Abstract Despite advances in automation, manual material handling (MMH) tasks continue to be commonplace in the workplace. To design and control the high burden of musculoskeletal disorders (MSDs) during MMH tasks, several assessment tools have been proposed to monitor injury risk factors such as posture, repetition and force. However, several fundamental limitations of current tools affect their effectiveness in controlling injury risk factors. First, tools currently used in practiced are typically cross-sectional and observer-based. These manually observed snapshots of the jobs are insufficient for capturing the complex exposures (e.g., varying frequencies, loads, hand-load couplings) that workers experience daily in MMH. Second, worker force exertion is a key causal factor for MS injuries, and unlike repetition and posture, force exertions are “invisible” such that even trained ergonomists have difficulty assessing without interfering with the workers or the hand-material interfaces. Finally, current tools are not practical at scale for capturing the individual exposures of every worker at every task (e.g., time and labor cost of trained analysts to directly observe or videotape the workers). This proposal aims to address the need for automated systems for predicting workers’ hand, wrist, and forearm injury risk in manual material handling (MMH) tasks. We propose innovative low cost, sensitive, and scalable triboelectric glove system with advanced deep-learning techniques. The proposed tool will be the first all- in-one glove system that can automatically assess all metrics required for the American Conference of Governmental Industrial Hygienists (ACGIH) Threshold Limit Value (TLV) for Hand Activity Level (HAL). Three studies are proposed: 1) material engineering to produce reliable triboelectric sensors at scale, 2) iterative, user-centered design of multi-modal glove sensors for MMH, 2) experiments to train artificial intelligence models for predicting HAL TLV, and 3) demonstration of the technology in real work environments. The expected immediate outcomes of this work will result in a novel system that can impact two critical challenges in managing workplace hand/wrist MSDs: 1) scalable, automated assessment methods that can continuously monitor the high varied MMH tasks and 2) enable practitioners to assess the “invisible” force exertion risk factor that current relies on techniques such as force matching or manually weighing objects. This work aligns with NIOSH’s overall strategic goal of reducing occupational musculoskeletal disorders and have cross-sector impacts, specifically the immediate goal of reducing musculoskeletal disorders with emerging technologies.