MSMili Shah

Mili Shah

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Mili Shah has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Performance Evaluation of Monocular Markerless Pose Estimation Systems for Industrial Exoskeletons

    by Soocheol Yoon, Ya-Shian Li-Baboud, Ann Virts, Roger Bostelman, Mili Shah, Nishat Ahmed

    Industrial exoskeletons (a.k.a. wearable robots) have been developed to reduce musculoskeletal fatigue and work injuries. Human joint kinematics and human–robot alignment are important measurements in understanding the effects of industrial exoskeletons. Recently, markerless pose estimation systems based on monocular color (red, green, blue—RGB) and depth cameras are being used to estimate human joint positions. This study analyzes the performance of monocular markerless pose estimation systems on human skeletal joint estimation while wearing exoskeletons. Two pose estimation systems producing RGB and depth images from ten viewpoints are evaluated for one subject in 14 industrial poses. The experiment was repeated for three different types of exoskeletons on the same subject. An optical tracking system (OTS) was used as a reference system. The image acceptance rate was 56% for the RGB, 22% for the depth, and 78% for the OTS pose estimation system. The key sources of pose estimation error were the occlusions from the exoskeletons, industrial poses, and viewpoints. The reference system showed decreased performance when the optical markers were occluded by the exoskeleton or when the markers’ position shifted with the exoskeleton. This study performs a systematic comparison of two types of monocular markerless pose estimation systems and an optical tracking system, as well as a proposed metric, based on a tracking quality ratio, to assess whether a skeletal joint estimation would be acceptable for human kinematics analysis in exoskeleton studies.


  • Open Access

    Custom 3D Printed Wrist Brace Featuring a Voronoi Pattern

    by Ayushi Bhattacharjee, Sabrina Zhou, Kayla Lee, Jennifer R Weiser, Mili Shah

  • Continuous mobile manipulator performance measurement data

    by Omar Aboul-Enein, Henry Medeiros, Mili Shah, Ya-Shian Li-Baboud, Roger Bostelman, Ann Virts

    Mobile manipulators, which are robotic systems integrating an automatic or autonomous mobile base with a manipulator, can potentially enhance automation in many industrial and unstructured environments. Namely, large-scale manufacturing processes, typical in the aerospace, energy, transportation, and conformal additive manufacturing fields, encompass a notable subset of potential future mobile manipulator use-cases. Utilizing autonomous mobility for manipulator re-positioning could allow for continuous simultaneous arm and mobile base cooperation, which is referred to as continuous performance. Continuous mobile manipulator capabilities may hold particular benefit for large, curved, and complex workpieces. However, such flexibility can also introduce additional sources of performance uncertainty, preventing mobile manipulators from satisfying stringent pose repeatability and accuracy requirements. To identify and quantify this uncertainty, the Configurable Mobile Manipulator Apparatus was developed by the National Institute of Standards and Technology. Previous test implementations with the apparatus included non-continuous mobile manipulator performance, such as static and indexed performance, but continuous performance measurement had been demonstrated previously only in simulation and on proof-of-concept hardware. The work presented in this report details the transfer of the latest version of simulations and algorithms for continuous registration to an industrial mobile manipulator platform. Additionally, a 2^3 factorial designed experiment was conducted to produce an accompanied continuous mobile manipulator performance dataset. Analysis of the dataset focused on comparing the performance and robustness of two continuous localization methods: 1) a deterministic spiral search and 2) a stochastic Unscented Kalman Filter search across two selected mobile base speeds and sides of the apparatus.