Modern manufacturing systems require a transformation from mass production towards mass customization. This results in a trend towards more agile production lines. It also demands a reduction of configuration times when building the production line as well as faster reconfiguration when adding new hardware and product variants to the manufacturing line. This paper introduces the concept of a device adapter that allows the device to be seamlessly plugged into the agile production systems. The device adapter wraps the device functionality and offers it as a service, hiding away the low-level process capability (skill) implementation and allowing to formally represent the production steps. Preliminary tests have been performed on an industrial demonstrator that simulates a real manufacturing process.

This paper aims to support the creation of high performance `Plug-and-Produce' systems by proposing a new semantic model that targets the use of AutomationML (AML). In this direction, the focus is narrowed to the self-description of equipment modules that highlights the use of `Skill' concept. An insight description on how the concept of `Skill Recipe' can be used to execute the equipment `Skills' to fulfil the product's assembly requirements is also provided. This is viewed as a critical concept to achieve high performance in `Plug-and-Produce'. To translate the base semantic definitions, we have developed new libraries that are fully compliant with the AML standard. The main purpose of using AML in this context is to bridge production and other engineering domains. An overview of the literature that covers the past and current trends in data exchange and standards is presented, while pointing out the existing challenges and limitations. The vision of this paper is to support the standardization effort of integrating information for design, build, ramp-up and operation of production systems. Hence, this approach elucidates the use of existing AML concepts to model and instantiate Product, Process and Resource (PPR), and the underlying definitions such as: `Skills', `Skill Recipes' and `Skill Requirements'. Finally, this paper illustrates the implementation of this approach in AML with a help of an industrial case study demonstrated within the openMOS project.

Stereo-based off-road obstacle detection is a complex and still open problem. The challenges are in great extent related to computational cost and noise level. Previous work has shown that visual saliency and voting mechanisms are extremely effective in tackling these issues. This paper proposes a set of extensions to these mechanisms, to further improve the detector's speed-accuracy trade-off as well as its robustness. The observed enhancements are due in part to the adaptive way saliency is accounted for by the detector during the image scanning procedure. Additionally, detector's positive results are in turn used to boost the saliency map itself, thus reinforcing the analysis of relevant regions of the image. To enable detection in highly roughed terrain, the detector's invariance to the robot's posture is also enhanced. Experimental results show that, with the extended detector, denominated of ESalOD, higher levels of robustness, accuracy and computational efficiency are attained.