As artificial intelligence shifts from pure tool for delegation toward agentic collaboration, its use in the arts can shift beyond the exploration of machine autonomy toward synergistic co-creation. While our earlier robotic works utilized automation to distance the artist's intent from the final mark, we present Companion: an artistic apparatus that integrates a drawing robot with Large Language Models (LLMs) to re-center human-machine presence. By leveraging in-context learning and real-time tool use, the system engages in bidirectional interaction via speech and sketching. This approach transforms the robot from a passive executor into a playful co-creative partner capable of driving shared visual storytelling into unexpected aesthetic territories. To validate this collaborative shift, we employed the Consensual Assessment Technique (CAT) with a panel of seven art-world experts. Results confirm that the system produces works with a distinct aesthetic identity and professional exhibition merit, demonstrating the potential of AI as a highly capable artistic collaborator.

Earlier works with drawing robots were motivated by ideas of delegation and autonomy to create a distance between the artist’s intentions and the final mark. In contrast, we present Companion, an artistic apparatus integrating a drawing robot with multimodal large language models (LLMs) to reintroduce the artist’s presence through collaboration. Using in-context learning (ICL) and tool use for robot control, the system engages in bidirectional interaction via drawing and speech. Our goal is to develop an agent capable of pushing shared visual storytelling into unexpected aesthetic and narrative territories. Experiments demonstrate the system’s potential as a playful cocreative partner. To validate the artistic contribution, we employed the consensual assessment technique (CAT) with a panel of seven art world experts (curators, a collector, and an artist) familiar with the authors’ prior robotic works. The results confirm that the system produces artworks with a distinct aesthetic identity and professional exhibition merit.

We describe the implementation and evaluation of a public interactive robotic art installation in a rehabilitation hospital. The project had two goals; to provide an enjoyable and novel artistic experience for the hospital community, and to better understand how human-centred robotics, particularly a receptive-focused intervention, might promote wellbeing and quality of life for members of hospital communities. By evaluating the experiences of the participants and stakeholders, the value of the installation for participants was assessed. This work contributes relevant insight towards the development of future art installations within the health jurisdiction and more broadly. The data also informs the ongoing discussion concerning the potential role of social and therapeutic robots in health care settings.

As part of EVA London 2017, Lumen Prize for Digital Art and V&A Digital Futures are coming together with a special event presenting a series of installations, networking and the announcement of the 2017 Lumen Prize Longlist.

In this paper we report on our research into the develop- ment of computational embodied systems dedicated to the produc- tion of artworks. We present a conceptual framework that introduces the notion of style-space in relation to the visual arts. This frame- work underpins and guides our general approach to the development of autonomous agents capable of producing objects that have artistic value. In addition we introduce the importance of intentionality and embodiment, two interrelated elements that are fundamental in the appreciation of visual artworks such as paintings and drawings. Our practical research has at this stage only touched upon the develop- ment of agents that are adapted and sufficiently skilled to display the lowest level of artistic autonomy. Having such agents is essential to conduct further research into the autonomous invention of artistically valuable styles. Two of these skilled agents and their production are presented in this document.

We describe Paul, a robotic installation that produces observational face drawings of people. Paul is a naive drawer: it does not have highlevel knowledge of the structures constitutive of the human face (such as the mouth, nose, eyes) nor the capability of learning expertise based on experience as a human would. However, Paul is able to draw using the equivalent of an artist's stylistic signature based on a number of processes mimicking drawing skills and technique, which together form a drawing cycle. Furthermore, we present here our first efforts in implementing two different versions of visual feedback to permit the robot to iteratively augment and improve a drawing which initially is built from a process of salient lines recovery. The first form of visual feedback we study we refer to as computational as it involves a purely internal (memory-based) representation of regions to render via shading by the robot. The second version we call physical as it involves the use of a camera as an ‘eye’ taking new snapshots of the artefact in progress. This is then analysed to take decisions on where and how to render shading next. A main point we emphasise in this work is the issue of embodiment of graphical systems, in our case in a robotic platform. We present our arguments in favour of such a position for the graphics community to reflect upon. Finally, we emphasise that the drawings produced by Paul have been considered of interest by fine art professionals in recent international art fairs and exhibitions, as well as by the public at large. One drawing is now in the Victoria and Albert museum collection. We identify a number of factors that may account for such perceived qualities of the produced drawings.

In this paper we describe Paul, a robotic installation that produces observational sketches of people. The sketches produced have been considered of interest by fine art professionals in recent art fairs and exhibitions, as well as by the public at large. We identify factors that may account for the perceived qualities of the produced sketches. A technical overview of the system is also presented.

1 Concept We consider the problem of generating face sketches with a computer system, based on the understanding of a drawing style. Our research goal is for the system to mimic the interplay between the ensemble of processes — perceptual, cognitive, motor — active when a draughtsman is sketching. One hypothesis we are exploring is that the aesthetics of a sketch is dependent on each individual step involved in the collection of processes leading to the creation of a stylised portrait, as well as in the interactions between such processes. A second hypothesis we formulate is that during a sketch session each limitation, approximation, shortcut performed by the draughtsman due to his/her physical, perceptual, or cognitive impairments or qualities are what constitute the final mood, style, aesthetic of the sketch. Interestingly, the simulation of a stylised portrait sketching session via a computational model remains approximate, and as such the computerised system might be thought to draw in its own limited style. The modelled drawing process is the most spontaneous technique Tresset uses, not the most precise, which gives the most dramatic effects. The aesthetic effect of the drawing, its mood, is due in large part to its apparent imprecision.

We consider the problem of generating art with a computer system, as it relates to the understanding of a drawing style. Our system in its present development is able to sketch faces automatically, starting from a picture, typically a photographic snapshot of a scene with humans. Once a digital image is considered, the system automatically finds where some of the faces (or face-like patterns) are and isolate these. Each face image pattern is then used to produce a stylised portrait. The style which the system aims at using is derived from the one the first author has developed over the years in his artistic practice. The goal is for the final system to mimic the process developed by the artist, rather than aiming at results exactly reproducing his way of drawing a portrait. Nevertheless, the produced sketches are in the style of the artist. Various steps in the process of producing a sketch by the artist were isolated, including: image segmentation, filtering, shape selection and depiction, filling and shading. The implementation of these steps relies on an understanding of human visual perception, of the artist’s work process, and of advances made in computer vision.