Bruno De Araujo

Since the advent of computing, humans have sought computer input technologies that are expressive, intuitive and universal. While diverse modalities have been developed, including keyboards, mice and touchscreens, they require interaction with a device that can be limiting, especially in on-the-go scenarios. Gesture-based systems use cameras or inertial sensors to avoid an intermediary device, but tend to perform well only for unobscured movements. By contrast, brain–computer or neuromotor interfaces that directly interface with the body’s electrical signalling have been imagined to solve the interface problem1, but high-bandwidth communication has been demonstrated only using invasive interfaces with bespoke decoders designed for single individuals2,3,4. Here, we describe the development of a generic non-invasive neuromotor interface that enables computer input decoded from surface electromyography (sEMG). We developed a highly sensitive, easily donned sEMG wristband and a scalable infrastructure for collecting training data from thousands of consenting participants. Together, these data enabled us to develop generic sEMG decoding models that generalize across people. Test users demonstrate a closed-loop median performance of gesture decoding of 0.66 target acquisitions per second in a continuous navigation task, 0.88 gesture detections per second in a discrete-gesture task and handwriting at 20.9 words per minute. We demonstrate that the decoding performance of handwriting models can be further improved by 16% by personalizing sEMG decoding models. To our knowledge, this is the first high-bandwidth neuromotor interface with performant out-of-the-box generalization across people.

We demonstrate rich inferences about unaugmented everyday objects and hand object interactions by measuring minute skin surface deformations at the wrist using a sensing technique based on capacitance. The wristband prototype infers muscle and tendon tension, pose, and motion, which we then map to force (9 users, 13.66 +/- 9.84 N regression error on classes 0–49.1 N), grasp (9 users, 81 +/- 7 % classification accuracy on 6 grasps), and continuous interaction (10 users, 99 +/- 1 % discrimination accuracy between 6 interactions, 89–97 % accuracy on 3 states within each interaction) using basic machine learning models. We wrapped these sensing capabilities into a proof-of-concept end-to-end system, Ubiquitous Controls, that enables virtual range inputs by sensing continuous interactions with unaugmented objects. Eight users leveraged our system to control UI widgets (like sliders and dials) with object interactions (like “cutting with scissors’’ and “squeezing a ball”). Finally, we discuss the implications and opportunities of using hands as a ubiquitous sensor of our surroundings.

Creating whimsical, personal data visualizations remains a challenge due to a lack of tools that enable for creative visual expression while providing support to bind graphical content to data. Many data analysis and visualization creation tools target the quick generation of visual representations, but lack the functionality necessary for graphics design. Toolkits and charting libraries offer more expressive power, but require expert programming skills to achieve custom designs. In contrast, sketching affords fluid experimentation with visual shapes and layouts in a free-form manner, but requires one to manually draw every single data point. We aim to bridge the gap between these extremes. We propose DataInk, a system supports the creation of expressive data visualizations with rigorous direct manipulation via direct pen and touch input. Leveraging our commonly held skills, coupled with a novel graphical user interface, DataInk enables direct, fluid, and flexible authoring of creative data visualizations.

We present Storeoboard, a system for stereo-cinematic conceptualization, via storyboard sketching directly in stereo. The resurgence of stereoscopic media has motivated filmmakers to evolve a new stereo-cinematic vocabulary, as many principles for stereo 3D film are unique. Concepts like plane separation, parallax position, and depth budgets are missing from early planning due to the 2D nature of existing storyboards. Storeoboard is the first of its kind, allowing filmmakers to explore, experiment and conceptualize ideas in stereo early in the film pipeline, develop new stereo-cinematic constructs and foresee potential difficulties. Storeoboard is the design outcome of interviews and field work with directors, stereographers, and storyboard artists. We present our design guidelines and implementation of a tool combining stereo-sketching, depth manipulations and storyboard features into a coherent and novel workflow. We report on feedback from storyboard artists, industry professionals and the director of a live action, feature film on which Storeoboard was deployed.

We present Object-Oriented Drawing, which replaces most WIMP UI with Attribute Objects. Attribute Objects embody the attributes of digital content as UI objects that can be manipulated through direct touch gestures. In the paper, the fundamental UI concepts are presented, including Attribute Objects, which may be moved, cloned, linked, and freely associated with drawing objects. Other functionalities, such as attribute-level blending and undo, are also demonstrated. We developed a drawing application based on the presented concepts with simultaneous touch and pen input. An expert assessment of our application shows that direct physical manipulation of Attribute Objects enables a user to quickly perform interactions which were previously tedious, or even impossible, with a coherent and consistent interaction experience throughout the entire interface.

Augmented and virtual reality have the potential of being indistinguishable from the real world. Holographic displays, including head mounted units, support this vision by creating rich stereoscopic scenes, with objects that appear to float in thin air - often within arm’s reach. However, one has but to reach out and grasp nothing but air to destroy the suspension of disbelief. Snake-charmer is an attempt to provide physical form to virtual objects by revisiting the concept of Robotic Graphics or Encountered-type Haptic interfaces with current commodity hardware. By means of a robotic arm, Snake-charmer brings physicality to a virtual scene and explores what it means to truly interact with an object. We go beyond texture and position simulation and explore what it means to have a physical presence inside a virtual scene. We demonstrate how to render surface characteristics beyond texture and position, including temperature; how to physically move objects; and how objects can physically interact with the user’s hand. We analyze our implementation, present the performance characteristics, and provide guidance for the construction of future physical renderers.

Our work introduces a semi-immersive environment for conceptual design where virtual mockups are obtained from gestures we aim to get closer to the way people conceive, create and manipulate three-dimensional shapes. We present on-and-above-the-surface interaction techniques following Guiard’s asymmetric bimanual model to take advantage of the continuous interaction space for creating and editing 3D models in a stereoscopic environment. To allow for more expressive interactions, our approach continuously combines hand and finger tracking in the space above the table with multi-touch on its surface. This combination brings forth an alternative design environment where users can seamlessly switch between interacting on the surface or in the space above it depending on the task. Our approach integrates continuous space usage with bimanual interaction to provide an expressive set of 3D modeling operations. Preliminary trials with our experimental setup show this as a very promising avenue for further work.