AI-based creativity-support systems are gaining attention from designers and researchers. However, a research gap exists on how to tailor those systems by maximizing flexibility based on human needs and preferences. This study proposes a schematic human-AI co-creation framework to maximize system flexibility and enhance creative outcome generation. The framework proposes the involvement of AI in three levels of creation and allows humans to adjust between the levels anytime during the creative process based on their preferences. We tentatively define how AI should collaborate at the three levels. To implement the framework, a co-creation system (GSM) was built to support humans in creating sculpture maquettes with AI. It includes three key components: a prompt-based generated model (DALL·E), advanced computer vision, and robotic arms. A user interface is provided to ensure transparency. Preliminary user studies have demonstrated that the system enhances flexibility and allows users to generate more creative maquettes.
23 July 2023 in International Journal of Human–Computer Interaction
Fully Automated Vehicles (FAVs) have the potential to provide blind and visually impaired (BVI) individuals with mobility independence. However, understanding their user experience in this new form of transportation presents challenges. Researchers in human-computer interaction and accessibility lack comprehensive guidance on conducting safe and ecologically valid studies with BVI participants. This poster reviews the literature and proposes a methodology for conducting field research with BVI users in automated vehicles, particularly in designing the human-machine interface (HMI) for FAVs. We present the participatory and in-the-field method with example study designs: a focus group for field study and an on-road driving study with a Wizard of Oz FAV. This method will assist researchers in gaining deeper insights into the interaction between BVI users and automated vehicles in the real world.
The heritage restoration of paintings and calligraphy is a labour-intensive process, characterised by repetitive, low-intensity, and high-precision. Two core steps, “lift up the previous” and “fix and maintain”, can lead to muscle fatigue in the upper limbs. In this paper, we develop a human-in-the-loop based human-robot collaboration system that provides real-time force feedback to restorers based on their muscle load and motion intention, with the support strength changing to relieve fatigue. Different robot-aided positions on human arm are explored and a two-point elbow-supporting mechanism is evaluated as the optimal solution. Moreover, a novel muscle load calculation model is developed to integrate human factors into the HRC system with electromyography. The results of a usability experiment show the effectiveness of the proposed method in addressing the current anti-fatigue challenge in heritage paintings and calligraphy restoration.