The use of drones in agriculture is becoming more and popular. paper presents a novel approach to distinguish between different field's plowing techniques by means an RGB-D sensor. presented system can be easily integrated commercially available Unmanned Aerial Vehicles (UAVs). In order successfully classify the techniques, two measurement algorithms have been developed. Experimental tests show that proposed methodology able provide good classification depths.

Abstract Multimodal learning analytics provides researchers new tools and techniques to capture different types of data from complex activities in dynamic environments. This paper investigates the use diverse sensors, including computer vision, user‐generated content, objects (physical computing components), record high‐fidelity synchronised multimodal recordings small groups learners interacting. We processed extracted aspects students' interactions answer following question: Which features...

Teleoperation in robotic embodiments allows operators to perform and program manipulation tasks with better accuracy, dexterity, visualization than what is possible traditional human-robot interaction paradigms. However, the perception of cues (e.g., egocentric distances) relevant task execution, known be distorted virtual environments due many factors, which can grouped into technical, human, methodological categories. This phenomenon becomes more pronounced a low-cost/encumbrance setup,...

The development of natural interfaces for human-robot interaction provides the user an intuitive way to control and guide robots. In this paper, we propose a novel ROS (Robot Operating System)-integrated interface remote that allows teleoperate robot using his hands motion. can adjust online autonomy between two levels: direct waypoint following. hand tracking gestures recognition capabilities Leap Motion device are exploited generate commands. receives real-time 3D augmented visual feedback...

Vitality form is a term, originally introduced by Stern (2010), to describe "how" an action performed. The capacity perceive the vitality of others' actions fundamental element social interactions and basic way relating understanding behaviors. Although forms characterize all human interactions, few studies have addressed their role in communicative disorders such as autism. aim present study evaluate ability recognize different during observation motor group children with autism spectrum...

Elite-standard rowers tend to use a fast-start strategy followed by an inverted parabolic-shaped speed profile in 2000-m races. This is probably the best manage energy resources during race and maximise performance. study investigated of virtual reality (VR) with novice as means learn about management. Participants from avatar group (n = 7) were instructed track boat on screen, whose was set individually follow appropriate to-be-learned profile. A control 8) indoor training programme. In...

Wearable motion tracking systems have gained large popularity in the last decades because of their effectiveness many fields, from performance assessment to human-robot interaction. Among all approaches, those based on inertial sensors been widely explored. Since are affected by measurements drift, they need be aided other sensors, thus requiring sensor fused. The most used fusion techniques Kalman filter. In particular, Extended Filter (EKF) and Unscented (UKF) non linearity characterizing...

This article focuses on the trends, opportunities, and challenges of novel arithmetic for deep neural network (DNN) signal processing, with particular reference to assisted- autonomous driving applications. Due strict constraints in terms latency, dependability, security driving, machine perception (i.e., detection decision tasks) based DNNs cannot be implemented by relying remote cloud access. These tasks must performed real time embedded systems board vehicle, particularly inference phase...

Nowadays, two groundbreaking factors are emerging in neural networks. First, there is the RISC-V open instruction set architecture (ISA) that allows a seamless implementation of custom sets. Second, several novel formats for real number arithmetic. In this work, we combined these key aspects using very promising posit format, developing light Posit Processing Unit (PPU-light). We present an extension base ISA conversion between 8 or 16-bit posits and 32-bit IEEE Floats fixed point order to...

This paper presents a vibrotactile methodology for rowing training system. Since hands' trajectories are fundamental in the gesture, it is completely necessary to search and develop new technologies techniques that can interact help user perform better movement. These methodologies must be as natural possible order guarantee transparency feedback of Therefore this an analysis visual, visual-tactile tactile strategies understand importance period time when each one applied. Data shows...

The use of virtual environments (VE) for training sports is quite natural when considering strategic or cognitive aspects. Using VE sensorimotor more challenging, in particular with the difficulty transferring task learned world to real. Of special concern successful transfer adequate combination experience protocols and delivery modes multimodal feedback. Analyzing feedback terms information exchange, this work discusses different combinations their application reality rowing skills.

Multimodal learning analytics provides researchers new tools and techniques to capture different types of data from complex activities in dynamic environments. This paper investigates high-fidelity synchronised multimodal recordings small groups learners interacting diverse sensors that include computer vision, user generated content, the objects (like physical computing components or laboratory equipment). We processed extracted aspects students' interactions answer following question:...

Observing how an action is done by others allows the observer to understand cognitive state of agent. This information, carried kinematics observed action, has been defined Stern "vitality forms". In present experiment we presented participants with videos showing hand actions performed different velocities and asked them judge their vitality form (gentle, neutral, rude) or velocity (slow, medium, fast). Previous studies showed that dorso-central insula selectively active both during...

This paper discusses the introduction of an integrated Posit Processing Unit (PPU) as alternative to Floating-point (FPU) for Deep Neural Networks (DNNs) in automotive applications. Autonomous Driving tasks are increasingly depending on DNNs. For example, detection obstacles by means object classification needs be performed real-time without involving remote computing. To speed up inference phase DNNs CPUs on-board vehicle should equipped with co-processors, such GPUs, which embed specific...

With increasing real-time constraints being put on the use of Deep Neural Networks (DNNs) by scenarios, there is need to review information representation. A very challenging path employ an encoding that allows a fast processing and hardware-friendly representation information. Among proposed alternatives IEEE 754 standard regarding floating point real numbers, recently introduced Posit format has been theoretically proven be really promising in satisfying mentioned requirements. However,...

Collaborative learning activities are a key part of education and many common teaching approaches including problem-based learning, inquiry-based and project-based learning. However, in open-ended collaborative small group work where learners make unique solutions to tasks that involve robotics, electronics, programming, and design artefacts evidence on the effectiveness using these hard to find. The paper argues multimodal analytics (MMLA) can offer novel methods that generate...

The development and evaluation of haptic rendering algorithms presents two unique challenges. Firstly, the information channel is fundamentally bidirectional, so output a environment dependent on user input, which difficult to reliably reproduce. Additionally, it compare results real-world, “gold standard” results, since such comparison requires applying identical inputs real virtual objects measuring resulting forces, hardware that not widely available. We have addressed these challenges by...

This paper presents a sensor fusion model for integrating wearable inertial measures with sensors in the environment. approach is designed and tested to support body motion tracking of rowing indoor outdoor environments. based on complex kinematic Unscented Kalman filtering. The validated an setup SPRINT system by comparison against results obtained from commercial capture system, thus providing future directions assessment rowers’ performance instrumented boat.

Abstract The present work deals with the design, implementation and assessment of a new haptic system specifically conceived for manipulative tasks in virtual environments. Such was designed by taking into account specific issues related to fine manipulation, such as multipoint haptics, coherence, transparency physical representation. described herein is integrated environment engine simulation multifinger manipulation. A preliminary evaluation conducted comparing human performance...