Search

Getting dressed is a universally performed daily activity, and has a substantial impact on a person’s well-being. Choosing appropriate outfits to wear is important, as clothes protect a person from elements in the environment, and act as a barrier against harsh surfaces [1]. Studies have shown strong correlation between clothing choices and perceptions of sociability, emotional stability, and impression formation (e.g., [2]). This activity, however, can be difficult for some individuals, as they may lack the required reasoning and judgement required [3]. They include children with intellectual and learning disabilities [4] (e.g., Down syndrome [5], dyspraxia [6], autism spectrum disorder [7]), and older adults suffering from dementia including Alzheimer’s disease [8,9], or HIV-associated neurocognitive disorders [10]. In this paper, we present the development of a novel autonomous robotic clothing recommendation system to provide appropriate clothing options, which are personalized to a user’s wardrobe. This research expands on our previous work on socially assistive robots providing assistance with other daily activities, including meal eating [11] and playing Bingo games [12]. Currently, a few smartphone applications exist for providing outfit choices (e.g., [13,14]); however, unlike our proposed system, they are fashion-focused and not able to adapt online to a user’s preferences. Furthermore, by utilizing a socially assistive robot, we provide a more engaging interaction. We utilize the small Nao social robot, Leia, to guide and interact with a user in order to obtain information regarding his/her preferences, the activity for which the clothing will be worn, as well as the environment in which the activity will take place in order to make outfit recommendations, Fig. 1.

Socially assistive robots can provide cognitive assistance with activities of daily living, and promote social interactions to those suffering from cognitive impairments and/or social disorders. They can be used as aids for a number of different populations including those living with dementia or autism spectrum disorder, and for stroke patients during post-stroke rehabilitation [1]. Our research focuses on developing socially assistive intelligent robots capable of partaking in natural human-robot interactions (HRI). In particular, we have been working on the emotional aspects of the interactions to provide engaging settings, which in turn lead to better acceptance by the intended users. Herein, we present a novel multimodal affect recognition system for the robot Luke, Fig. 1(a), to engage in emotional assistive interactions. Current multimodal affect recognition systems mainly focus on inputs from facial expressions and vocal intonation [2], [3]. Body language has also been used to determine human affect during social interactions, but has yet to be explored in the development of multimodal recognition systems. Body language has been strongly correlated to vocal intonation [4]. The combined modalities provide emotional information due to the temporal development underlying the neural interaction in audiovisual perception [5]. In this paper, we present a novel multimodal recognition system that uniquely combines inputs from both body language and vocal intonation in order to autonomously determine user affect during assistive HRI.

This paper presents the workspace-based architecture selection process and singularity analysis of a high-speed, high-precision three degree-of-freedom (3-DOF) planar parallel manipulator for wire-bonding and electronic-component placement applications. A novel concept of manipulator “effective base area” is utilized for selecting the optimal architecture amongst the possible six well-known configurations. Dexterity regions, based on the manipulator requirements, within the reachable workspace have been identified for the selected architecture. Singular configurations of the optimal 3-PRR architecture have also been examined within the reachable workspace. Simulation results for both workspace and singularity analyses are also presented.

This paper presents a method of selecting and positioning groups of sensors in a coordinated manner for the surveillance of a maneuvering object The object trajectory is discretized into a number of demand instants (data acquisition times) to which groups of sensors are assigned, respectively. Heuristic rules are used to evaluate the suitability of each sensor for servicing (observing) a demand instant, determine the composition of the sensor group, and, in the case of dynamic sensors, specify the position of each sensor with respect to the object This approach aims to improve the quality of the surveillance data in three ways: (1) the assigned sensors are maneuvered into “optimal” sensing positions, (2) the uncertainty of the measured data is mitigated through sensor fusion, and (3) the poses of the unassigned sensors are adjusted to ensure that sensing-system can react to object maneuvers. Simulations with proximity sensors demonstrate the advantages of dispatching dynamic sensors over similar static-sensor systems.

This paper addresses the fluid mechanics of the slot-coating process within the context of the layered manufacturing system. The investigation was carried out to assist with the design of a novel slot-coating-based liquid-layer-formation subsystem. This subsystem, when used as a part of a lithography-based Rapid Layered Composite parts Manufacturing (RLCM) system, successfully solves some of the difficulties encountered in the formation of thin layers from a highly viscous fibre-photopolymer composite liquid. In addition to an analytical model, the paper presents a numerical model based on a volume of fluid (VOF) algorithm. The algorithm allows (1) solution of non-steady-state problems, (2) tracking of the free surface of the fluid undergoing large deformations, and (3) easy modification of model’s domain to facilitate experimentation with coater geometry. Results from a set of simulated experiments are reported which show the relationship between the liquid coat height and several design and process parameters. Examination of cross-sections of test parts built on an RLCM prototype system confirmed the ability of the new coater design to form solid layers of good quality.

This paper addresses a multi-robot optimal assembly planning problem which in essence is an augmented Travelling Salesperson Problem (TSP+). In our TSP+, both the “salesperson” (a robot with a tool) as well as the “cities” (another robot with a workpiece) move. Namely, in addition to the sequencing of tasks, further planning is required to choose where the “salesperson” should rendezvous with each “city”. The use of a genetic algorithm (GA) is chosen as the search engine for the solution of the multi-robot TSP+ optimization. As an example industrial application the optimization of the electronic-component placement process is addressed. In the most generalized component-placement system configuration, the placement robots meet the component delivery systems (CDSs) at optimal rendezvous locations for the pick-up of components and subsequently meet the printed circuit board (on the mobile XY-table) at optimal rendezvous locations for their placement. In addition to the solution of the component-placement sequencing problem and the rendezvous-point planning problem, the collision-avoidance issue is also addressed.

This paper approaches environmentally conscious design by further developing a reliability model that facilitates design for reuse. Many reliability models are not suitable for describing systems that undergo repairs performed during remanufacture and maintenance because the models do not allow the possibility of system reconfiguration. In this paper, expressions of reliability indices of a model that allows system reconfiguration are developed to enable life-cycle cost estimation for repairable systems. These reliability indices of a population of repairable systems are proven theoretically to reach steady state. The expressions of these indices at steady state are obtained to gain insight into the model behavior, and to facilitate life-cycle cost estimation.

Current commercial Rapid Prototyping (RP) systems can be used for fabricating layered models for subsequent creation of fully-dense metal parts using investment casting. Due to increased demand for shortened product development cycles, however, there exists a demand to rapidly create functional fully-dense metal parts without hard tooling. A possible solution to this problem is direct layered Rapid Manufacturing (RM) of such parts, for example, via laser-beam fusion of the metal powder. The RM process proposed herein is based on this approach. It involves selective laser-beam scanning of a predeposited metal-powder layer, forming fully-dense claddings, as the basic building block of individual layers. This paper specifically addresses only one of the fundamental issues of the proposed RM process, namely the fabrication of single claddings. Our theoretical investigation of the influence of the process parameters on cladding’s geometrical properties employed thermal modeling and computer process simulation. Numerous experiments, involving fabrication of single claddings, were also carried out with varying process parameters. Comparisons of the process simulations and experimental results showed good agreement in terms of overall trends.

This paper introduces a unified approach to the singularity analysis of mechanisms with arbitrary kinematic chains and any number of inputs or outputs. The presented framework for the interpretation and classification of singularities is obtained by generalizing previous results (Zlatanov et al, 1995) valid only for non-redundant mechanisms. A velocity-space model is used to describe the instantaneous kinematics and interpret mechanism singularity. The definition of six singularity types and the study of their interdependence in the case of redundant mechanisms yield a comprehensive singularity classification.

Feature-extraction techniques address the primary limitation of feature-recognition approaches, namely their lack of generalization. This paper presents a boundary-based procedure for the classification and sequential extraction of form features from the CAD models of objects with planar surfaces. Form features are first classified based on their effect on the boundary elements of a basic shape. Geometric reasoning is then used to obtain generalized properties of the form-features’ classes. Finally, form-features’ classes are sequentially extracted based on the recognized properties. At the onset of each extraction stage, the object is viewed as an initial basic shape that has been iteratively altered through the introduction of form features.

For the efficient manipulation of information in support of design and manufacturing one would need to access large active databases. In this context, it is envisioned that 3-D object models must be easily retrieved for modification, or for simply reviewing related information. This paper addresses the development of a classification system for the efficient retrieval of 3-D object CAD models. For the design of a new object the user would access the database to locate the most similar object model and, if worthwhile, modify it to attain a model for the new object under consideration. The proposed classification procedure comprises three main stages: First, 3-D geometrical data, sufficient for classification, is determined and extracted from a selected model of the object, and a primary representation domain is determined. Contours, were selected as the basic descriptive units. Based on this selection, relationships defined by descriptor elements were established between (a) two solid contours; (b) a solid and a hollow contour; and, (c) two hollow contours. In order to facilitate the use of the descriptor elements, a simple alpha-numeric coding system was developed. In the second stage, the description of the object is mapped from the geometrical domain into a numerical-factor domain, where each contour is represented by a numerical value. In the final stage, a code is generated based on the factor-domain representation in the form of a Fourier signature. Classification is then carried out according to the similarity of the generated Fourier signatures.

In this paper a three-legged 6-dof platform-type parallel manipulator is described. Each of the legs is a serial subchain with three revolute joints connected to the output platform via a spherical joint. Due to the proposed asymmetrical 3-2-1 distribution of the controlled joints, a closed-form solution exists to the forward kinematics problem. The mechanical design of the manipulator has been developed. The forward and inverse kinematics as well as the instantaneous kinematics of the mechanism have been solved analytically.

A new method is presented for the optimal coordination of a two-robot system performing contact operations. One of the robots carries a tool and performs the specific contact operation on a workpiece which is grasped and maneuvered by the second robot. The two robots move simultaneously relative to each other so that the tool maintains contact with the workpiece while moving along its prescribed trajectory at a constant speed. This prescribed trajectory, which is specified with respect to the workpiece frame, is thus resolved into a pair of conjugate trajectories, one for each robot, and specified in the world coordinate frame. This resolution process does not yield a unique solution, i.e. there exist an infinity of conjugate-trajectory pairs corresponding to a given tool trajectory. This paper presents a technique for resolving the original tool trajectory, where the robots’ conjugate trajectories are parameterized using polynomial functions. A method is then developed for selecting the optimal pair of conjugate trajectories on the basis of minimizing a given choice of cost function. This optimization is further enhanced by coupling it to a procedure for selecting the optimal layout of the robots within the workcell, resulting in the best possible solutions. Numerical simulation results support the validity of the proposed technique.