We integrated these in a modified force model (MSFM) which allows predict motion perform avoidance. In the model, short-term intended...

We propose a social navigation model that allows robot to navigate in human environment according intentions, particular during situation where the encounters and he/she wants avoid, unavoid (maintain his/her course), or approach robot. Avoiding, unavoiding, approaching trajectories of humans are classified based on face orientation force their predicted motion. The proposed is developed motion behavior (especially overlapping personal space) analysis preliminary experiments. Our...

Low light situations pose a significant challenge to individuals working in variety of different fields such as firefighting, rescue, maintenance and medicine. Tools like flashlights infrared (IR) cameras have been used augment the past, but they must often be operated manually, provide field view that is decoupled from operator's own view, utilize color schemes can occlude content original scene. To help address these issues, we present VisMerge, framework combines thermal imaging head...

Inspection and maintenance are extremely important to maintain safety long-term usability of bridges. This application requires a robot that is able maneuver in complex 3D environment stabilize on steel surfaces perform bolts checking. We propose novel design concept hybrid (integrated walkability flyability) for bridge inspection maintenance. Our proposed allow the access structure without being time consuming. In order our space, we present vibration control based vibrator compensate...

This paper presents an alternative approach to identify and classify the small flying drones from birds in near field, by examining pattern of their flight paths trajectories. The trajectories were extracted multiple clips videos including various natural synthetic database. Small that are piloted both automatically manually usually fly a stable manner. Their straight smooth with sharp angle turns. Whereas being flyers have intrinsically periodic due flapping motion occasional glides soaring...

Drone navigation in complex environments poses many problems to teleoperators. Especially 3D structures like buildings or tunnels, viewpoints are often limited the drone's current camera view, nearby objects can be collision hazards, and frequent occlusion hinder accurate manipulation. To address these issues, we have developed a novel interface for teleoperation that provides user with environment-adaptive automatically configured improve safety smooth operation. This real-time adaptive...

Drone navigation in complex environments poses many problems to teleoperators. Especially three dimensional (3D) structures such as buildings or tunnels, viewpoints are often limited the drone’s current camera view, nearby objects can be collision hazards, and frequent occlusion hinder accurate manipulation. To address these issues, we have developed a novel interface for teleoperation that provides user with environment-adaptive automatically configured improve safety provide smooth...

A unified detection-tracking-estimation vision navigation system and algorithms framework for position pose estimation of small aerial vehicle (UAV) is proposed in conjunction with our recent 3D dynamic localization technique. The major contribution this work a novel combination deep learning detection moving object as the UAV, follow by tracking spatial location global frame. can be multiplied that extended systems would provide coordinates UAV. demonstrations both indoor outdoor were...

This paper presents a real-time multiple camera system for detecting, tracking and localizing moving drones simultaneously in 3 dimension space. The distinct feature of the is its target re-identification process, which provides information fusion among cameras based on targets' trajectories relative locations. Drones are detected by motion-based blob detection, 2D locations each drone individual frames tracked A geometry- camera-based model. From paths drones, their examined using track...

In virtual reality, VR sickness resulting from continuous locomotion via controllers or joysticks is still a significant problem. this article, we present set of algorithms to mitigate that dynamically modulate the user's field view by modifying contrast periphery based on movement, color, and depth. with previous work, vision modulator shader triggered specific motions known cause sickness, such as acceleration, strafing, linear velocity. Moreover, algorithm governed delta velocity, angle,...

Robot navigation in a human environment is challenging because moves according to many factors such as social rules and the way other moves. By introducing robot environment, situations are expected want interact with or humans expect avoid collision. modeling have take these into consideration. This paper presents Social Navigation Model (SNM) unified interaction model that allows navigate response intentions, particular during situation where encounters wants avoid, unavoid (maintain...

This paper presents an alternative approach to identify and classify the group of small flying objects especially drones from others, notably birds kites (inclusive kiteflying), in near field, by examining pattern their flight paths trajectories. The trajectories other were extracted multiple clips videos including various natural synthetic database. Four characteristics are observed object’s paths, i.e., heading or turning angle, curvature, pace velocity, acceleration. Subsequently,...

Prediction and observation of human motion are essential functions for robots co-existing with humans in everyday environments. We propose a people tracking prediction approach by using the advantage detailed 3D information about positions body joints. Using shoulder position displayed geometrical skeleton diagram human's upper part, pose from proposed kinematic model is estimated. Human path achieved via extended Kalman Filter. The method verified an indoor environment where pass each...

In order for robots to be a part of human society, their social accceptance is an important issue if smooth interaction with humans achieved. We propose modified force model that allows move naturally like humans, based on estimated motion and face pose. add the previous effect due pose, in predict compute robot itself. Our approach was implemented tested real humanoid situation which confronted indoor environment. Experimental results illustrate able perform human-like navigation by...

Locomotion is an essential factor for interaction in virtual environments. Virtual reality allows users to move freely from the constraints of gravity or environment, which impossible real world. These experiences, can at all 6 degrees freedom, enable new navigation paradigms that exceed 2D ground-based movement terms enjoyment and interactivity. However, most existing VR locomotion interfaces have limitations because they are developed locomotion, constraining freedom (DoF) during as This...

Abstract Firefighters need to gain information from both inside and outside of buildings in first response emergency scenarios. For this purpose, drones are beneficial. This paper presents an elicitation study that showed firefighters’ desires collaborate with autonomous drones. We developed a Human–Drone interaction (HDI) method for indicating target drone using 3D pointing gestures estimated solely monocular camera. The participant points window without any wearable or body-attached...

Packing optimization is a challenging and time-consuming task for number of industry logistics applications. Efficient packing can reduce the cost storage shipping also guarantee that damage will not occur during shipping. To help address this problem, we propose spatial augmented reality-based support system assisting workers with optimization. Our first uses an RGB-D camera to acquire color depth information items be packed destination container. Then, object segmentation dimension...