論文名稱：Wander: An AI-driven Chatbot to Visit the Future Earth

論文作者：Yuqian Sun, Chenhang Cheng, Ying Xu, Yihua Li, Chang Hee Lee, Ali Asadipour

論文來源：ACM MM’22 https://dl.acm.org/doi/10.1145/3503161.3549971

報告PPT：[PPT] [PDF]

Abstract

This artwork presents an intelligent chatbot called Wander. This work used knowledge based story generation to facilitate a narrative AI chatbot on daily communication  platforms, producing interactive fiction with the most accessible natural language input: text messages. On social media platforms such as Discord and WeChat, Wander can generate a science-fiction style travelogue about the future earth, including text, images  and global coordinates (GPS) based on real-world locations (e.g. Paris). The journeys are visualised in real-time on an interactive map that can be updated with participants’ data. Based on Viktor Shklovsky’s defamiliarization technique, we present how an AI agent can become a storyteller through common messages in daily life and lead participants to
see the world from new perspectives. The website of this work is:
https://wander001.com/

keywords : Intelligent Interactive System, Co-creative AI, Chatbot, Metaverse, Gaming

Designing and Deploying Robotic Companions to Improve Human Psychological Wellbeing

Author: Sooyeon Jeong

Submitted to the Program in Media Arts and Sciences, School of Architecture and Planning,on June 29, 2022, in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Media Arts and Sciences

論文Link

報告PPT

Abstract:
Globally, more than 264 million people of all ages are affected by depression, which
has become a leading cause of disability. Several interactive technologies for mental
health have been developed to make various therapeutic services more accessible and scalable. However, most are designed to engage users only within therapy and in-
tervention tasks. This thesis presents social robots that deliver interactive positive psychology interventions and build rapport with people over time as helpful compan-
ions to improve psychological wellbeing. Two long-term deployment studies explored and evaluated how these robotic agents could improve people’s psychological wellbeing in real-world contexts. In Study 1, a robotic coach provided seven positive psychology interventions for college students in on-campus dormitory settings and showed significant association with improvements in students’ psychological wellbeing, mood,and motivation to change. In Study 2, we deployed our robots in 80 people’s homes across the U.S. during the COVID-19 pandemic and evaluated the efficacy of a social robot that delivers wellbeing interventions as a peer-like companion rather than an expert coach. The companion-like robot was shown to be the most effective in building a positive therapeutic alliance with people and resulted in enhanced psychological wellbeing, improved readiness for change, and reduced negative affect. We further explored how traits, such as personality and age, influence the intervention outcomes and participants’ engagement with the robot. The two long-term in-the-wild studies offer valuable insights into design challenges and opportunities for companion AI agents that personalize mental health interventions and agent behaviors based on users’ traits and behavioral cues for better mental health outcomes.

論文作者：Mariza Dima , Brunel University London,UK

論文來源：

ACM Journals > Journal on Computing and Cultural Heritage 

2022  https://dl.acm.org/doi/10.1145/3490393[PDF]

報告PPT：[PPT]

RePrompt:AutomaticPromptEditingtoRefineAI-GenerativeArt TowardsPreciseExpressions

Authors:

Yunlong Wang, Shuyuan Shen, Brian Y Lim

National University of Singapore, Singapore

Abstract:

Generative AI models have shown impressive ability to produce images with text prompts, which could benefit creativity in visual art creation and self-expression. However, it is unclear how precisely the generated images express contexts and emotions from the input texts. We explored the emotional expressiveness of AI-generated images and developed RePrompt, an automatic method to refine text prompts toward precise expression of the generated images. Inspired by crowdsourced editing strategies, we curated intuitive text features, such as the number and concreteness of nouns, and trained a proxy model to analyze the feature effects on the AI-generated image. With model explanations of the proxy model, we curated a rubric to adjust text prompts to optimize image generation for precise emotion expression. We conducted simulation and user studies, which showed that RePrompt significantly improves the emotional expressiveness of AI-generated images, especially for negative emotions.

Keywords:

Text-to-image generated model, prompt engineering, AI-generated visual art, emotion expression, explainable AI

→ Original Link:

→ Author Website:

→ Class Presentation PPT

論文名稱：LearnIoTVR: An End-to-End Virtual Reality Environment
Providing Authentic Learning Experiences for Internet of Things

論文作者：Zhengzhe Zhu, Ziyi Liu, Youyou Zhang, Lijun Zhu, Joey Huang, Ana M Villanueva, Xun Qian, Kylie Peppler, Karthik Ramani

論文來源：ACM  CHI 2023  https://doi.org/10.1145/3544548.3581396 [PDF]

報告PPT：[PPT] [PDF]

ABSTRACT

The rapid growth of Internet-of-Things (IoT) applications has generated interest from many industries and a need for graduates with relevant knowledge. An IoT system is comprised of spatially distributed interactions between humans and various interconnected IoT components. These interactions are contextualized within their ambient environment, thus impeding educators from recreating authentic tasks for hands-on IoT learning. We propose LearnIoTVR, an end-to-end virtual reality (VR) learning environment which helps students to acquire IoT knowledge through immersive design, programming, and exploration of real-world environments empowered by IoT (e.g., a smart house). The students start the learning process by installing virtual IoT components we created in diferent locations inside the VR environment so that the learning will be situated in the same context where the IoT is applied. With our custom-designed 3D block-based language, students can program IoT behaviors directly within VR and get immediate feedback on their programming outcome. In the user study, we evaluated the learning outcomes among students using LearnIoTVR with a pre- and post-test to understand to what extent does engagement in LearnIoTVR lead to gains in learning programming skills and IoT competencies. Additionally, we examined what aspects of LearnIoTVR support usability and learning of programming skills compared to a traditional desktop-based learning environment. The results from these studies were promising. We also acquired insightful user feedback which provides inspiration for further expansions of this system.

KEYWORDS

Virtual Reality, IoT, Block-based Programming, Project-based Learning, Immersive Programming, Embodied Interaction

Sympathetic wear

ACM SIGGRAPH 2022 Art Gallery

-PaperLink

-PPT

Authors:
Junichi Kanebako ,Naoya Watabe ,Miki Yamamura ,Haruki Nakamura ,Keisuke Shuto,HirokoUchiyama

ABSTRACT:

In situations where people must maintain physical distance from one another and rely on communication through digital screens, we sometimes feel a sense of absence and loneliness. Sympathetic Wear is artwork that supplements communication through digital displays and considers the person on the other side of the network. When we are sad or in pain, the action of having our backs rubbed can provide comfort. Adopting the back as our theme, Sympathetic Wear brings gentle healing to people’s minds and bodies by creating a soft tactile sensation on the back that is invisible on screen.

演講題目：3D場景表示與生成藝術最新技術介紹
演講時間：2023年4月11日晚上6:30PM
演講地點：清華大學綜合大樓R603
演講專家：楊元福博士

摘要:
3D場景表示和生成藝術是人工智慧領域中最令人興奮和發展迅速的研究領域之一。3D場景表示是建構元宇宙最重要的基礎技術，使用3D模型和算法將現實世界的物體數字化表示。生成藝術是指使用機器學習算法和神經網絡生成各種藝術作品，如繪畫、音樂和詩歌等。3D場景表示技術可以幫助人們輕鬆地創建具有細節和真實感的3D物體，例如人物角色、動物和建築。使用生成藝術技術，人們可以創造出與現實世界不同的，嶄新的和富有創意的3D藝術作品。
除了藝術創作，結合3D場景表示和生成藝術技術還可以應用於許多實際領域，如建築設計、遊戲開發和虛擬現實。我們可以使用3D場景表示技術創建逼真的建築模型，並使用生成藝術技術為其添加創新的藝術風格和細節。然而使用3D場景表示和生成藝術技術創造出的作品有時可能會出現缺陷，例如細節不夠精確或者現實感不夠強烈。此外使用3D場景表示和生成藝術技術需要大量的計算和資源，因此訓練與推論的成本較高。
3D場景表示和生成藝術技術是當前人工智慧領域中最具前景的研究方向之一。這些技術可以應用於許多領域，為人類提供更加豐富、逼真和具有創意的藝術體驗。隨著技術的不斷發展和完善，我們相信這些技術將在未來的藝術和科技領域中扮演越來越重要的角色。

楊元福準博士簡歷：
簡歷:
• AAID/MLAD Data Scientist
• CIT(持續改善團隊) 評審/輔導員
• 2020 機器學習與統計競賽 First Runner-up
• 2018 影像辨識比賽 First Place
• 2015 tsmc Patent Award.
• 2015 tsmc 最佳改善工程師
• 2011/2015/2016 CIT競賽First Award

• CVPR / ICCV / IEEE TNNLS 評審
• 2021 清華大學國際論文獎
• 2020 先進半導體製造會議(ASMC) – 最佳論文獎 (紐約)
• 2019~2022 先進半導體製造會議(ASMC) – 論文入選 (紐約)
• 2022 國際電腦視覺與圖型識別會議(CVPR) – 論文入選 (紐澳良)
• 2021 林茲電子藝術節- Medium . Permeation (林茲, 奧地利)
• NFT 藝術創作

Health Greeter Kiosk : Tech-enabled Signage to Encourage Face Mask Use and Social Distancing

Authors:

• Max Hudnell – Computer Vision Engineer
• Steven King – Associate Professor

 UNC , Reese Innovation Lab(USA)

Abstract:

COVID-19 has been the cause of a global health crisis over the last year. High transmission rates of the virus threaten to cause a wave of infections which have the potential to overwhelm hospitals, leaving infected individuals without treatment. The World Health Organization (WHO) endorses two primary preventative measures for reducing transmission rates: the usage of face masks and adherence to social distancing [World Health Organization 2021]. In order to increase population adherence to these measures, we designed the Health Greeter Kiosk: a form of digital signage. Traditional physical signage has been used throughout the pandemic to enforce COVID-19 mandates, but lack population engagement and can easily go unnoticed. We designed this kiosk with the intent to reinforce these COVID-19 prevention mandates while also considering the necessity of population engagement. Our kiosk encourages engagement by providing visual feedback which is based on analysis from our kiosk’s computer vision software. This software integrates real-time face mask and social distance detection on a low-budget computer, without the need of a GPU. Our kiosk also collects statistics, relevant to the WHO mandates, which can be used to develop well-informed reopening strategies.

→ Original Link:

→ Class Presentation PPT

論文名稱：MagnetIO:Passive yet Interactive Soft Haptic Pathes Anywhere

論文作者：Alex Mazursky, Shan-Yuan Teng(鄧善元), Romain Nith, Pedro Lopes

論文來源：ACM  Siggraph 2021 Emerging Technologies

報告PPT：[PPT] [PDF]

ABSTRACT

We propose a new type of haptic actuator, which we call MagnetIO, that is comprised of two parts: one battery-powered voice-coil worn on the user’s fingernail and any number of interactive soft patches that can be attached onto any surface (everyday objects, user’s body, appliances, etc.). When the user’s finger wearing our voice-coil contacts any of the interactive patches it detects its magnetic signature via magnetometer and vibrates the patch, adding haptic feedback to otherwise input-only interactions. To allow these passive patches to vibrate, we make them from silicone with regions doped with polarized neodymium powder, resulting in soft and stretchable magnets. This stretchable form-factor allows them to be wrapped to the user’s body or everyday objects of various shapes. We demonstrate how these add haptic output to many situations, such as adding haptic buttons to the walls of one’s home. In our technical evaluation, we demonstrate that our interactive patches can be excited across a wide range of frequencies (0-500 Hz) and can be tuned to resonate at specific frequencies based on the patch’s geometry. Furthermore, we demonstrate that MagnetIO’s vibration intensity is as powerful as a typical linear resonant actuator (LRA); yet, unlike these rigid actuators, our passive patches operate as springs with multiple modes of vibration, which enables a wider band around its resonant frequency than an equivalent LRA.

KEYWORDS

soft magnets, ubiquitous haptics, fabrication

Balanced Glass Design: A flavor perception changing system by controlling the center-of-gravity

Paper Link

報告PPT

Authors: Masaharu Hirose、Masahiko Inami

ABSTRACT: 

In this paper, we propose Balanced Glass Design, a system to change flavor perception. The system consists of glass-type device shifting its center of gravity in response to the user’s motion which allows drinking a beverage with a virtual perception of weight through drinking motion. We thought It’s possible to intervene in the user’s perception of flavor by displaying virtual weight perception, and so conducted experiments on weight perception and demonstrations as a user study. This paper describes the system design, the result of experiments, and comments obtained through a user study.

Demonstrating Touch&Fold: A Foldable Haptic Actuator for Rendering Touch in Mixed Reality

Authors:

Shan-Yuan Teng, Pengyu Li, Romain Nith, Joshua Fonseca, Pedro Lopes

University of Chicago, USA

Abstract:

We propose a nail-mounted foldable haptic device that provides tactile feedback to mixed reality (MR) environments by pressing against the user’s fingerpad when a user touches a virtual object. What is novel in our device is that it quickly tucks away when the user interacts with real-world objects. Its design allows it to fold back on top of the user’s nail when not in use, keeping the user’s fingerpad free to, for instance, manipulate handheld tools and other objects while in MR. To achieve this, we engineered a wireless and self-contained haptic device, which measures 24×24×41 mm and weighs 9.5 g. Furthermore, our foldable end-effector also features a linear resonant actuator, allowing it to render not only touch contacts (i.e., pressure) but also textures (i.e., vibrations). We demonstrate how our device renders contacts with MR surfaces, buttons, low- and high-frequency textures.

→ Original Link:

→ Author Website:

→ Class Presentation PPT

create your world | Young Professionals Award, Prix Ars Electronica 2021

Urban Green: Bamboo Bicycle

Authors:

Angelina Djukic (AT), Lukas Gabesam (AT), Japleen Khurana (AT), and Alina Schweighofer (AT)

→ Original Link:

→ Class Presentation PPT

Abstract: 

In the project “Urban Green: Bamboo Bicycle”, an environmentally friendly manufacturing process of bamboo bicycles was developed. The four artists did not want to accept that the conventional construction of bamboo frames uses non-environmentally friendly fasteners and toxic paints. Therefore, they developed an innovative production process that uses only biodegradable materials such as lignin and bio-resin. The fasteners are designed using CAD programs such as Fusion 360 and produced via 3D printing. Environmentally friendly injection molding technology is used to connect the fasteners to the frame. In addition, the artists* have given the bamboo bicycle of the future an innovative design that can be adapted to individual wishes.

Source:

Art Title:SISYPHUS

ARS ELECTRONICA Honorary Mention 2022

Catagory: Digital Communities

Author: Kachi Chan 

報告 ppt : [ppt]

ArtWork:[Ars link] , [Video]

Art Statement:

Sisyphus is an art installation featuring two robots engaged in endless cyclic interaction. Smaller robots build brick arches, whilst a giant robot pushes them down. This robotic system propels a narrative of construction and deconstruction.

Named after a figure in Greek mythology, who is condemned to push a boulder up a hill every day only to watch it roll back down afterwards. Sisyphus is a commentary on the current socio-political climate, where systems of authority and resistance continuously clash against each other. Repetition is explored in this piece through the interaction of two contrasting robotic systems—one small and nimble, the other powerful and oppressive—the Greek Sisyphus representing either or both of them.

Despite the discrepancy that exists between the size of the two robots, their struggle is endless. The giant robot does not make any concessions and continues to crush the brick arches. Even once destroyed, however, the small robots proceed to building new brick arches, thereby manifesting a collective resistance through individual autonomous actions. Here, the status quo is continuously challenged by small, dispersed acts that disrupt the absolute power of the giant robot. The persistence of the small robots and their ability to propagate small-scale, new forms of resistance make all efforts worthwhile, as opposed to “futile.” Hence, Sisyphus symbolizes not only the confrontation between power and resistance, but also the hope that comes with the possibility of change.

The Home

PRIX ARS ELECTRONICA 2021 – Digital Musics & Sound Art – Honorary Mention

Authors:

Annie Saunders(US) & Jackie Zhou(US)

→ Original Link:

→ Artwork Video

→ Class Presentation PPT

Abstract: 

報告者：劉士達
報告PPT：TechArt Seminar 2023.03.07-Dream Printer (S.T.Liu)  [PPT)]

作品名稱：Dream Painter

作品作者：Varvara Guljajeva, Mar Canet Sola

作品來源：ACM  Multimedia 2022 Interactive Art

Abstract：

Dream Painter is an interactive robotic art installation that turns the audience’s spoken dreams into a collective painting. By telling one’s past dream, a participant guides the interactive robotic system in the latent space of the AI model that results in a multicolored line drawing. The artwork consists of several parts: an interaction station, a painting robot, a kinetic and animated mechanism that moves the paper roll when a drawing is finished, and the deep learning model that transforms a spoken word into a painting. All these interconnected components of hardware and software are arranged into an autonomous and interactive robotic art installation. The main aims of this project are to explore the interactive potential of AI technology and robotics, and trigger discussion over the deep learning applications in a wider sense. More precisely, this case study is primarily focused on the translation of different semiotic spaces as a trigger for creativity and audience interaction method.

Keywords：

Interactive Art, Co-creative AI, Robotic Art, Speech-to-image, Human-Centered-Interface, Latent-space