6-DOF Research Articles

Hierarchical robot learning method for industrial fluorescent penetrant inspection

Fluorescent Penetrant Inspection (FPI) is a Non-Destructive Testing (NDT) method, extensively used to evaluate components for identifying defects across a broad range of industries. FPI process remains a manual visual inspection, where the operator by means of fluorescent dye, that penetrates discontinuities on the component, aims to distinguish between indications that are relevant (i.e., can be associated with surface defects) and non-relevant (i.e., can be associated to insufficient wash-off, dust or other non-relevant factors). The FPI process can be decomposed into the following steps: (a) thorough visual examination of the component, (b) executing manual wiping-off of the fluorescent dye with a brush, of all areas that require interrogation for potential indications, and (c) disposition of the inspected components. The number of those areas on the component that require interrogation and hence to be wiped-off is unknown a priori of the inspection and varies depending on the condition of the part. As a result, replacing this manual wipe-off step by a robot requires tedious manual programming of an excessive number of robot paths to assure reach of the robot to the entire surface of the part as well as safe robot motion. In addition, these robot motions are part specific and thus not transferrable to other geometries of components, making scaling of this technology across manufacturing industry not possible. In this paper, we propose a hierarchical robot learning method to address the challenge of reducing manual robot programming and enable the scaling of this automated NDT technology. The proposed method integrates and fuses Deep Reinforcement Learning (DRL), Screw Linear Interpolation (ScLERP) and Learning from Demonstration (LfD), enabling an autonomous generation of brushing strokes with a six-degrees of freedom (DoF) industrial manipulator, and automating the wipe-off step of the FPI process. Using this approach, a robot learning policy is generated for the wipe-off motion in a simulated industrial robotic cell at first and then the policy is transferred to the real system for validation.

A pixel-level grasp detection method based on Efficient Grasp Aware Network

Abstract This work proposes a novel grasp detection method, the Efficient Grasp Aware Network (EGA-Net), for robotic visual grasp detection. Our method obtains semantic information for grasping through feature extraction. It efficiently obtains feature channel weights related to grasping tasks through the constructed ECA-ResNet module, which can smooth the network’s learning. Meanwhile, we use concatenation to obtain low-level features with rich spatial information. Our method inputs an RGB-D image and outputs the grasp poses and their quality score. The EGA-Net is trained and tested on the Cornell and Jacquard datasets, and we achieve 98.9% and 95.8% accuracy, respectively. The proposed method only takes 24 ms for real-time performance to process an RGB-D image. Moreover, our method achieved better results in the comparison experiment. In the real-world grasp experiments, we use a 6-degree of freedom (DOF) UR-5 robotic arm to demonstrate its robust grasping of unseen objects in various scenes. We also demonstrate that our model can successfully grasp different types of objects without any processing in advance. The experiment results validate our model’s exceptional robustness and generalization.

Effects of particle size and reciprocating frequency of the plunger on performance and flow characteristics of a diaphragm pump

ABSTRACT The present study aims to reveal characteristics of the diaphragm pump applied in transporting the mixture of liquid and solid particles. The computational fluid dynamics (CFD) technique was used in combination with the six degree of freedom (SDOF) method to simulate the solid-liquid two-phase flow in the diaphragm pump. The zero-gap overlapping grid technique was employed to treat unsteady gap flows near the two valves. Effects of particle size and the reciprocating frequency of the plunger were investigated. The results indicate that solid particles pass smoothly through the diaphragm pump. When particle size increases from 2.0 mm to 3.0 mm, the solid volume fraction (SVF) in the pump chamber increases. When the reciprocating frequency of the plunger increases from 150 to 250 cycles per minute, the SVF increases and then decreases. When the reciprocating frequency of the plunger increases, the performance of the diaphragm pump declines, whereas the distribution of particles in the pump chamber is gradually uniformized due to the disturbance of the reversed flow from the pump outlet.

Wind-induced creaking noise assessment of 3D full-scale assemblies of drywall system using multi-axis cyclic testing

The lateral wind load applied to high-rise buildings results in movements that can cause creaking noises in drywall partitions with suspended ceiling systems. These noises can be disruptive to the residents and impair the structure’s serviceability. In this study, a sequence of large-scale three-dimensional (3D) experiments was conducted on two assemblies of drywall partitions with a suspended ceiling system to address this serviceability issue. The goal was to explore the 3D response of these assemblies, with a key emphasis on validating the effectiveness of adhesives in mitigating noise introduced by screw fixings, not only for individual walls but also when interacting with neighbouring walls and ceilings, which represent the real-world conditions. The six-degree of freedom (6-DOF) Multi-Axis Substructure Testing (MAST) system at Swinburne University Technology was used to simulate realistic wind load conditions. Two sets of test specimens were constructed using different methods to fix the plasterboard wall lining to the cold-formed steel (CFS) frame, which was rigidly bolted to both the MAST crosshead and the floor below. The first set of specimens (Assembly 1) had the plasterboards screw-fixed to the steel frame, while the second set (Assembly 2) used adhesive-only or a combination of adhesive and screw-fixing methods. Additionally, the instrumentation employed for acoustic measurements was strategically chosen to capture the noise generated by the overall system-level response. This served as a means of validating the serviceability noise experienced by users/occupants. Sound pressure level measurements and an acoustic camera were used simultaneously to identify the noise sources. The creaking noise measurements were compared for different specimens of Assemblies 1 and 2 and the effects of different construction details (e.g. fixing method, plasterboard ceiling lining, etc.) on wind-induced creaking noises were discussed. The results of this study can provide valuable insights for manufacturers and designers to minimize creaking noises in drywall partition systems and propose new construction techniques to improve the serviceability of high-rise buildings.

A heavy-load wall-climbing robot for bridge concrete structures inspection

Purpose The purpose of this paper is to present a wall-climbing robot platform for heavy-load with negative pressure adsorption, which could be equipped with a six-degree of freedom (DOF) collaborative robot (Cobot) and detection device for inspecting the overwater part of concrete bridge towers/piers for large bridges. Design/methodology/approach By analyzing the shortcomings of existing wall-climbing robots in detecting concrete structures, a wall-climbing mobile manipulator (WCMM), which could be compatible with various detection devices, is proposed for detecting the concrete towers/piers of the Hong Kong-Zhuhai-Macao Bridge. The factors affecting the load capacity are obtained by analyzing the antislip and antioverturning conditions of the wall-climbing robot platform on the wall surface. Design strategies for each part of the structure of the wall-climbing robot are provided based on the influencing factors. By deriving the equivalent adsorption force equation, analyzed the influencing factors of equivalent adsorption force and provided schemes that could enhance the load capacity of the wall-climbing robot. Findings The adsorption test verifies the maximum negative pressure that the fan module could provide to the adsorption chamber. The load capacity test verifies it is feasible to achieve the expected bearing requirements of the wall-climbing robot. The motion tests prove that the developed climbing robot vehicle could move freely on the surface of the concrete structure after being equipped with a six-DOF Cobot. Practical implications The development of the heavy-load wall-climbing robot enables the Cobot to be installed and equipped on the wall-climbing robot, forming the WCMM, making them compatible with carrying various devices and expanding the application of the wall-climbing robot. Originality/value A heavy-load wall-climbing robot using negative pressure adsorption has been developed. The wall-climbing robot platform could carry a six-DOF Cobot, making it compatible with various detection devices for the inspection of concrete structures of large bridges. The WCMM could be expanded to detect the concretes with similar structures. The research and development process of the heavy-load wall-climbing robot could inspire the design of other negative-pressure wall-climbing robots.

Investigation of parasitic motion in 3-RRS parallel manipulator

This paper investigates the Parasitic Motion (PaMo) in a 3-Degree of Freedom (DoF) 3-RRS Spatial Parallel Manipulator (SPM) for its different link proportions. The position kinematic analysis of the manipulator is addressed initially. The PaMo is investigated and quantified as the percentage of Reachable Workspace (RW) for each link proportion at the tip of an End-Effector (EE), which is attached at the centroid of the moving platform. The PaMo which happens in the constrained DoF is an unwanted motion, and this entire process allows to know the total occupancy of PaMo in comparison to RW for each link proportion. The results are depicted with the aid of 3D plots of the reachable work-volume and the volume of PaMo for each link proportion. In order to evaluate the performance measure, a performance index called as the parasitic motion index ( PaMoI) is proposed. The PaMoI variation pattern is also discussed based on the obtained results. The conclusions are drawn at the end based on this investigation that also identify the provisions to minimize the PaMo.

Orbit-injection Strategy to a Multistage Launch Vehicle Based on Six-Degree of Freedom and Coupled Axes Attitude Control System

Orbit-injection Strategy to a Multistage Launch Vehicle Based on Six-Degree of Freedom and Coupled Axes Attitude Control System

Aerodynamics and bird ingestion characteristics of a bulge-adjustable turboprop engine inlet

Turboprop aircraft plays an important role in the field of regional airliners and military transport. During take-off or landing, turboprop aircrafts frequently encounter bird flocks that can be ingested into the engine inlet, thereby posing a significant threat to flight safety. Consequently, the aerodynamic characteristics and bird ingestion characteristics of turboprop inlet are investigated in this article. An unsteady computational fluid dynamics (CFD) approach has been proposed to calculate bird ingestion characteristics in a turboprop inlet with different bulge heights under propeller interference by combining a self-developed collision-rebound model with the overset mesh method and 6-degree of freedom (6-DOF) motion method. Considering the characteristics of bird strikes, a parameterized controlled bulge of turboprop inlet with a scavenge duct has been designed. Moreover, the trajectory characteristics of the bird, bird-inlet coupling flowfield characteristics and the aerodynamic characteristics are analyzed in depth. The bulge of the inlet plays a positive role in preventing the bird object from entering the engine duct at a 23° incidence angle. The bird rebounds from the upper bulge and is discharged through the scavenge duct at MaAIP=0.45. The results show that the growth of inlet bulge height has the minimal influence on the total pressure recovery coefficient σ, with only approximately 0.3% variation within the bulge height range of interest. However, it significantly affects the total pressure distortion DC60 with an increase up to 84%.

NN-based reinforcement-learning optimal sliding mode control for drag-free and attitude of spacecraft with state constraints

This paper investigates a tracking control issue for a class of drag-free spacecraft with state constraints caused by the optical assembly. Firstly, a nonlinear kinematics and dynamics relative equation of coupling system of position and attitude is devised by a 6-degree of freedom (DOF) model of rigid body. Secondly, an optimal control method with a terminal functional is designed to meet state constraints. To solve the Hamilton-Jacobi-Bellman (HJB) equation generated by the optimal control of the nonlinear model, a policy iteration ideal is presented and the final numerical solution of the iteration is obtained by a critic neural network (NN). Thirdly, to enhance the robustness of the closed-loop system, an optimal sliding mode control is proposed, which can ensure the optimal and robustness performance simultaneously. At last, the simulation results demonstrate the performance of the proposed methods and the contrast of precision and robustness of two methods are showcased.

Scalp Volumetric Modulated Arc Therapy Using 3D Milled Bolus: Dosimetry, Toxicity and Outcome.

Radiotherapy for scalp lesions is frequently challenging due to the competing needs for target volume coverage, sparing of numerous critical nearby OARs, and reproducible bolus setup despite the irregular and highly convex scalp geometry. Here, we evaluate the use of 3D milled bolus in treating such tumors. A retrospective analysis of scalp patients (pts) treated between 2016-2022 using 3D milled bolus and VMAT. All pts were treated with 6 MV photon beams, IGRT via daily CBCT, and 6-degree of Freedom (6-DOF) couch tops. Pts demographics, tumor characteristics, DVHs, toxicities and outcomes were evaluated. Regional control (RC) defined as control of the disease in the rest of the scalp/neck and local control (LC) defined as disease control within the PTV. A total of 23 pts were identified. Median age 74 (46-85), ECOG performance status was 0-1 in 20 pts (87%) and 92% were males. The histopathologies were squamous cell carcinoma (SCC) (61%), angiosarcoma (AS) (35%) and melanoma (4%). 35% of pts were treated with definitive intent to gross disease; the remaining 65% were treated post-operatively, 22% with microscopically positive margins and 43% with negative margins. 21% had perineural invasion (PNI), and none had lymphovascular invasion (LVI). 78% had T3/T4 and 13% had N+ disease. Median radiation dose was 66 Gy (60-69.96Gy). 44% received concurrent systemic therapy (Paclitaxel 22%, Cemiplimab 12%, Temozolomide 5%, Nivolumab 5%). In 40% of pts, the whole scalp was treated; in the remaining 60%, the median ratio of PTV volume to scalp volume was 35% (25-90%). 22% of pts (n = 5) had neck irradiation for prophylactic (3pts)/ neck lymph node involvement (2 pts). The median brain Dmax was 65 Gy (52.5-71.9), median brain mean dose was 15.4Gy (1.4-38.4), median eye Dmax was 10.9Gy (0.23-49), median cochlea mean was 8.4Gy (0.1-20.4), median lacrimal gland mean dose was 6.8Gy (0.11-38), median hippocampus Dmin was 5.9Gy (0.1-14.9) and Dmax was 10Gy (0.3-23). Most common acute side effects were grade 1-2 fatigue (100%), grade 1-2 pain (78%), grade 1 dysgeusia (22%), grade 1-2 dermatitis (74%). The only grade > = 3 adverse event was grade 3 dermatitis in 26%. Regarding long-term side effects, one pt had grade 2 osteoradionecrosis and other one developed grade 2 skin ulcer. 17% developed grade 1 memory impairment. 17% had grade 1 eye dryness. None developed brain radionecrosis. At a median follow-up was 14.4 months (1-73.5), the 1-yr LC was 96%. The 1-yr RC was 75% overall, 100% in angiosarcoma vs 62% in SCC (p = 0.18). Of the 4 regional recurrences, 1 pt had marginal recurrence along V1, 2 had neck nodal recurrence, and 1 had recurrence elsewhere in the scalp. 1-yr DMFS was 62% overall. 1-yr OS was 78% overall, 100% for AS vs 64% for SCC (P = 0.097). VMAT planning with 3D milled bolus permits technically sound radiotherapy for scalp targets with an acceptable toxicity profile and relatively favorable clinical outcomes. This approach warrants further evaluation in a larger prospective study.

Comparison of 3-[PP]S-Y Spatial Parallel Manipulators based on link tolerances and parasitic motions

This paper strives to compare between two 3-Degree of Freedom (DoF) Spatial Parallel Manipulators (SPMs) belonging to the 3-[PP]S-Y family viz., 3-RRS and 3-RPS. The planes of the manipulators belong to this family are arranged in a Y-pattern such that they intersect at 120° in a common line. Both of these manipulators have a common motion of 1T2R (T: Translation, R: Rotation) type, and their comparison in this work is carried out by considering the effects of link tolerance and parasitic motions, for the same task space and End-Effector (EE) positions. Their respective position kinematic analysis is discussed initially. The comparison is then carried out by considering two different cases based on the sizes of the moving platform relative to the base platform. The errors are quantified and all the comparative results are represented with the aid of plots. The conclusions are summarized at the end that allow to know the better of the two manipulators for the given effects.

SDV-LOAM: Semi-Direct Visual-LiDAR Odometry and Mapping.

Visual-LiDAR odometry and mapping (V-LOAM), which fuses complementary information of a camera and a LiDAR, is an attractive solution for accurate and robust pose estimation and mapping. However, existing systems could suffer nontrivial tracking errors arising from 1) association between 3D LiDAR points and sparse 2D features (i.e., 3D-2D depth association) and 2) obvious drifts in the vertical direction in the 6-degree of freedom (DOF) sweep-to-map optimization. In this paper, we present SDV-LOAM which incorporates a semi-direct visual odometry and an adaptive sweep-to-map LiDAR odometry to effectively avoid the above-mentioned errors and in turn achieve high tracking accuracy. The visual module of our SDV-LOAM directly extracts high-gradient pixels where 3D LiDAR points project on for tracking. To avoid the problem of large scale difference between matching frames in the VO, we design a novel point matching with propagation method to propagate points of a host frame to an intermediate keyframe which is closer to the current frame to reduce scale differences. To reduce the pose estimation drifts in the vertical direction, our LiDAR module employs an adaptive sweep-to-map optimization method which automatically choose to optimize 3 horizontal DOF or 6 full DOF pose according to the richness of geometric constraints in the vertical direction. In addition, we propose a novel sweep reconstruction method which can increase the input frequency of LiDAR point clouds to the same frequency as the camera images, and in turn yield a high frequency output of the LiDAR odometry in theory. Experimental results demonstrate that our SDV-LOAM ranks 8th on the KITTI odometry benchmark which outperforms most LiDAR/visual-LiDAR odometry systems. In addition, our visual module outperforms state-of-the-art visual odometry and our adaptive sweep-to-map optimization can improve the performance of several existing open-sourced LiDAR odometry systems. Moreover, we demonstrate our SDV-LOAM on a custom-built hardware platform in large-scale environments which achieves both a high accuracy and output frequency. We have released the source code of our SDV-LOAM for the development of the community.

Modeling and structural optimization design of switched reluctance motor based on fusing attention mechanism and CNN-BiLSTM

Six-degrees of freedom (6-DOF) parallel mechanisms driven by switched reluctance motors (SRMs) can realize flexible control with high precision. Efficiency is an important indicator to measure the speed control system of SRMs. There are many characteristic factors affecting efficiency and strong nonlinear relationships between different characteristic parameters, which makes it difficult for analytical models and traditional neural network models to express their spatial correlation. For this reason, a convolutional neural network (CNN)-bidirectional long short-term memory network (BiLSTM) efficiency regression prediction model (CNN-BiLSTM-SENet) that integrates the attention mechanism (SENet) is proposed. Firstly, customize a formula for sensitivity analysis to screen characteristic parameters of efficiency. Secondly, build the CNN-BiLSTM-SENet model and use sparrow search algorithm (SSA) for hyperparameter optimization, input data to CNN to extract high-dimensional feature vectors that reflect complex changing relationships between features and efficiency while establishing feature channels. Embed the SENet to adaptively perceive and assign different weights to the feature channels, enhancing the influence of key features. Input the feature vectors outputted by the front-end network to BiLSTM to bidirectionally learn coupling relationships between sequences and complete regression prediction. Finally, propose improved northern goshawk optimization (MNGO) to solve the regression model to obtain the maximum efficiency and corresponding characteristic parameters. The results proved that the SSA-optimized CNN-BiLSTM-SENet model has higher fitting exactness and better prediction effect for efficiency regression prediction, and the MNGO also has stronger search ability and faster convergence.

Six-DOF modular robotic arm bearing chatter suppression algorithm

Robotic arms are frequently utilized in contemporary industrial production since they offer great qualities like high precision and low mass. How to minimize robotic arm tremors in order to maximize their control effect has emerged as one of the most critical issues to be resolved with the continued development of industrial intelligence. The study uses a combination of PID control and an artificial fish swarm technique to optimize the parameters and confirm the simulation control effect based on the kinematic analysis of a six-degree-of-freedom (Six-DOF) modular robotic arm. The findings demonstrated that the suggested fusion approach converges to zero in 80 iterations and has a recall of 0.893 and 0.785 at an accuracy of 0.8 and 0.9, respectively. The robotic arm control system’s average control effect is 42.96 %, which is a respectable control performance. In the second and third studies, the fusion approach stabilized actuator end tremor suppression after 0.01 s and 0.0001 s, respectively. It shows that the technique can effectively suppress robotic arm bearing tremor and has high flexibility for robotic arm tremor suppression, which offers trustworthy technological support for improving the motion control system of industrial robots.

Hybrid Visual-Ranging Servoing for Positioning Based on Image and Measurement Features.

In this article, a hybrid visual-ranging servoing method is proposed to realize high-precision positioning tasks with a 6-degree of freedom (DOF) manipulator. This method utilizes the image and measurement features directly in the control loop. Without the need of complex image feature design and attitude estimation, this method realizes the 6-DOF control of a robot. A vital challenge in traditional vision-based systems is avoiding local minima and singularity problems. To tackle this issue, a full-rank interaction matrix hybrid visual servo (FRHVS) design criterion is proposed, which guarantees that the hybrid interaction matrix and its pseudoinverse matrix are both full rank. Moreover, the interaction matrix for these hybrid strategies, which combines image features with other sensors features, is derived in an analytical form. Experiments on a 6-DOF manipulator show that the proposed method is effective and has global asymptotic stability and high precision.

Early Postoperative Activities of Daily Living Do Not Adversely Affect Joint Torques or Translation Regardless of Capsular Condition: A Cadaveric Study

To evaluate the impact of capsular management on joint constraint and femoral head translations during simulated activities of daily living (ADL). Using 6 (n= 6) cadaveric hip specimens, the effect of capsulotomies and repair was then evaluated during simulated ADL. Joint forces and rotational kinematics associated with gait and sitting, adopted from telemeterized implant studies, were applied to the hip using a 6-degrees of freedom (DOF) joint motion simulator. Testing occurred after creation of portals, interportal capsulotomy (IPC), IPC repair, T-capsulotomy (T-Cap), partial T-Cap repair, and full T-Cap repair. The anterior-posterior (AP), medial-lateral (ML), and axial compression DOFs were operated in force control, whereas flexion-extension, adduction-abduction, and internal-external rotation were manipulated in displacement control. Resulting femoral head translations and joint reaction torques were recorded and evaluated. Subsequently, the mean-centered range of femoral head displacements and peak signed joint restraint torques were calculated and compared. During simulated gait and sitting, the mean range of AP femoral head displacements with respect to intact exceeded 1% of the femoral head diameter after creating portals, T-Caps, and partial T-Cap repair (Wilcoxon signed rank P < .05); the mean ranges of ML displacements did not. Deviations in femoral head kinematics varied by capsule stage but were never very large. No consistent trends with respect to alterations in peak joint restrain torques were observed. In this cadaveric biomechanical study, capsulotomy and repair minimally affected resultant femoral head translation and joint torques during simulated ADLs. The tested ADLs appear safe to perform after surgery, regardless of capsular status, because adverse kinematics were not observed. However, further study is required to determine the importance of capsular repair beyond time-zero biomechanics and the resultant effect on patient-reported outcomes.

3D human hands rendering by a six degrees of freedom collaborative robot and a single 2D camera

Human hands are essential in everyday tasks, mainly manipulating and grasping objects. Thus, accurate and precise three-dimensional (3D) models of digitally reconstructed hands are valuable to the world of ergonomics. A 3D scan-to-render system called the “3D hands model rendering using a 6-degrees of freedom (DoF) collaborative robot” is proposed to ensure that a person receives the best possible outcome for their unique anatomy. The description implies this is using a 6-DoF robot with a two-dimensional (2D) camera sensor that will encompass all forms of the production line in a timely, low-cost, precise, and accurate manner so that an individual can go to and scan their hand and have an actual 3D reconstruction print within the same facility, the same day. It is expected to generate an accurate hand model using structure from motion (SFM) system techniques to create a dense point cloud using photogrammetry. The point cloud is used to develop the tetrahedral mesh of the surface of the hand. This mesh is then refined to filter out the noise of the point cloud. The mesh can produce a precise 3D model that can tailor products to the consumer's needs. The results show the effectiveness of the 3D model of the hand.

Influence of cavitation state and launch angle on water-exit process of vehicle based on moving domain method

This paper, aiming at the water-exit process of the vehicle with cavitation, based on the moving domain method coupled with the SDOF (six degrees of freedom) solver, using VOF (volume of fluid) multiphase model and the Schnerr-Sauer cavitation model, carrying out numerical simulation research on multi-conditions. Comparing vertical launch vehicles with different water-exit Ca (cavitation number) cases, the sudden decrease in cavitation number is closely related to the cavitation state, and there is a maximum influent cavitation state of the cavitation collapse on the process of the water-exit. Comparing different initial launch angle cases, it is found that there is a most unstable launch angle, which makes the angular deflection of the vehicle the most severe during the water-exit process.

Dynamic modeling and vibration control of barge offshore wind turbine using tuned liquid column damper in floating platform

This study investigated the vibration suppression of a barge-type floating offshore wind turbine (FOWT) using a passive tuned liquid damper (TLCD) in the floating platform. The fully coupled aero-hydro–servo-elastic model was established using OpenFAST, and it was used to evaluate the suppression performance of the TLCD in the time and frequency domains. To optimally design the TLCD parameters, a 3-degree of freedom (DOF) model was proposed based on the Lagrange equation for a barge-type FOWT with a platform TLCD, which accounts for the DOF of platform pitching, tower bending in the fore–aft direction, and vertical-liquid column motion of TLCD. The unknown parameters of the 3-DOF model were estimated and validated to ensure result accuracy. The exhaustive search method was implemented to obtain the optimized TLCD parameters of the barge-type FOWT, and the simulation results showed that TLCD can effectively mitigate the structural vibration of barge-type FOWT. When applying a large TLCD mass to the barge platform for structural vibration control, replacing part of the ballast with a TLCD of equal mass to maintain the overall mass of the barge-type FOWT was prioritized.

Conceptual design and simulation study of an autonomous indoor medical waste collection robot

Solid waste management is one of the critical challenges seen everywhere, and the coronavirus disease (COVID-19) pandemic has only worsened the problems in the safe disposal of infectious waste. This paper outlines a design for a mobile robot that will intelligently identify, grasp, and collect a group of medical waste items using a six-degree of freedom (DoF) arm, You Only Look Once (YOLO) neural network, and a grasping algorithm. Various designs are generated before running simulations on the selected virtual model using Robot Operating System (ROS) and Gazebo simulator. A lidar sensor is also used to map the robot's surroundings and navigate autonomously. The robot has good scope for waste collection in medical facilities, where it can help create a safer environment.