Personal drones are becoming part of every day life. To fully integrate them into society, it is crucial to design safe and intuitive ways interact with these aerial systems. The recent advances on User-Centered Design (UCD) applied Natural User Interfaces (NUIs) intend make use human innate features, such as speech, gestures vision technology in the way humans would one another. In this paper, a Graphical Interface (GUI) several NUI methods studied implemented, along computer techniques,...

Lateral flow assay tests are nowadays becoming powerful, low-cost diagnostic tools. Obtaining a result is usually subject to visual interpretation of colored areas on the test by human operator, introducing subjectivity and possibility errors in extraction results. While automated readers providing result-consistent solution widely available, they lack portability. In this paper, we present smartphone-based reader for drug-of-abuse lateral tests, consisting an inexpensive light box...

The motivation of this research is to show that visual based object tracking and following reliable using a cheap GPS-denied multirotor platform such as the AR Drone 2.0. Our architecture allows user specify an in image robot has follow from approximate constant distance. At current stage our development, event loss system starts hover waits for recovery or second detection, which requires usage odometry measurements self stabilization. During task, software utilizes forward-facing camera...

We present a vision based control strategy for tracking and following objects using an Unmanned Aerial Vehicle. have developed image visual servoing method that uses only forward looking camera from multi-rotor UAV, without any dependence on GPS systems. Our proposed tracks user specified object continuously while maintaining fixed distance the also simultaneously keeping it in center of plane. The algorithm is validated Parrot AR Drone 2.0 outdoor conditions people, occlusions fast moving...

In this paper a scalable and flexible Architecture for real-time mission planning dynamic agent-to-task assignment swarm of Unmanned Aerial Vehicles (UAV) is presented. The proposed architecture consists Global Mission Planner (GMP) which responsible assigning monitoring different high-level missions through an Agent (AMP), in charge providing each task the to UAV swarm. objective carry out such as autonomous multi-agent exploration, automatic target detection recognition, search rescue,...

To simplify the usage of Unmanned Aerial Systems (UAS), extending their use to a great number applications, fully autonomous operation is needed. There are many open-source architecture frameworks for UAS that claim UAS, but they still have two main open issues: (1) level autonomy, being in most cases limited and (2) versatility, them designed specifically some applications or aerial platforms. As response these needs issues, this paper presents Aerostack, system multi-purpose software...

Collaborative Simultaneous Localization and Mapping (CSLAM) is critical to enable multiple robots operate in complex environments.Most CSLAM techniques rely on raw sensor measurement or low-level features such as keyframe descriptors, which can lead wrong loop closures due the lack of deep understanding environment.Moreover, exchange these measurements among requires transmission a significant amount data, limits scalability system.To overcome limitations, we present Multi S-Graphs,...

Mobile robots should be aware of their <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">situation</i> , comprising the deep understanding surrounding environment along with estimation its own state, to successfully make intelligent decisions and execute tasks autonomously in real environments. 3D scene graphs are an emerging field research that propose represent a joint model geometric, semantic relational/topological dimensions. Although have...

This work introduces TRIGGER, the first lighTweight univeRsal jammInG Gripper for aErial gRasping. TRIGGER is an omnidirectional, landing-capable aerial grasping system with resilience and robustness to collisions inherent passive compliance. In particular, this presents design, fabrication, experimental validation of a novel, intelligent, modular, universal jamming gripper specifically designed applications. Leveraging recent developments in particle soft granular materials, produces 15N...

This paper investigates the application of Deep Reinforcement (DRL) Learning to address motion control challenges in drones for additive manufacturing (AM). Drone-based promises flexible and autonomous material deposition large-scale or hazardous environments. However, achieving robust real-time a multi-rotor aerial robot under varying payloads potential disturbances remains challenging. Traditional controllers like PID often require frequent parameter re-tuning, limiting their applicability...

In this paper we tackle the problem of landing a helicopter autonomously on ship deck, using as main sensor, an on-board colour camera. To create test-bed, first adequately simulate movement platform Sea, for different Sea States, ships, randomly and realistically enough. We use commercial parallel robot to get movement. Once had this, developed accurate robust computer vision system measure pose helipad with respect deal noise possible fails vision, state estimator was created. With all are...

In this paper, we present an evolved version of the Situational Graphs, which jointly models in a single optimizable factor graph, SLAM as set robot keyframes, containing its associated measurements and poses, 3D scene high-level representation environment that encodes different geometric elements with semantic attributes relational information between those elements.Our proposed S-Graphs+ is novel four-layered graph includes: (1) keyframes layer pose estimates, (2) walls representing wall...

Fiducial markers are widely used in various robotics tasks, facilitating enhanced navigation, object recognition, and scene understanding. Despite their advantages for robots Augmented Reality (AR) applications, they often disrupt the visual aesthetics of environments because visible to humans, making them unsuitable non-intrusive use cases. To address this gap, paper presents "iMarkers"-innovative, unobtrusive fiducial detectable exclusively by equipped with specialized sensors. These offer...

Autonomous navigation in unknown environments populated by humans and other robots is one of the main challenges when working with mobile robots. In this paper, we present a new approach to dynamic collision avoidance for multi-rotor unmanned aerial vehicles (UAVs). A nonlinear model predictive control (NMPC) proposed safely navigate workspace static and/or moving obstacles. The uniqueness our lies its ability anticipate dynamics multiple obstacles, avoiding them real-time. Exploiting active...