As artificial intelligence and industrial automation are developing, human–robot collaboration (HRC) with advanced interaction capabilities has become an increasingly significant area of research. In this paper, we design and develop a real-time, multi-model HRC system using speech and gestures. A set of 16 dynamic gestures is designed for communication from a human to an industrial robot. A data set of dynamic gestures is designed and constructed, and it will be shared with the community. A convolutional neural network is developed to recognize the dynamic gestures in real time using the motion history image and deep learning methods. An improved open-source speech recognizer is used for real-time speech recognition of the human worker. An integration strategy is proposed to integrate the gesture and speech recognition results, and a software interface is designed for system visualization. A multi-threading architecture is constructed for simultaneously operating multiple tasks, including gesture and speech data collection and recognition, data integration, robot control, and software interface operation. The various methods and algorithms are integrated to develop the HRC system, with a platform constructed to demonstrate the system performance. The experimental results validate the feasibility and effectiveness of the proposed algorithms and the HRC system.

Additive manufacturing is a group of fabrication techniques that is used to build components by depositing material in a layer-by-layer manner. Fused deposition modelling (FDM) is one of the additive manufacturing techniques which is widely used for prototyping and production applications of thermoplastic components. In load-bearing applications, flexural and compression forces often coexist. In order to avoid failure under these loads, it is essential to study the mechanical properties of FDM components. The main focus of this research is to study the flexural properties of FDM components and to comprehend their dependence on various build parameters. It has been observed from a series of flexural tests that FDM parts have anisotropic properties and this anisotropy was not due to the material in use, but due to the fabrication process itself. In this study Ultem 9085 is used as the material to fabricate coupons with variations in build parameters including build direction, raster angle and negative air gap. A full-factorial experimental design was used to study the individual and combined effects of these build parameters on the flexural properties of the coupons. Solid and sparse-build styles were used in the coupon fabrication. Flexural properties investigated include flexural yield strength, flexural modulus, flexural strength/mass ratio and flexural modulus/mass ratio. Qualitative observation and reasoning is used to comprehend how the flexural properties are affected by the build parameters.

This paper presents a study wherein the Laser Sintering (LS) process is used to perform additive manufacturing of zirconium diboride (ZrB₂) parts. Experiments were conducted to determine values of LS process parameters (laser power, scan speed, energy density, line spacing, and layer thickness) that can be used to improve building of ZrB₂ parts. A sacrificial plate with a proper number of layers was first constructed in order to reduce thermal gradients in building the main part. The sacrificial plate was found to eliminate cracks that would otherwise occur in the bottom of the main part. The fabricated green parts went through post-processing steps, including binder burnout and sintering at appropriate heat treatment schedules, to remove the binder and sinter the ZrB₂ particles. The test bars after sintering had an average relative density of 87% and an average flexural strength of 250 MPa.