With generative AI acquiring the right training data is a critical part of designing the user experience. Training large language models to talk like humans requires exposing them to the interaction patterns distinctive of natural conversation. Although models are typically fine-tuned on question-answer or instruction pairs, they are less often trained on real-time human conversations. Natural conversation data are hard to find and "conversation" is used to mean very different kinds of interaction or content. We demonstrate a method for scoring language content using \textit{generic conversational phrase detection}. We generate three scores: 1) range of unique features, 2) density of features within sections of the content, and 3) overall score combining these. Using our method, we score over 27,000 documents from 6 datasets, which vary widely in terms of whether or not they contain conversation content. Our results show this approach is effective in distinguishing conversation content from non-conversation and from conversation-like content.
Intermittent Interaction is a turn-taking approach used to interact with fabrication devices to do something that otherwise would be impractical or impossible for the machine. We investigate how people perceive intermittent interactions in a controlled study.
A LEGO assembly task with timed lock boxes simulates human involvement with a semi-automated machine process, similar to a 3D printer. This is used in an in situ study with 12 participants over 4-hour sessions with experimental controls for number of interactions and step complexity.
Results suggest complex interactions during assembly can amplify the perceived value of the assembled object and increase enjoyment.
Participants used either a clustered or evenly distributed strategy to schedule interactions, which can be modelled with simple heuristics.
We contribute evidence that intermittent interaction is generally acceptable for creation tasks and practical guidelines for integrating intermittent interactions into semi-automated fabrication systems.
As tools for designing and manufacturing hardware become more accessible, smaller producers can develop and distribute novel hardware. However, processes for supporting end-user hardware troubleshooting or routine maintenance aren't well defined. As a result, providing technical support for hardware remains ad-hoc and challenging to scale. Inspired by patterns that helped scale software troubleshooting, we propose a workflow for asynchronous hardware troubleshooting: SplatOverflow.
SplatOverflow creates a novel boundary object, the SplatOverflow scene, that users reference to communicate about hardware. A scene comprises a 3D Gaussian Splat of the user's hardware registered onto the hardware’s CAD model. The splat captures the current state of the hardware, and the registered CAD model acts as a referential anchor for troubleshooting instructions. With SplatOverflow, remote maintainers can directly address issues and author instructions in the user’s workspace. Workflows containing multiple instructions can easily be shared between users and recontextualized in new environments.
In this paper, we describe the design of SplatOverflow, the workflows it enables, and its utility to different kinds of users. We also validate that non-experts can use SplatOverflow to troubleshoot common problems with a 3D printer in a usability study.
Project Page: https://amritkwatra.com/research/splatoverflow.
The material properties of 3D prints depend on their constituent materials, how they were printed, and local geometrical features. Motivated by challenges in sharing physical details of 3D printing workflows including machine state and print settings, we contribute tools to support the exploration of the vast design space these interdependent parameters make up. Inspired by live music performance and video captioning, we contribute an interactive controller for parameters not represented in geometry such as speed and extrusion rate, and a system for automatically syncing video documentation to machine settings, G-Code, and print commands. By synchronizing video with machine instructions and interactive adjustments, we archive the relationship between digital settings and physical output for revisiting and sharing. We demonstrate example workflows in multiple materials. Our approach suggests how maker tools that promote settings exploration and sharing can support the integration of fabrication technologies in new contexts, with new materials.
Hybrid paper interfaces leverage augmented reality to combine the desired tangibility of paper documents with the affordances of interactive digital media. Typically, virtual content can be embedded through direct links (e.g., QR codes); however, this impacts the aesthetics of the paper print and limits the available visual content space. To address this problem, we present Imprinto, an infrared inkjet watermarking technique that allows for invisible content embeddings only by using off-the-shelf IR inks and a camera. Imprinto was established through a psychophysical experiment, studying how much IR ink can be used while remaining invisible to users regardless of background color. We demonstrate that we can detect invisible IR content through our machine learning pipeline, and we developed an authoring tool that optimizes the amount of IR ink on the color regions of an input document for machine and human detectability. Finally, we demonstrate several applications, including augmenting paper documents and objects.
Papermaking is an ancient yet evolving craft, with changes in techniques and materials giving paper contemporary qualities that keep it relevant for everyday use. This adaptability makes papermaking an ideal process for crafting computational composites for tangible interactions. We began by studying ancient Chinese papermaking, replicating it by hand and simplifying the practice into five key steps and tools accessible to novices. We then adapted these steps to imbue the paper with interactive and computational properties, such as integrating conductive materials during pulp preparation, modifying fiber properties through soaking, and customizing sheet texture through watermarking, multi-layering, and coating. We detail our exploration in this paper, as well as demonstrate our findings through four interactive systems focusing on expressive applications made with the computational paper from our adapted process. We also document our exploration in a detailed workbook that captures recipes, failures, and key moments of discovery.
Mobility aids (e.g., canes, crutches, and wheelchairs) are crucial for people with mobility disabilities; however, pervasive dissatisfaction with these aids keeps usage rates low. Through semi-structured interviews with 17 mobility aid users, mostly under the age of 30, we identified specific sources of dissatisfaction among younger users of mobility aids, uncovered community-based solutions for these dissatisfactions, and explored ways these younger users wanted to improve mobility aids. We found that users sought customizable, reconfigurable, multifunctional, and more aesthetically pleasing mobility aids. Participants' feedback guided our prototyping of tools/accessories, such as laser cut decorative skins, hot-swappable physical interface modules, and modular canes with custom 3D-printed handles. These prototypes were then the focus of additional co-design sessions where six returning participants offered suggestions for improvements and provided feedback on their usefulness and usability. Our findings highlight that many mobility aid users have the desire, ability, and need to customize and improve their aids in different ways compared to older adults. We propose various solutions and design guidelines to facilitate the modifications of mobility aids.