People living with Motor Neuron Disease (plwMND) frequently encounter speech and motor impairments that necessitate a reliance on augmentative and alternative communication (AAC) systems. This paper tackles the main challenge that traditional symbol-based AAC systems offer a limited vocabulary, while text entry solutions tend to exhibit low communication rates. To help plwMND articulate their needs about the system efficiently and effectively, we iteratively design and develop a novel multimodal text generation system called ImageTalk through a tailored proxy-user-based and an end-user-based design phase. The system demonstrates pronounced keystroke savings of 95.6%, coupled with consistent performance and high user satisfaction. We distill three design guidelines for AI-assisted text generation systems design and outline four user requirement levels tailored for AAC purposes, guiding future research in this field.

The conceptual design phase represents a critical early stage in the product development process, where designers generate potential solutions that meet predefined design specifications based on functional requirements. Functional modeling, a foundational aspect of this phase, enables designers to reason about product functions before specific structural details are determined. A widely adopted approach to functional modeling is the Function-Behavior-Structure (FBS) framework, which supports the transformation of functional intent into behavioral and structural descriptions. However, the effectiveness of function-based design is often hindered by the lack of well-structured and comprehensive functional data. This scarcity can negatively impact early design decision-making and hinder the development of accurate behavioral models. Recent advances in Large Language Models (LLMs), such as those based on GPT architectures, offer a promising avenue to address this gap. LLMs have demonstrated significant capabilities in language understanding and natural language processing (NLP), making them suitable for automated classification tasks. This study proposes a novel LLM-based domain adaptation (DA) framework using fine-tuning for the automated classification of mechanical assembly parts' functions. By fine-tuning LLMs on domain-specific datasets, the traditionally manual and subjective process of function annotation can be improved in both accuracy and consistency. A case study demonstrates fine-tuning GPT-3.5 Turbo on data from the Oregon State Design Repository (OSDR), and evaluation on the A Big CAD (ABC) dataset shows that the domain-adapted LLM can generate high-quality functional data, enhancing the semantic representation of mechanical parts and supporting more effective design exploration in early-phase engineering.

The development and deployment of safe and dependable AI models is crucial in applications where functional safety is a key concern. Given the rapid advancement in AI research and the relative novelty of the safe-AI domain, there is an increasing need for a workflow that balances stability with adaptability. This work proposes a transparent, complete, yet flexible and lightweight workflow that highlights both reliability and qualifiability. The core idea is that the workflow must be qualifiable, which demands the use of qualified tools. Tool qualification is a resource-intensive process, both in terms of time and cost. We therefore place value on a lightweight workflow featuring a minimal number of tools with limited features. The workflow is built upon an extended ONNX model description allowing for validation of AI algorithms from their generation to runtime deployment. This validation is essential to ensure that models are validated before being reliably deployed across different runtimes, particularly in mixed-criticality systems. Keywords-AI workflows, safe-AI, dependable-AI, functional safety, v-model development

The sustainability of AI systems depends on the capacity of project teams to proceed with a continuous sensitivity to their potential real-world impacts and transformative effects. Stakeholder Impact Assessments (SIAs) are governance mechanisms that enable this kind of responsiveness. They are tools that create a procedure for, and a means of documenting, the collaborative evaluation and reflective anticipation of the possible harms and benefits of AI innovation projects. SIAs are not one-off governance actions. They require project teams to pay continuous attention to the dynamic and changing character of AI production and use and to the shifting conditions of the real-world environments in which AI technologies are embedded. This workbook is part two of two workbooks on AI Sustainability. It provides a template of the SIA and activities that allow a deeper dive into crucial parts of it. It discusses methods for weighing values and considering trade-offs during the SIA. And, it highlights the need to treat the SIA as an end-to-end process of responsive evaluation and re-assessment.

As collaborative robot (Cobot) adoption in many sectors grows, so does the interest in integrating digital twins in human-robot collaboration (HRC). Virtual representations of physical systems (PT) and assets, known as digital twins, can revolutionize human-robot collaboration by enabling real-time simulation, monitoring, and control. In this article, we present a review of the state-of-the-art and our perspective on the future of digital twins (DT) in human-robot collaboration. We argue that DT will be crucial in increasing the efficiency and effectiveness of these systems by presenting compelling evidence and a concise vision of the future of DT in human-robot collaboration, as well as insights into the possible advantages and challenges associated with their integration.

A wide range of nanomedicines exist, many of which revolve around being the'carrier'. This means that they act as a vessel that can carry therapeutic payloads (a drug of interest) and deliver them to a specific location. This has become particularly useful for delivering drugs that would otherwise be too toxic to administer on their own. There are other nanomedicines as well, such as nanoparticles that can kill cancer cells and nanoforms of drugs that are in solid nanoparticle suspensions. These are but a few examples, and because nanomedicines span many areas from the'drug' itself to being a carrier, to being either inorganic or organic in nature, there are many things to think about when it comes to designing new nanomedicines.

This paper presents the first results of the research into AI-based support of the room configuration process during the early design phases in architecture. Room configuration (also: room layout or space layout) is an essential stage of the initial design phase: its results are crucial for user-friendliness and success of the planned utilization of the architectural object. Our approach takes into account different possible actions of the configuration process, such as adding, removing, or (re)assigning of the room type. Its mode of operation is based on specific process chain clusters, where each cluster represents a contextual subset of previous configuration steps and provides a recurrent neural network trained on this cluster data only to suggest the next step, and a case base that is used to determine if the current process chain belongs to this cluster. The most similar cluster then tries to suggest the next step of the process. The approach is implemented in a distributed CBR framework for support of early conceptual design in architecture and was evaluated with a high number of process chain queries to prove its general suitability.

Facial recognition tools have significant error rates that differ by race. An AI hiring tool from Amazon "learned" gender bias against women and favored male candidates. We know diversity bias is rampant in artificial intelligence. But decisions made based on prejudiced AI systems aren't just an ethical dilemma; they're a financial one. The more unbiased a system, the more likely it is to maximize profits, make better hiring or selling recommendations and provide accurate risk predictions.

Today's automobile development process is highly complicated. In the past, vehicles were just a combination of mechanical pieces. Now, automobiles are a multi-faceted combination of mechanical parts, electronics and in-vehicle software. As automotive designers, Honda R&D must continuously adapt our development processes to handle these complexities. Many design problems actually occur early in the development process, but don't become apparent until the latter stages.

What is interesting about this, and what makes it a great example for what is happening in many industries, is that baseball games will still require an umpire. They will remain a critical part of the game, and there is no suggestion that their job will disappear. In this case, AI is therefore helping umpires become better at their jobs, serving as a second set of eyes so they can be more accurate in a particular part of their role. In this article, I want to discuss the role of design thinking in creating these systems where AI works side by side with people, helping them to become better at their jobs. Another great example is with customer service agents, where a company can use bots to answer certain customer queries, but humans are responsible for other situations, such as when more empathy or understanding is required.