This content will become publicly available on March 25, 2025
Effective teamwork translates to fewer preventable errors and higher task performance in collaborative tasks. However, in time-critical tasks, successful teamwork becomes highly challenging to attain. In such settings, often, team members have partial observability of their surroundings, incur high cost of communication, and have trouble estimating the state and intent of their teammates. To assist a team in improving teamwork at task time, my doctoral research proposes an automated task-time team intervention system. Grounded in the notion of shared mental models, the system first detects whether the team is on the same page or not. It then generates effective interventions to improve teamwork. Additionally, by leveraging past demonstrations to learn a model of team behavior, this system minimizes the need for domain experts to specify teamwork models and rules.
more » « less- Award ID(s):
- 2205454
- PAR ID:
- 10517532
- Publisher / Repository:
- Association for the Advancement of Artificial Intelligence (AAAI)
- Date Published:
- Journal Name:
- Proceedings of the AAAI Conference on Artificial Intelligence
- Volume:
- 38
- Issue:
- 21
- ISSN:
- 2159-5399
- Page Range / eLocation ID:
- 23415 to 23416
- Subject(s) / Keyword(s):
- Human-AI Collaboration Computer-Aided Human Decision-Making Imitation Learning Teamwork Multi-agent Systems
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
Effective human-human and human-autonomy teamwork is critical but often challenging to perfect. The challenge is particularly relevant in time-critical domains, such as healthcare and disaster response, where the time pressures can make coordination increasingly difficult to achieve and the consequences of imperfect coordination can be severe. To improve teamwork in these and other domains, we present TIC: an automated intervention approach for improving coordination between team members. Using BTIL, a multi-agent imitation learning algorithm, our approach first learns a generative model of team behavior from past task execution data. Next, it utilizes the learned generative model and team's task objective (shared reward) to algorithmically generate execution-time interventions. We evaluate our approach in synthetic multi-agent teaming scenarios, where team members make decentralized decisions without full observability of the environment. The experiments demonstrate that the automated interventions can successfully improve team performance and shed light on the design of autonomous agents for improving teamwork.more » « less
-
Abstract Background Effectively facilitating teamwork experiences, particularly in the context of large-size courses, is difficult to implement. This study seeks to address the challenges of implementing effective teamwork experiences in large courses. This study integrated teamwork pedagogy to facilitate a semester-long project in the context of a large-size class comprising 118 students organized into 26 teams. The data for this study were collected from two online teamwork sessions when teams collaborated and self-recorded during the in-class time. The video recordings were qualitatively analyzed to identify patterns in team dynamics processes through visualizations. The study aims to provide insights into the different ways team members engaged in team dynamics processes during different phases of the semester.
Results Findings suggest that members of teams were mostly active and passive during meetings and less constructive and interactive in their engagement. Team members mainly engaged in communication, team orientation, and feedback behaviors. Over time, team members' interactions with one another remained about the same, with feedback behaviors tending to diminish and coordination behaviors staying about the same or slightly increasing over time.
Conclusion The implications of this study extend to both practice and theory. Practically, combining cooperative learning and scrum practices enabled a blend of collaborative and cooperative work, which suggests providing teams with tools and structures to coordinate teamwork processes and promote interaction among team members. From a theoretical perspective, this study contributes to the understanding of temporal aspects of teamwork dynamics by examining how team interactions evolve during working sessions at different points in time. Overall, this research provides valuable insights for educators, practitioners, and researchers aiming to enhance teamwork experiences in large courses, particularly in software development disciplines.
-
Global teams frequently consist of language-based subgroups who put together complementary information to achieve common goals. Previous research outlines a two-step work communication flow in these teams. There are team meetings using a required common language (i.e., English); in preparation for those meetings, people have subgroup conversations in their native languages. Work communication at team meetings is often less effective than in subgroup conversations. In the current study, we investigate the idea of leveraging machine translation (MT) to facilitate global team meetings. We hypothesize that exchanging subgroup conversation logs before a team meeting offers contextual information that benefits teamwork at the meeting. MT can translate these logs, which enables comprehension at a low cost. To test our hypothesis, we conducted a between-subjects experiment where twenty quartets of participants performed a personnel selection task. Each quartet included two English native speakers (NS) and two non-native speakers (NNS) whose native language was Mandarin. All participants began the task with subgroup conversations in their native languages, then proceeded to team meetings in English. We manipulated the exchange of subgroup conversation logs prior to team meetings: with MT-mediated exchanges versus without. Analysis of participants' subjective experience, task performance, and depth of discussions as reflected through their conversational moves jointly indicates that team meeting quality improved when there were MT-mediated exchanges of subgroup conversation logs as opposed to no exchanges. We conclude with reflections on when and how MT could be applied to enhance global teamwork across a language barrier.more » « less
-
Situational awareness (SA) is vital for coordination and safety in complex domains. However, the lack of focus on shared SA (SSA) between teammates undermines effective teamwork. Gaze sharing allows partners to view each other’s gaze points on their respective displays while completing their tasks. Understanding how performance and SSA are influenced by gaze sharing is critical but understudied in dynamic contexts. In this study, 35 teams completed unmanned aerial vehicle (UAV) command-and-control (C2) tasks using different visualization techniques. SSA scores were the highest with the fixation trail, correlating positively with target detection accuracy. SSA scores were lower in the no gaze sharing condition and the lowest while using the fixation dot. These findings underscore the importance of visualization methods in shaping SSA and task performance. If gaze sharing is used, the results here show that there is a need to select appropriate visualization techniques to support team SSA and performance.
-
This research paper investigates the effectiveness of cooperative learning and co-regulation strategies in promoting teamwork and enhancing students' performance in higher education. The study was conducted in an in-person intermediate-level information system design course with 152 students divided into 31 teams. The students utilized the Scrum framework to manage a semester-long project with three milestones. Retrospective data were collected at the end of each milestone, and the first milestone data were analyzed in this study. Through a thematic analysis of retrospective data collected after the first milestone, the study examines students' planning, monitoring, and reflection strategies. The findings reveal that students demonstrated adaptive planning, equitable contribution, and task allocation based on individual strengths and preferences. In terms of monitoring, students adopted a proactive approach, displayed relational competence, and utilized both synchronous and asynchronous communication channels. Regarding reflection, students valued effective planning and execution but struggled with time management. They developed concrete improvement strategies for the next milestone, emphasizing realistic deadlines, improved communication, and a better understanding of team members' strengths. This research contributes to the understanding of cooperative learning and co-regulation in promoting effective teamwork in higher education. The findings have implications for pedagogical practices and suggest the importance of integrating cooperative learning and co-regulation strategies in team-based learning environments. Future research can further explore the application of these strategies in different educational contexts and investigate their long-term effects on students' performance and engagement.more » « less