More Like this

1. A measure of visuospatial reasoning skills: Painting the big picture

   Michelson, J.; Sanyal, D.; Ainooson, J.; Kunda, M. (January 2020, Proceedings of the Eighth Annual Conference on Advances in Cognitive Systems (ACS))

   null (Ed.)

   Visuospatial reasoning refers to a diverse set of skills that involve thinking about space and time. An artificial agent with access to a sufficiently large set of visuospatial reasoning skills might be able to generalize its reasoning ability to an unprecedented expanse of tasks including portions of many popular intelligence tests. In this paper, we stress the importance of a developmental approach to the study of visuospatial reasoning, with an emphasis on fundamental skills. A comprehensive benchmark, with properties we outline in this paper including breadth, depth, explainability, and domain-specificity, would encourage and measure the genesis of such a skillset. Lacking an existing benchmark that satisfies these properties, we outline the design of a novel test in this paper. Such a benchmark would allow for expanding analysis of existing datasets’ and agents’ applicability to the problem of generalized visuospatial reasoning. 

   more » « less
2. How Does Working on an Interdisciplinary Service-Learning Project vs. a Disciplinary Design Project Affect Peer Evaluators' Teamwork Skills?

   Kumi, I. K. (June 2023, ASEE New England annual conference)

   Over the course of several semesters, two different project-based learning approaches were used in two undergraduate engineering courses–a 100-level introductory course that covered a general education requirement on information literacy and a 300-level fluid mechanics course. One project (treatment) was an interdisciplinary service-learning project, implemented with undergraduate engineering and education students who collaborated to develop and deliver engineering lessons to fourth and fifth-grade students in a field trip model. The other projects (comparison) involved a team-based design project contained within each class. In the 100-level course, students selected their project based on personal interests and followed the engineering design process to develop, test, and redesign a prototype. In the fluid mechanics class, students designed a pumped pipeline system for a hypothetical plant. This study aimed to determine whether participating in the interdisciplinary project affected students’ evaluation of their own and their teammates’ teamwork effectiveness skills, measured using the Behaviorally Anchored Rating Scale (BARS) version of the Comprehensive Assessment of Team Member Effectiveness (CATME). The five dimensions of CATME measured in this study are (1) contribution to the team’s work, (2) interacting with teammates, (3) keeping the team on track, (4) expecting quality, and (5) having relevant knowledge, skills, and abilities (KSAs). The quantitative data from CATME were analyzed using ANCOVA. Furthermore, since data were collected over three semesters and coincided with the pre, during, and post-phases of the COVID-19 pandemic, it was possible to examine the effects of the evolving classroom constraints over the course of the pandemic on the teamwork effectiveness skills of both the treatment and comparison classes. 

   more » « less
3. Simple Temporal Networks for Improvisational Teamwork

   https://doi.org/10.1609/icaps.v32i1.19809  

   Morgan, Malia; Schalkwyk, Julianna; Wang, Huaxiaoyue; Davalos, Hannah; Martinez, Ryan; Rohilla, Vibha; Boerkoel, James (June 2022, Proceedings of the International Conference on Automated Planning and Scheduling)

   When communication between teammates is limited to observations of each other's actions, agents may need to improvise to stay coordinated. Unfortunately, current methods inadequately capture the uncertainty introduced by a lack of direct communication. This paper augments existing frameworks to introduce Simple Temporal Networks for Improvisational Teamwork (STN-IT)—a formulation that captures both the temporal dependencies and uncertainties between agents who need to coordinate but lack reliable communication. We define the notion of strong controllability for STN-ITs, which establishes a static scheduling strategy for controllable agents that produces a consistent team schedule, as long as non-communicative teammates act within known problem constraints. We provide both an exact and approximate approach for finding strongly controllable schedules, empirically demonstrate the trade-offs between these approaches on benchmarks of STN-ITs, and show analytically that the exact method is correct. 

   more » « less
4. Simple Temporal Networks for Improvisational Teamwork

   Morgan, M.; Schalkwyk, J.; Wang, H.; Davalos, H.; Martinez, R.; Rohilla, V.; Boerkoel, J. (March 2022, AAAI Spring Symposium Series on Can We Talk? How to Design Multi-Agent Systems In the Absence of Reliable Communications)

   When communication between teammates is limited to observations of each other’s actions, agents may need to improvise to stay coordinated. Unfortunately, current methods inadequately capture the uncertainty introduced by a lack of direct communication. This paper augments existing frameworks to introduce Simple Temporal Networks for Improvisational Teamwork (STN-IT) — a formulation that captures both the temporal dependencies and uncertainties between agents who need to coordinate, but lack reliable communication. We define the notion of strong controllability for STN-ITs, which establishes a static scheduling strategy for controllable agents that produces a consistent team schedule, as long as non-communicative teammates act within known problem constraints. We provide both an exact and approximate approach for finding strongly controllable schedules, empirically demonstrate the trade-offs between these two approaches on a benchmark of STN-ITs, and show analytically that the exact method is correct. In addition, we provide an empirical analysis of the exact and approximate approaches’ efficiency 

   more » « less
5. Skills geoscience employers look for in bachelors-level geoscientists

   Shafer, Gregory; Viskupic, Karen; Egger, Anne (July 2021, Earth Educators' Rendezvous)

   Preparing graduates to enter the workforce is a common goal of undergraduate geoscience degree programs. Determining what skills are necessary for new graduates to succeed in the workforce requires knowledge of the skills sought by employers of bachelors-level geoscientists. To investigate skills desired by employers, we systematically analyzed job advertisements retrieved from 4 search engines between May and November 2020. We used 15 search words derived from the 2018 Status of the Geoscience Workforce (AGI) report to select job advertisements that required or preferred a geoscience-based bachelor's degree. Additionally, we categorized each advertisement by industry sector based on definitions in the 2018 AGI report. Each job advertisement (n=1214) was coded to identify skills sought by the employer. An initial set of codes was based on skills identified by the Future of Undergraduate Geoscience Education project and additional emergent codes were identified during the coding process. We generated a final set of 34 codes, with definitions and examples, through an iterative coding process, checking for inter-rater reliability. Advertisements were not coded for geoscience content knowledge. The most common skills sought by employers were the ability to conduct field work, teamwork, work with computers, collect, process and interpret data, and communicate effectively, however, the desirability of skills varied across industry sectors. For example, teamwork skills were sought in 60% of mining sector advertisements but only 22% of oil and gas sector advertisements. Our results provide insight into the expectations of potential employers for recent graduates seeking a career in geoscience. Additionally, our results provide geoscience degree programs with critical information required to prepare undergraduates with the necessary skills to be successful in the current job market. 

   more » « less