skip to main content


Title: Baba is Y’all: Collaborative Mixed-Initiative Level Design
We present a collaborative mixed-initiative system for building levels for the puzzle game “Baba is You”. Unlike previous mixed-initiative systems, Baba is Y’all is designed for collaborative asynchronous creation by multiple users over the internet. The system includes several AI-assisted features to help designers, including a level evolver and an automated player for playtesting. The level archives catalogues levels according to which mechanics are implemented and not implemented, allowing the system to ask users to design levels with specific combinations of mechanics. We describe the operation of the system and the results of small-scale informal user test, and discuss future development paths for this system as well as for collaborative mixed-initiative systems in general.  more » « less
Award ID(s):
1717324
NSF-PAR ID:
10231879
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
IEEE Conference on Games
Page Range / eLocation ID:
542 to 549
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    Mixed-initiative visual analytics systems incorporate well-established design principles that improve users' abilities to solve problems. As these systems consider whether to take initiative towards achieving user goals, many current systems address the potential for cognitive bias in human initiatives statically, relying on fixed initiatives they can take instead of identifying, communicating and addressing the bias as it occurs. We argue that mixed-initiative design principles can and should incorporate cognitive bias mitigation strategies directly through development of mitigation techniques embedded in the system to address cognitive biases in situ. We identify domain experts in machine learning adopting visual analytics techniques and systems that incorporate existing mixed-initiative principles and examine their potential to support bias mitigation strategies. This examination considers the unique perspective these experts bring to visual analytics and is situated in existing user-centered systems that make exemplary use of design principles informed by cognitive theory. We then suggest informed opportunities for domain experts to take initiative toward addressing cognitive biases in light of their existing contributions to the field. Finally, we contribute open questions and research directions for designers seeking to adopt visual analytics techniques that incorporate bias-aware initiatives in future systems. 
    more » « less
  2. Major challenges in engineering education include retention of undergraduate engineering students (UESs) and continued engagement after the first year when concepts increase in difficulty. Additionally, employers, as well as ABET, look for students to demonstrate non-technical skills, including the ability to work successfully in groups, the ability to communicate both within and outside their discipline, and the ability to find information that will help them solve problems and contribute to lifelong learning. Teacher education is also facing challenges given the recent incorporation of engineering practices and core ideas into the Next Generation Science Standards (NGSS) and state level standards of learning. To help teachers meet these standards in their classrooms, education courses for preservice teachers (PSTs) must provide resources and opportunities to increase science and engineering knowledge, and the associated pedagogies. To address these challenges, Ed+gineering, an NSF-funded multidisciplinary collaborative service learning project, was implemented into two sets of paired-classes in engineering and education: a 100 level mechanical engineering class (n = 42) and a foundations class in education (n = 17), and a fluid mechanics class in mechanical engineering technology (n = 23) and a science methods class (n = 15). The paired classes collaborated in multidisciplinary teams of 5-8 undergraduate students to plan and teach engineering lessons to local elementary school students. Teams completed a series of previously tested, scaffolded activities to guide their collaboration. Designing and delivering lessons engaged university students in collaborative processes that promoted social learning, including researching and planning, peer mentoring, teaching and receiving feedback, and reflecting and revising their engineering lesson. The research questions examined in this pilot, mixed-methods research study include: (1) How did PSTs’ Ed+gineering experiences influence their engineering and science knowledge?; (2) How did PSTs’ and UESs’ Ed+gineering experiences influence their pedagogical understanding?; and (3) What were PSTs’ and UESs’ overall perceptions of their Ed+gineering experiences? Both quantitative (e.g., Engineering Design Process assessment, Science Content Knowledge assessment) and qualitative (student reflections) data were used to assess knowledge gains and project perceptions following the semester-long intervention. Findings suggest that the PSTs were more aware and comfortable with the engineering field following lesson development and delivery, and often better able to explain particular science/engineering concepts. Both PSTs and UESs, but especially the latter, came to realize the importance of planning and preparing lessons to be taught to an audience. UESs reported greater appreciation for the work of educators. PSTs and UESs expressed how they learned to work in groups with multidisciplinary members—this is a valuable lesson for their respective professional careers. Yearly, the Ed+gineering research team will also request and review student retention reports in their respective programs to assess project impact. 
    more » « less
  3. null (Ed.)
    This paper introduces RL Brush, a level-editing tool for tile-based games designed for mixed-initiative co-creation. The tool uses reinforcement-learning-based models to augment manual human level-design through the addition of AI-generated suggestions. Here, we apply RL Brush to designing levels for the classic puzzle game Sokoban. We put the tool online and tested it in 39 different sessions. The results show that users using the AI suggestions stay around longer and their created levels on average are more playable and more complex than without. 
    more » « less
  4. There are huge on-going challenges to timely access of accurate online biomedical content due to exponential growth of unstructured biomedical data. Therefore, semantic annotations are essentially required with the biomedical content in order to improve search engines’ context-aware indexing, search efficiency, and precision of the retrieved results. In this study, we propose a personalized semantic annotation recommendations approach to biomedical content through an expanded socio-technical approach. Our layered architecture generates annotations on the users’ entered text in the first layer. To optimize the yielded annotations, users can seek help from professional experts by posing specific questions to them. The socio-technical system also connects help seekers (users) to help providers (experts) employing the pre-trained BERT embedding, which matches the profile similarity scores of users and experts at various levels and suggests a run-time compatible match (of the help seeker and the help provider). Our approach overcomes previous systems’ limitations as they are predominantly non-collaborative and laborious. While performing experiments, we analyzed the performance enhancements offered by our socio-technical approach in improving the semantic annotations in three scenarios in various contexts. Our results show overall achievement of 89.98% precision, 89.61% recall, and an 89.45% f1-score at the system level. Comparatively speaking, a high accuracy of 90% was achieved with the socio-technical approach whereas the traditional approach could only reach 87% accuracy. Our novel socio-technical approach produces apt annotation recommendations that would definitely be helpful for various secondary uses ranging from context-aware indexing to retrieval accuracy improvements. 
    more » « less
  5. Nepal is positioned at the intersection of the Indian Summer Monsoon (ISM) and Subtropical Jet (SJ). Although the ISM is responsible for ~two thirds of annual precipitation, the SJ supplies precipitation in the winter and spring, with the jet migrating southwards to the subcontinent beginning in October and reaching its most southerly position in May before moving northward in June. Using the state-of-the-art Community Earth System Model Last Millennium Ensemble, we investigated potential drivers of the latitudinal position of the SJ over Nepal (referred to as the Himalayan Jet) between 850-2005 CE. The Himalayan Jet Latitude [HJL] is defined as the latitude with the highest wind speed at 200 mb for every longitude containing Nepal (Thapa et al., 2022). In order to identify dominant periodicities in HJL positioning, power-spectral-density analyses were used. For the purpose of evaluating drivers of HJL position, we identified years with a northward or southward displaced HJL, defined as being two standard deviations above or below the average annual HJL position, and used anomaly composites of precipitation, winds (upper- and lower-level), sea surface temperature, moisture transport (lower-level at 850mb), and geopotential height (upper-level at 200mb). Our analyses seem to point toward a link between HJL and the phases of the El Niño Southern Oscillation and Indian Ocean Dipole (IOD): Southerly HJL years often occur during years with an El Niño and a positive IOD event. Northerly HJL years often occur when a Rossby wave train appears to be present over Nepal, indicative of a remote teleconnection. We provide an initial quantification of the physical mechanics of how these climate modes in the Pacific, Indian, and Atlantic Oceans, including remote teleconnections transmitted via atmospheric Rossby Waves, affect HJL. These climate model simulation results are also compared with a sub-decadally-resolved, precisely-dated, composite stalagmite isotope record of ISM variability from Siddha Baba cave, central Nepal. 
    more » « less