Heejin Jeong

Hari Iyer, Neel Macwan, Shenghan Guo et al.

The performance of physical workers is significantly influenced by the extent of their motions. However, monitoring and assessing these motions remains a challenge. Recent advancements have enabled in-situ video analysis for real-time observation of worker behaviors. This paper introduces a novel framework for tracking and quantifying upper and lower limb motions, issuing alerts when critical thresholds are reached. Using joint position data from posture estimation, the framework employs Hotelling's $T^2$ statistic to quantify and monitor motion amounts. A significant positive correlation was noted between motion warnings and the overall NASA Task Load Index (TLX) workload rating (\textit{r} = 0.218, \textit{p} = 0.0024). A supervised Random Forest model trained on the collected motion data was benchmarked against multiple datasets including UCF Sports Action and UCF50, and was found to effectively generalize across environments, identifying ergonomic risk patterns with accuracies up to 94\%.

Hari Iyer, Neel Macwan, Atharva Jitendra Hude et al.

Human motion simulation (HMS) supports cost-effective evaluation of worker behavior, safety, and productivity in industrial tasks. However, existing methods often suffer from low motion fidelity. This study introduces Generative-AI-Enabled HMS (G-AI-HMS), which integrates text-to-text and text-to-motion models to enhance simulation quality for physical tasks. G-AI-HMS tackles two key challenges: (1) translating task descriptions into motion-aware language using Large Language Models aligned with MotionGPT's training vocabulary, and (2) validating AI-enhanced motions against real human movements using computer vision. Posture estimation algorithms are applied to real-time videos to extract joint landmarks, and motion similarity metrics are used to compare them with AI-enhanced sequences. In a case study involving eight tasks, the AI-enhanced motions showed lower error than human created descriptions in most scenarios, performing better in six tasks based on spatial accuracy, four tasks based on alignment after pose normalization, and seven tasks based on overall temporal similarity. Statistical analysis showed that AI-enhanced prompts significantly (p $<$ 0.0001) reduced joint error and temporal misalignment while retaining comparable posture accuracy.

Sruthi Ramadurai, Heejin Jeong

Human-robot collaboration has significant potential in recycling due to the wide variation in the composition of recyclable products. Six participants performed a recyclable item sorting task collaborating with a robot arm equipped with a vision system. The effect of three different levels of human involvement or assistance to the robot (Level 1- occlusion removal; Level 2- optimal spacing; Level 3- optimal grip) on performance metrics such as robot accuracy, task time and subjective fluency were assessed. Results showed that human involvement had a remarkable impact on the robot's accuracy, which increased with human involvement level. Mean accuracy values were 33.3% for Level 1, 69% for Level 2 and 100% for Level 3. The results imply that for sorting processes involving diverse materials that vary in size, shape, and composition, human assistance could improve the robot's accuracy to a significant extent while also being cost-effective.

Yalda Ghasemi, Ankit Singh, Myunghee Kim et al.

An augmented reality (AR) environment includes a set of digital elements with which the users interact while performing certain tasks. Recent AR head-mounted displays allow users to select how these elements are presented. However, few studies have been conducted to examine the effect of the way of presenting augmented content on user performance and workload. This study aims to evaluate two methods of presenting augmented content - world-locked and head-locked modes in a data entry task. A total of eighteen participants performed the data entry task in this study. The effectiveness of each mode is evaluated in terms of task performance, muscle activity, perceived workload, and usability. The results show that the task completion time is shorter and the typing speed is significantly faster in the head-locked mode while the world-locked mode achieved higher scores in terms of preference. The findings of this study can be applied to AR user interfaces to improve content presentation and enhance the user experience.

Yalda Ghasemi, Heejin Jeong

In this paper, we introduce two remote extended reality (XR) research methods that can overcome the limitations of lab-based controlled experiments, especially during the COVID-19 pandemic: (1) a predictive model-based task analysis and (2) a large-scale video-based remote evaluation. We used a box stacking task including three interaction modalities - two multimodal gaze-based interactions as well as a unimodal hand-based interaction which is defined as our baseline. For the first evaluation, a GOMS-based task analysis was performed by analyzing the tasks to understand human behaviors in XR and predict task execution times. For the second evaluation, an online survey was administered using a series of the first-person point of view videos where a user performs the corresponding task with three interaction modalities. A total of 118 participants were asked to compare the interaction modes based on their judgment. Two standard questionnaires were used to measure perceived workload and the usability of the modalities.

Christopher D. Hsu, Heejin Jeong, George J. Pappas et al.

We develop a Multi-Agent Reinforcement Learning (MARL) method to learn scalable control policies for target tracking. Our method can handle an arbitrary number of pursuers and targets; we show results for tasks consisting up to 1000 pursuers tracking 1000 targets. We use a decentralized, partially-observable Markov Decision Process framework to model pursuers as agents receiving partial observations (range and bearing) about targets which move using fixed, unknown policies. An attention mechanism is used to parameterize the value function of the agents; this mechanism allows us to handle an arbitrary number of targets. Entropy-regularized off-policy RL methods are used to train a stochastic policy, and we discuss how it enables a hedging behavior between pursuers that leads to a weak form of cooperation in spite of completely decentralized control execution. We further develop a masking heuristic that allows training on smaller problems with few pursuers-targets and execution on much larger problems. Thorough simulation experiments, ablation studies, and comparisons to state of the art algorithms are performed to study the scalability of the approach and robustness of performance to varying numbers of agents and targets.

Heejin Jeong, Hamed Hassani, Manfred Morari et al.

We solve active target tracking, one of the essential tasks in autonomous systems, using a deep reinforcement learning (RL) approach. In this problem, an autonomous agent is tasked with acquiring information about targets of interests using its onboard sensors. The classical challenges in this problem are system model dependence and the difficulty of computing information-theoretic cost functions for a long planning horizon. RL provides solutions for these challenges as the length of its effective planning horizon does not affect the computational complexity, and it drops the strong dependency of an algorithm on system models. In particular, we introduce Active Tracking Target Network (ATTN), a unified RL policy that is capable of solving major sub-tasks of active target tracking -- in-sight tracking, navigation, and exploration. The policy shows robust behavior for tracking agile and anomalous targets with a partially known target model. Additionally, the same policy is able to navigate in obstacle environments to reach distant targets as well as explore the environment when targets are positioned in unexpected locations.

Heejin Jeong, Brent Schlotfeldt, Hamed Hassani et al.

In this paper, we propose a novel Reinforcement Learning approach for solving the Active Information Acquisition problem, which requires an agent to choose a sequence of actions in order to acquire information about a process of interest using on-board sensors. The classic challenges in the information acquisition problem are the dependence of a planning algorithm on known models and the difficulty of computing information-theoretic cost functions over arbitrary distributions. In contrast, the proposed framework of reinforcement learning does not require any knowledge on models and alleviates the problems during an extended training stage. It results in policies that are efficient to execute online and applicable for real-time control of robotic systems. Furthermore, the state-of-the-art planning methods are typically restricted to short horizons, which may become problematic with local minima. Reinforcement learning naturally handles the issue of planning horizon in information problems as it maximizes a discounted sum of rewards over a long finite or infinite time horizon. We discuss the potential benefits of the proposed framework and compare the performance of the novel algorithm to an existing information acquisition method for multi-target tracking scenarios.

Heejin Jeong, Clark Zhang, George J. Pappas et al.

While off-policy temporal difference (TD) methods have widely been used in reinforcement learning due to their efficiency and simple implementation, their Bayesian counterparts have not been utilized as frequently. One reason is that the non-linear max operation in the Bellman optimality equation makes it difficult to define conjugate distributions over the value functions. In this paper, we introduce a novel Bayesian approach to off-policy TD methods, called as ADFQ, which updates beliefs on state-action values, Q, through an online Bayesian inference method known as Assumed Density Filtering. We formulate an efficient closed-form solution for the value update by approximately estimating analytic parameters of the posterior of the Q-beliefs. Uncertainty measures in the beliefs not only are used in exploration but also provide a natural regularization for the value update considering all next available actions. ADFQ converges to Q-learning as the uncertainty measures of the Q-beliefs decrease and improves common drawbacks of other Bayesian RL algorithms such as computational complexity. We extend ADFQ with a neural network. Our empirical results demonstrate that ADFQ outperforms comparable algorithms on various Atari 2600 games, with drastic improvements in highly stochastic domains or domains with a large action space.