Simulation of passive exotendon assistive device for agricultural harvesting task.

This study proposes and investigates the feasibility of the passive assistive device to assist agricultural harvesting task and reduce the Musculoskeletal Disorder (MSD) risk of harvesters using computational musculoskeletal modelling and simulations. Several passive assistive devices comprised of elastic exotendon, which acts in parallel with different back muscles (rectus abdominis, longissimus, and iliocostalis), were designed and modelled. These passive assistive devices were integrated individually into the musculoskeletal model to provide passive support for the harvesting task. The muscle activation, muscle force, and joint moment were computed with biomechanical simulations for unassisted and assisted motions. The simulation results demonstrated that passive assistive devices reduced muscle activation, muscle force, and joint moment, particularly when the devices were attached to the iliocostalis and rectus abdominis. It was also discovered that assisting the longissimus muscle can alleviate the workload by distributing a portion of it to the rectus abdominis. The findings in this study support the feasibility of adopting passive assistive devices to reduce the MSD risk of the harvesters during agricultural harvesting. These findings can provide valuable insights to the engineers and designers of physical assistive devices on which muscle(s) to assist during agricultural harvesting.

A Deep Learning Framework for Soft Robots with Synthetic Data.

Data-driven methods with deep neural networks demonstrate promising results for accurate modeling in soft robots. However, deep neural network models rely on voluminous data in discovering the complex and nonlinear representations inherent in soft robots. Consequently, while it is not always possible, a substantial amount of effort is required for data acquisition, labeling, and annotation. This article introduces a data-driven learning framework based on synthetic data to circumvent the exhaustive data collection process. More specifically, we propose a novel time series generative adversarial network with a self-attention mechanism, Transformer TimeGAN (TTGAN) to precisely learn the complex dynamics of a soft robot. On top of that, the TTGAN is incorporated with a conditioning network that enables it to produce synthetic data for specific soft robot behaviors. The proposed framework is verified on a widely used pneumatic-based soft gripper as an exemplary experimental setup. Experimental results demonstrate that the TTGAN generates synthetic time series data with realistic soft robot dynamics. Critically, a combination of the synthetic and only partially available original data produces a data-driven model with estimation accuracy comparable to models obtained from using complete original data.

Musculoskeletal modelling and simulation of oil palm fresh fruit bunch harvesting.

Oil palm harvesting is a labor-intensive activity and yet it was rarely investigated. Studies showed that complementing human motion analysis with musculoskeletal modelling and simulation can provide valuable information about the dynamics of the joints and muscles. Therefore, this study aims to be the first to create and evaluate an upper extremity musculoskeletal model of the oil palm harvesting motion and to assess the associated Musculoskeletal Disorder (MSD) risk. Tests were conducted at a Malaysia oil palm plantation. Six Inertial Measurement Units (IMU) and Surface Electromyography (sEMG) were used to collect kinematics of the back, shoulder and elbow joints and to measure the muscle activations of longissimus, multifidus, biceps and triceps. The simulated joint angles and muscle activations were validated against the commercial motion capture tool and sEMG, respectively. The muscle forces, joint moments and activations of rectus abdominis, iliocostalis, external oblique, internal oblique and latissimus dorsi were investigated. Findings showed that the longissimus, iliocostalis and rectus abdominis were the primary muscles relied on during harvesting. The harvesters were exposed to a higher risk of MSD while performing back flexion and back rotation. These findings provide insights into the dynamical behavior of the upper extremity muscles and joints that can potentially be used to derive ways to improve the ergonomics of oil palm harvesting, minimize the MSD risk and to design and develop assistive engineering and technological devices or tools for this activity.

Robust Multimodal Indirect Sensing for Soft Robots Via Neural Network-Aided Filter-Based Estimation.

Sensory data are critical for soft robot perception. However, integrating sensors to soft robots remains challenging due to their inherent softness. An alternative approach is indirect sensing through an estimation scheme, which uses robot dynamics and available measurements to estimate variables that would have been measured by sensors. Nevertheless, developing an adequately effective estimation scheme for soft robots is not straightforward. First, it requires a mathematical model; modeling of soft robots is analytically demanding due to their complex dynamics. Second, it should perform multimodal sensing for both internal and external variables, with minimal sensors, and finally, it must be robust against sensor faults. In this article, we propose a recurrent neural network-based adaptive unscented Kalman filter (RNN-AUKF) architecture to estimate the proprioceptive state and exteroceptive unknown input of a pneumatic-based soft finger. To address the challenge in modeling soft robots, we adopt a data-driven approach using RNNs. Then, we interconnect the AUKF with an unknown input estimator to perform multimodal sensing using a single embedded flex sensor. We also prove mathematically that the estimation error is bounded with respect to sensor degradation (noise and drift). Experimental results show that the RNN-AUKF achieves a better overall performance in terms of accuracy and robustness against the benchmark method. The proposed scheme is also extended to a multifinger soft gripper and is robust against out-of-distribution sensor dynamics. The outcomes of this research have immense potentials in realizing a robust multimodal indirect sensing in soft robots.

Quantification of muscles activations and joints range of motions during oil palm fresh fruit bunch harvesting and loose fruit collection.

Although global demand for palm oil has been increasing, most activities in the oil palm plantations still rely heavily on manual labour, which includes fresh fruit bunch (FFB) harvesting and loose fruit (LF) collection. As a result, harvesters and/or collectors face ergonomic risks resulting in musculoskeletal disorder (MSD) due to awkward, extreme and repetitive posture during their daily work routines. Traditionally, indirect approaches were adopted to assess these risks using a survey or manual visual observations. In this study, a direct measurement approach was performed using Inertial Measurement Units, and surface Electromyography sensors. The instruments were attached to different body parts of the plantation workers to quantify their muscle activities and assess the ergonomics risks during FFB harvesting and LF collection. The results revealed that the workers generally displayed poor and discomfort posture in both activities. Biceps, multifidus and longissimus muscles were found to be heavily used during FFB harvesting. Longissimus, iliocostalis, and multifidus muscles were the most used muscles during LF collection. These findings can be beneficial in the design of various assistive tools which could improve workers' posture, reduce the risk of injury and MSD, and potentially improve their overall productivity and quality of life.