The following research projects are conducted in the Occupational Ergonomics and Biomechanics Laboratory:

A Direct Reading Assessment Instrument for Repetitive Motion Stress

We are investigating if computer vision (i.e. software for processing video recording data) can more effectively evaluate worker exposure and assess the associated risk for work related injuries than conventional methods.  Automated job analysis potentially offers a more objective, accurate, repeatable, and efficient exposure assessment tool than observational analysis. Computer vision uses less resources than instruments attached to workers and does not interfere with production; can quantify more exposure variables and interactions; is suitable for long-term, direct reading exposure assessment; and offers animated data visualizations synchronized with video for identifying aspects of jobs needing interventions. This research leverages data from coordinated multi-institutional prospective studies of upper limb work related musculoskeletal disorders conducted between 2001 and 2010 that studied production and service workers from a variety of US industries, and used rigorous case-criteria and individual-level exposure assessments prospectively, including recording detailed videos of the work, associated exposure variable data, and prospective health outcomes for 1,649 workers. We build on our previous success in developing video marker-less hand motion algorithms for estimating the ACGIH hand activity level, and reliable video processing methods for hand tracking under challenging viewing conditions.  The video extracted exposure measures will be compared against conventional observational exposure measures made by our collaborators. The prospective health outcomes data will be used to develop and validate parsimonious exposure risk models for an automated direct reading repetitive motion instrument. We are testing if automation has better predictive capability than observation and also consider the accuracy and utility of computer vision analysis against conventional job analysis for selected industrial jobs.  

Sponsor: US Department of Health and Human Services, National Institute for Occupational Safety and Health

Development of Automatic Video Risk Analysis of Repetitive Lifting

We are developing computer vision algorithms (i.e. software for processing video recording data) to determine multiple physical risk factors for lower back pain (LBP) associated with manual lifting.  This  research is leveraged by video recordings of various lifting tasks from an National Institute for Occupational Safety and Health (NIOSH) sponsored epidemiologic study that was completed in 2007.  The project is developing and refining video processing computer algorithms for automatically and continuously measuring trunk (i.e. body torso) posture and kinematics including trunk flexion, acceleration and velocity during lifting.  We are testing the accuracy of the LBP risk factors measured by the computer algorithms using video recordings of human subjects performing lifting tasks in a NIOSH laboratory.

Sponsor: US Department of Health and Human Services, National Institute for Occupational Safety and Health

Computer Vision Technology to Automatically Measure, Quantify and Identify Risk for Occupational Back Injuries

Repetitive manual lifting is a significant occupational health and safety concern and is highly prevalent in warehousing, distribution centers, package delivery, transportation, and lean manufacturing. These types of tasks are the most challenging to analyze from an ergonomics perspective. Our laboratory developed a robust, non-intrusive, objective and accurate approach to automatically extract spatial and temporal factors necessary for applying a widely used occupational health and safety risk analysis tool, the revised National Institute for Occupational Safety and Health (NIOSH) lifting equation (RNLE), using a single video camera view of the worker. The subject’s silhouette is segmented by motion information and the novel use of a ghosting effect provides automatic detection of lifting instances, and hand and feet location measurements. This project creates a software prototype of a functioning system for evaluation and early adoption using our computer vision technology for analyzing individual and multi-task manual lifting jobs in various manufacturing facilities involving manual materials handling tasks in production, warehousing and supply chain operations.

Sponsor: State Economic Engagement and Development (SEED) Research Program

Effective Human-Robot Teaming to Advance Aviation Manufacturing

This research aims to transform aviation manufacturing processes that have been resistant to automation due to high variability of operations and reliance on human capabilities, which have become significant productivity bottlenecks and health and safety risks. We improve the efficiency and ergonomics of processes through a flexible human-robot collaboration platform that will provide technicians with intelligent assistance. Shared control/autonomy is studied where the robot performs operations with real-time input from a human operator that augments the input, while improving task ergonomics. We are developing this platform and its applications across a range of manufacturing processes that are central and critical to the aerospace industry in partnership with The Boeing Company.

Sponsor: NASA University Leadership Initiative

Integrating Human-Robot Collaboration in Manual Processes for Enhancing Work Capabilities

Despite the promise of collaborative robots substantially augmenting human capabilities as physical assistants working side-by-side human workers and redefining human work across many industries, the existing principles and methods for work design and automation fail to address fundamental technical challenges in realizing this vision. Rather than displacing human workers, robots can augment human activities and open new employment prospects by creating work that offers greater productivity, better working conditions, and more job satisfaction than manual labor or automation alone. The long-term research goal of the research team is to develop novel principles and tools that enable the use of collaborative robots to augment human cognitive and physical capacities to perform work that would otherwise be inefficient, unhealthy, unsafe, and even impossible. This framework will be applied to occupations in the manufacturing sector to understand the economic, individual, and societal impact of intelligent robotic assistants.

Sponsor: National Science Foundation