Alert button
Picture for Sangwon Seo

Sangwon Seo

Alert button

Automated Task-Time Interventions to Improve Teamwork using Imitation Learning

Mar 02, 2023
Sangwon Seo, Bing Han, Vaibhav Unhelkar

Figure 1 for Automated Task-Time Interventions to Improve Teamwork using Imitation Learning
Figure 2 for Automated Task-Time Interventions to Improve Teamwork using Imitation Learning
Figure 3 for Automated Task-Time Interventions to Improve Teamwork using Imitation Learning
Figure 4 for Automated Task-Time Interventions to Improve Teamwork using Imitation Learning

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.

* Extended version of an identically-titled paper accepted at AAMAS 2023 
Viaarxiv icon

Semi-Supervised Imitation Learning of Team Policies from Suboptimal Demonstrations

May 11, 2022
Sangwon Seo, Vaibhav V. Unhelkar

Figure 1 for Semi-Supervised Imitation Learning of Team Policies from Suboptimal Demonstrations
Figure 2 for Semi-Supervised Imitation Learning of Team Policies from Suboptimal Demonstrations
Figure 3 for Semi-Supervised Imitation Learning of Team Policies from Suboptimal Demonstrations
Figure 4 for Semi-Supervised Imitation Learning of Team Policies from Suboptimal Demonstrations

We present Bayesian Team Imitation Learner (BTIL), an imitation learning algorithm to model behavior of teams performing sequential tasks in Markovian domains. In contrast to existing multi-agent imitation learning techniques, BTIL explicitly models and infers the time-varying mental states of team members, thereby enabling learning of decentralized team policies from demonstrations of suboptimal teamwork. Further, to allow for sample- and label-efficient policy learning from small datasets, BTIL employs a Bayesian perspective and is capable of learning from semi-supervised demonstrations. We demonstrate and benchmark the performance of BTIL on synthetic multi-agent tasks as well as a novel dataset of human-agent teamwork. Our experiments show that BTIL can successfully learn team policies from demonstrations despite the influence of team members' (time-varying and potentially misaligned) mental states on their behavior.

* Extended version of an identically-titled paper accepted at IJCAI 2022 
Viaarxiv icon

Towards an AI Coach to Infer Team Mental Model Alignment in Healthcare

Feb 17, 2021
Sangwon Seo, Lauren R. Kennedy-Metz, Marco A. Zenati, Julie A. Shah, Roger D. Dias, Vaibhav V. Unhelkar

Figure 1 for Towards an AI Coach to Infer Team Mental Model Alignment in Healthcare
Figure 2 for Towards an AI Coach to Infer Team Mental Model Alignment in Healthcare

Shared mental models are critical to team success; however, in practice, team members may have misaligned models due to a variety of factors. In safety-critical domains (e.g., aviation, healthcare), lack of shared mental models can lead to preventable errors and harm. Towards the goal of mitigating such preventable errors, here, we present a Bayesian approach to infer misalignment in team members' mental models during complex healthcare task execution. As an exemplary application, we demonstrate our approach using two simulated team-based scenarios, derived from actual teamwork in cardiac surgery. In these simulated experiments, our approach inferred model misalignment with over 75% recall, thereby providing a building block for enabling computer-assisted interventions to augment human cognition in the operating room and improve teamwork.

* Submitted to the 2021 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA) 
Viaarxiv icon

VOTE400(Voide Of The Elderly 400 Hours): A Speech Dataset to Study Voice Interface for Elderly-Care

Jan 20, 2021
Minsu Jang, Sangwon Seo, Dohyung Kim, Jaeyeon Lee, Jaehong Kim, Jun-Hwan Ahn

Figure 1 for VOTE400(Voide Of The Elderly 400 Hours): A Speech Dataset to Study Voice Interface for Elderly-Care
Figure 2 for VOTE400(Voide Of The Elderly 400 Hours): A Speech Dataset to Study Voice Interface for Elderly-Care
Figure 3 for VOTE400(Voide Of The Elderly 400 Hours): A Speech Dataset to Study Voice Interface for Elderly-Care
Figure 4 for VOTE400(Voide Of The Elderly 400 Hours): A Speech Dataset to Study Voice Interface for Elderly-Care

This paper introduces a large-scale Korean speech dataset, called VOTE400, that can be used for analyzing and recognizing voices of the elderly people. The dataset includes about 300 hours of continuous dialog speech and 100 hours of read speech, both recorded by the elderly people aged 65 years or over. A preliminary experiment showed that speech recognition system trained with VOTE400 can outperform conventional systems in speech recognition of elderly people's voice. This work is a multi-organizational effort led by ETRI and MINDs Lab Inc. for the purpose of advancing the speech recognition performance of the elderly-care robots.

* 3 pages, 7 tables 
Viaarxiv icon