Search results

The purpose of this paper is to propose a new velocity prediction navigation algorithm to develop a conflict-free path for robots in dynamic crowded environments. The algorithm BP-prediction and reciprocal velocity obstacle (PRVO) combines the BP neural network for velocity PRVO to accomplish dynamic collision avoidance.

This presented method exhibits innovation by anticipating ahead velocities using BP neural networks to reconstruct the velocity obstacle region; determining the optimized velocity corresponding to the robot’s scalable radius range from the error generated by the non-holonomic robot tracking the desired trajectory; and considering acceleration constraints, determining the set of multi-step reachable velocities of non-holonomic robot in the space of velocity variations.

The method is validated using three commonly used metrics of collision rate, travel time and average distance in a comparison between simulation experiments including multiple differential drive robots and physical experiments using the Turtkebot3 robot. The experimental results show that our method outperforms other RVO extension methods on the three metrics.

In this paper, the authors propose navigation algorithms capable of adaptively selecting the optimal speed for a multi-robot system to avoid robot collisions during dynamic crowded interactions.

This paper presents a novel hands‐free control system for intelligent wheelchairs (IWs) based on visual recognition of head gestures.

A robust head gesture‐based interface (HGI), is designed for head gesture recognition of the RoboChair user. The recognised gestures are used to generate motion control commands to the low‐level DSP motion controller so that it can control the motion of the RoboChair according to the user's intention. Adaboost face detection algorithm and Camshift object tracking algorithm are combined in our system to achieve accurate face detection, tracking and gesture recognition in real time. It is intended to be used as a human‐friendly interface for elderly and disabled people to operate our intelligent wheelchair using their head gestures rather than their hands.

This is an extremely useful system for the users who have restricted limb movements caused by some diseases such as Parkinson's disease and quadriplegics.

In this paper, a novel integrated approach to real‐time face detection, tracking and gesture recognition is proposed, namely HGI.

It is an useful human‐robot interface for IWs.

The spatial representation technique is an efficient method for packing boxes into a container; however, it has a limitation in dealing with constraints. For practical applications, there are however limitations when dealing with constraints. These constraints provide flexibility for the user to decide which boxes should be placed first. After imposing the initial conditions, the optimisation packing algorithm based on the spatial representation technique ensures that the boxes remaining in the item list are packed as efficiently as possible into the container. The packing plan is then generated during the run time to provide visualisation of the result of actual packing sequences. It also simultaneously outputs a graphical file to the Autocad software for printing and detailed study. The program can be implemented under either the DOS platform or the Windows platform on an IBM PC. The performance is evaluated using data from another algorithm. The results confirm that the enhanced algorithm can manage the user‐specified constraints with good volume utilisation.

The aim of the research is the development of a small-scale ground mobile robot for surveillance and inspection; the main design goals are mobility in indoor environments with step climbing ability, pivoting around a vertical axis and without oscillations for stable vision, mobility in unstructured environments, low mechanical and control complexity.

The proposed hybrid leg-wheel robot is characterized by a main body equipped with two actuated wheels and two praying Mantis rotating legs; a rear frame with two idle wheels is connected to the main body by a vertical revolute joint for steering; a second revolute joint allows the rear axle to roll. The geometrical synthesis of the robot has been performed using a nondimensional approach for generality's sake.

The experimental campaign on the first prototype confirms the fulfilment of the design objectives; the robot can efficiently walk in unstructured environments realizing a mixed wheeled-legged locomotion.

Thanks to the operative flexibility of Mantis in indoor and outdoor environments, the range of potential applications is wide: surveillance, inspection, monitoring of dangerous locations, intervention in case of terroristic attacks, military tasks.

Different from other robots of similar size, Mantis combines high speed and energetic efficiency, stable vision, capability of climbing over high steps, obstacles and unevenness.

The purpose of this paper is to present an omni‐directional floor‐cleaning robot equipped with four omni‐directional wheels. The research purposes are to design a robot for cleaning jobs in domestic, narrow and crowded places and to provide a robotics‐study platform in a laboratory.

The robot system using Swedish wheels, one dust collector (brush) switching device and a sort of air‐bag sensing device is designed. The kinematics and the motion control conditions of the robot are analyzed. Specifically, a design method of wheels is described.

The configuration of the robot, parameters of the wheel and controlling methods are studied and demonstrated. The smooth locomotion capability and high‐working efficiency are verified by experiments.

The robot can perform its work in semi‐autonomous and tele‐operated mode. Moreover, the robot can pivot around, avoid obstacles and is provided with automatic power management system.

The research target is to provide a kind of robotic cleaner especially for crowded public or narrow places and educational robotics‐study platform in a laboratory.

Robots come in a variety of shapes and sizes, from manipulators in the industrial assembly line, to house cleaners, and to carebots of the elderly and sick. In recent years entertaining robots have been developed to engage adults and children into playing and learning. There are however no robots that have been specifically designed to entertain pets. The purpose of this paper is to present a prototype developed to engage pets into outdoor playing.

A prototype that can engage a dog or a cat into playing was designed, built, and tested by a group of senior students. The enclosure of the prototype has the shape of a round shell. Within this shell there is a sensor interfacing unit, which can interpret sounds generated by the animals, and a light and sound system designed to interact with the animals.

The testing results showed that the prototype was able to fulfill requirements for outdoor playing, such as being waterproof and able to travel through grass. Testing of the individual sensor interfacing circuits demonstrated the interactive capability. Dogs were chosen to be the subjects to be entertained. However, it is envisioned that a smaller version of this prototype can be suitable for cats.

This is the first prototype that explores ways to entertain pets when their human owners are absent or busy. The prototype developed is a good start for any intelligent robotic systems specifically designed to entertain pets.

Researchers began investigating the diffusion of renewable energy technologies (RETs) in the late 1990s, and, up to today, a variety of authors have presented different approaches to understand the special characteristics of RET diffusion. However, one factor has been thus far disregarded in the research: the influence of raw material prices on RET diffusion. The dependence of a multitude of technologies on raw material prices became especially apparent in recent years due to rather sudden and volatile price movements in raw material markets. Thus, the aim of this work is to contribute to the research by providing evidence for a direct linkage between raw material price developments and RET diffusion.

A theoretical framework used in this article derives from the concept of induced diffusion. This empirical study is based on publicly available data of 18 Organisation for Economic Co-operation and Development (OECD) countries over 20 years and uses multivariate regression analysis to identify the corresponding diffusion models for selected established and emerging RETs.

Results reveal that crude oil prices play a crucial role in the diffusion of emerging RETs. In addition, a joint reflection of induced diffusion and path dependencies as the theoretical foundation of RET diffusion models might be reasonable.

This paper makes a significant contribution to the literature on induced diffusion in the field of renewable energies by providing insights from publicly available data from 18 OECD-countries. The findings are highly relevant for managers of the energy industry and policymakers in this field.

The purpose of this paper is to understand users' acceptance of service robots by integrating perceived enjoyment of service robots and users' need to belong in a technology acceptance model (TAM) framework. Service robots are currently being used in homes and firms to provide various services.

The authors conducted a web‐based survey from 904 users in South Korea to test a research model and employed structural equation modelling as the analysis method.

This study found that perceived enjoyment and the need to belong played an important role in the perceived ease of use and usefulness of service robots. Furthermore, it was discovered that the research supported relationships proposed by the original TAM with regard to users' attitudes and intentions to use service robots. Therefore, this study provides a framework to understand users' acceptance of service robots.

This paper is of value to researchers designing and improving service robots for use in our society.