A Data-Driven Approach to Predict Hand Positions for Two-Hand Grasps of Industrial Objects

Abstract

The wide spread use of 3D acquisition devices with high-performance processing tools has facilitated rapid generation of digital twin models for large production plants and factories for optimizing work cell layouts and improving human operator effectiveness, safety and ergonomics. Although recent advances in digital simulation tools have enabled users to analyze the workspace using virtual human and environment models, these tools are still highly dependent on user input to configure the simulation environment such as how humans are picking and moving different objects during manufacturing. As a step towards, alleviating user involvement in such analysis, we introduce a data-driven approach for estimating natural grasp point locations on objects that human interact with in industrial applications. Proposed system takes a CAD model as input and outputs a list of candidate natural grasping point locations. We start with generation of a crowdsourced grasping database that consists of CAD models and corresponding grasping point locations that are labeled as natural or not. Next, we employ a Bayesian network classifier to learn a mapping between object geometry and natural grasping locations using a set of geometrical features. Then, for a novel object, we create a list of candidate grasping positions and select a subset of these possible locations as natural grasping contacts using our machine learning model. We evaluate the advantages and limitations of our method by investigating the ergonomics of resulting grasp postures.

A Review of the Roles of Digital Twin in CPS-Based Production Systems

“…The schematic results of this analysis are presented in Table 3, where the papers are confronted with the main aspects emerged from the previous literature on DT. 1) The important connection between the DT concept and the Industry 4.0, mentioned in Section 1, is confirmed also by the considered papers: in fact, only two papers do not mention it [44,47], all the others name the Industry 4.0 [25,28,31] or one of the connected concepts (IoT [29], Smart CPS [30], Smart Product [43]).…”

“…a. Optimization of system behaviour during design phase [30,33,43,46,47]; b. Optimization of product lifecycle, knowing the past and present states, it is possible to predict and optimize the future performances [22,45]. Many of the mentioned uses were targeted at improving maintenance activities, such as condition-based maintenance, diagnostics and prognostics activities.…”

“…I. For most of the authors, the DT is a model that represents the system that different types of simulations can be based upon [19][20][21]25,27,28,31,33,39,[44][45][46][47][48], II.…”

“…In the robotics field, the simulations are mainly performed for the Virtual Commissioning to optimize the control algorithms for robots during development phase [28,44]. In manufacturing, the main objective of simulations are to represent the complex behaviour of the system, also considering the possible sconsequences of external factors, human interactions and design constraints [25,30,47].…”

“…Schroeder sees the DT as composed of different models and data, which are aggregated in an AutomationML model for data exchange [31]. Arisoy mentions that the DT runs on a database with Computer-Aided Design (CAD) models to decide grasping point locations [47].…”