Pandu Ranga Vundavilli

Accurate detection of cardboard boxes is essential to mobile manipulators to perform pick-and-place operations in warehouses. Conventional object detection methods like YOLOv11 struggle in low-texture and occluded environments. This paper presents YOLO-REFB, a novel object detection framework for real-time cardboard box detection in robotic manipulation using a dual-arm mobile robot (DAMR) operating in indoor warehouse environments. The proposed approach enhances the network by integrating the Rectangular Edge Fusion Block (REFB) into the YOLOv11 architecture; it focuses on learning the geometric and structural features of cardboard boxes. Enhanced edge information extraction and feature fusion improve training stability and localization accuracy. A custom dataset of 3501 annotated images, collected under varied conditions, was utilized. The images were randomly assigned to training and validation sets while keeping an 80:20 ratio. They were manually annotated and trained using Roboflow software, ensuring precise alignment of bounding boxes with cardboard box edges for accurate comparison with existing YOLO models. The model outperformed existing YOLO variants (YOLOv8n and YOLOv5n) in terms of precision (89.29%), recall (83.95%), and F1-score (86.54%). YOLO-REFB achieved improved localization metrics, including mean Average Precision (mAP)@0.5 (91.68%) and mAP@0.5:0.95 (68.61%). The inclusion of REFB was essential to performance gains, enabling effective detection of objects in challenging environments. Future developments may include 3D pose estimation and multi-object grasp planning for advanced robotic manipulation.

Simultaneous Localization and Mapping (SLAM) is essential for autonomous movement in intelligent robotic systems. Traditional SLAM using a single sensor, such as an Inertial Measurement Unit (IMU), faces challenges including noise and drift. This paper introduces a novel Cartographer-based SLAM approach for DAMR trajectory generation in indoor environments to reduce drift errors and improve localization accuracy. This SLAM approach integrates multi-sensor data with extended Kalman filter (EKF) fusion from wheel odometry, an RGB-D camera (RTAB-Map), and an IMU for precise mapping with DAMR trajectory generation and is compared with the heading reference trajectory generated by robot pose estimation and frame transformation. This system is implemented in the Robot Operating System (ROS 2) for coordinated data acquisition, processing, and visualization. After experimental verification, the DAMR trajectories generated are closer to the reference trajectory and drift errors are tuned. The experimental results revealed that the DAMR trajectory with multi-sensor data integration using the EKF effectively improved the positioning accuracy and robustness of the system. The proposed approach shows improved alignment with the reference trajectory, yielding a mean displacement error of 0.352% and an absolute trajectory error of 0.007 m, highlighting the effectiveness of the fusion approach for accurate indoor robot navigation.

This present study epitomises the fabrication of Cu-15%WC-X%Gr (X = 0, 3, 6, 9, 12) hybrid composites through a microwave sintering process. The synthesised composites were evaluated for hardness and compression strength as per ASTM standards. The composite corresponding to Cu-15%WC-9%Gr shows the optimal compression strength of 395 MPa. Based on this, the composite corresponding to the maximum compression strength was selected for subsequent wear investigations under dry, oil, and SiC nanofluid lubrication conditions. The SiC nanofluids were prepared by dispersing 1 wt% SiC, 1.5 wt% SiC, and 2 wt% SiC nanoparticles in soluble oils. Increasing the nanoparticle content enhanced both the thermal conductivity and zeta potential, indicating an improved heat transfer and dispersion stability. The wear test under different lubricating regimes demonstrates that the lubricating type had a pronounced influence on the wear rate and C.O.F. The minimum rate of wear of 0.0235 mm³/m and C.O.F. of 0.28 were achieved for the 2 wt% SiC nanofluid lubrication. The worn surfaces under dry and oil-lubricated regimes revealed prominent microcracks and delamination wear. In contrast, surfaces tested under nanofluid lubrication exhibited smoother grooves with minimal surface damage and an absence of microcracking.

Microwave fabrication of aluminium composites has emerged as a novel and trending technique in the current industrial landscape due to its efficiency and energy-saving potential. In this study, Al-kaolin composites were fabricated using microwave energy techniques, focusing on predictive modelling of the microwave-assisted Al-kaolin composite’s wear rate and coefficient of friction (COF). The fabricated composites were evaluated for hardness, wear rate, and coefficient of friction (COF) under varying parameters. It was observed that 4 wt% kaolin is the optimal reinforcement fraction, resulting in a 34% improvement in tensile strength, while hardness showed a consistent increase up to 4 wt% Kaolin, reaching a maximum value of 96 RHC. Additionally, wear rate and COF exhibited a decreasing trend with increasing kaolin content, indicating enhanced tribological performance. The lowest wear rate of 3.2 × 10⁻⁴ mm³/Nm and COF of 0.42 were observed for the 4 wt% Kaolin composite, demonstrating improved wear resistance. To further understand and predict the behaviour of the composites, a systematic dataset was collected, and various machine learning (ML) models were trained and tested for predictive modelling of wear rate and COF. Among the trained models, XGBoost demonstrated the highest predictive accuracy, achieving 94.33% for wear rate and 94.62% for COF. A feature importance analysis revealed that the standard of distance (Sod) was the most influential parameter affecting these outputs.

The present work epitomises extracting the graphite (Gr) solid lubricant from the corn stover. The extracted Gr was incorporated as reinforcement in the A356 alloy (Al-7Si), and the effect of the Gr particles on the mechanical and tribological properties was investigated. In spite of this, the input process parameters for the dry sliding wear test at room temperature against the EN31 steel disc were optimised through ANOVA analysis. The fabricated A359—X wt% (X = 0, 2.5, 5, 7.5) composite through bottom pouring stir casting techniques was analysed microstructurally by using XRD and FESEM analysis. The micro Brinell hardness and tensile strength were investigated per ASTME10 and ASTME8M standards. A wear test was performed for the composite pins against the EN31 steel disc according to ASTM G99 specifications. The XRD analysis results depict the presence of carbon (C), aluminium (Al), and silicon (Si) in all the wt% of the Gr reinforcement. However, along with the elements, the Al₂Mg peak was confirmed for the A356—7.5 wt% Gr composite and the corresponding cluster element was confirmed in FESEM analysis. The maximum micro Brinell hardness of 92 BHN and U.T.S of 123 MPa and % elongation of 7.11 was attained at 5 wt% Gr reinforcement due to uniform Gr dispersion in the A356 alloy. Based on the ANOVA analysis, the optimal process parameters were obtained at 20 N applied load, 1 m/s sliding velocity, and 1000 m sliding distance for the optimal wear rate of 0.0052386 g/km and 0.364 COF.

The requirement for high-performance and energy-saving materials motivated the researchers to develop novel composite materials. This investigation focuses on utilizing aluminum alloy (A383) as the matrix material to produce hybrid metal matrix composites (HMMCs) incorporating boron carbide (B₄C) and multi-walled carbon nanotube (MWCNT) through a cost-effective stir casting technique. The synthesis of HMMCs involved varying the weight fractions of B₄C (2%, 4%, and 6%) and MWCNT (0.5%, 1%, and 1.5%). The metallographic study was carried out by field emission scanning electron microscopy (FESEM) mapped with EDS analysis. The results indicated a uniform dispersion and robust interfacial interaction between aluminum and the reinforced particles, significantly enhancing the mechanical properties. Micro-hardness and wear characteristics of the fabricated HMMCs were investigated using Vickers microhardness testing and the pin-on-disc tribometer setup. The disc is made of hardened chromium alloy EN 31 steel of hardness 62 HRC. The applied load was varied as 10N, 20N, 30N with a constant sliding speed of 1.5 m/s for different sliding distances. The micro-hardness value of composites reinforced with 1.5 wt% MWCNT and 6 wt% B₄C improved by 61% compared to the base alloy. Additionally, the wear resistance of the composite material improved with increasing reinforcement content. Incorporating 1.5% CNT and 6% B₄C as reinforcements results in the composite experiencing about a 40% reduction in wear loss compared to the unreinforced aluminum alloy matrix. Furthermore, the volumetric wear loss of the HMMCs was critically analyzed with respect to different applied loads and sliding distances. This research underscores the positive impact of varying the reinforcement content on the mechanical and wear properties of aluminum alloy-based hybrid metal matrix composites.

The requirement and applicability of exoskeletons for rehabilitation has been indicated by the amount of efforts invested in research across the world in the past decades. However, commercial exoskeletons are still expensive and limited by the need for adjusting the structure to the individual user. In this study, the human-exoskeleton interactions are explored by designing a lower limb exoskeleton with ten degrees of freedom: six actuated and four passive. Finite element analysis (FEA) of the structure is carried out to observe that the structural design is able to withstand the operating loads. Furthermore, the model is imported to Opensim software and connected with the human musculoskeletal model at the locations where both bodies would be connected in a real scenario, using braces and straps. The connections between the human and exoskele-ton models are modelled as six degrees of freedom joints with limits. Data of two subjects from an openly available gait data-set is used to carry out kinematic simulations. Comparison of five cases: human without an exoskeleton, human-exoskeleton combined, human-exoskeleton combined with locked hip adduction, human-exoskeleton combined with locked hip rotation, and human-exoskeleton combined with locked hip adduction and rotation, proved that the absence of degrees of freedom from the exoskeleton affects and restricts the motion of joints while trying to execute the same walking movement. The amount of movement at the interfaces is estimated by the simulation results. Therefore, a new approach for simulating humanex-oskeleton combined model is presented here.

The present study investigates the effects of multiple passes of equal channel angular pressing (ECAP) on magnesium alloy sheets with the assistance of an Inconel plunger along with a die setup having a channel angle of 120° and corner angle of 10° operating at a temperature of 200 °C followed by the required heat treatment processes. The microstructural analysis of the sheet samples at various stages of the multi-pass hot ECAP has shown evidence of ultrafine grain refinement (UFG) due to the occurrence of severe plastic deformation. X-ray diffraction analysis has also exhibited the presence of phases like MgZn and CeZn₃ which is supposedly responsible for the enhancement of the mechanical properties. As a result, the room temperature tensile and compressive strengths have improved by 6.12% and 6.63%, respectively, after the second pass, and 11.56% and 15.64%, respectively, after the fourth pass of ECAP. Additionally, the hardness of the sheets has increased by 6.49% and 16.64% after the second and fourth pass of hot ECAP, respectively, mainly attributed to the drastic decrease in grain size from 164 μm to 12 μm within four ECAP passes, all these with a negligible change in ductility. This success in the thermomechanical processing of Mg-RZ5 alloy sheets using a die channel angle of 120° with a minimal number of passes of hot ECAP under a controlled equivalent strain, further opens doors for incorporating optimizations and/or additional aspects so as to achieve even better grain refinements, and consequently, mechanical strength improvements thereby catering to the industrial needs of aerospace and construction areas.

This study focuses on a comparative analysis of mechanical behavior and microstructural characteristics of Cu matrix (C87600) based hybrid composites reinforced with SiC-Gr_p and WC-Gr_p fabricated by the stir casting process. The graphite particle percentage was kept constant, whereas the content of SiC and WC in the respective composites was varied to analyze the mechanical properties of the fabricated composites. The morphological observation was carried out by field emission scanning electron microscope (FESEM), which revealed uniform dispersion of the reinforced particles in the hybrid composites. Clear phases of SiC and WC along with the Cu alloy were identified by the x-ray diffractometer (XRD). Further, a comparative study was conducted to analyze the mechanical behavior of the Cu-SiC-Gr and Cu-WC-Gr hybrid composites. With the addition of the hard ceramic materials, the tensile behavior and microhardness of both the Cu-based MMCs were improved. The WC-Gr reinforced composites exhibited higher mechanical properties than the SiC-Gr reinforced hybrid composites. Further, the fracture surfaces were also characterized to study the tensile behavior of the fabricated copper-based hybrid composites, which shows that ductile fracture was mainly associated with both hybrid composites.

Machinability analyses of metal matrix composites are essential for manufacturing industries. The current study is focused on the mathematical modeling of the machinability of an in-situ synthesized RZ5-8 wt.% TiB₂ composite using the Taguchi design statistical tools and analysis of variance (ANOVA). Taguchi’s method indicates that the feed rate is the most influential parameter, followed by the depth of cut and cutting speed in determining the cutting force and surface roughness during the machining of the RZ5/8 wt.% TiB₂ composite. A regression analysis of the experimental data was carried out using ANOVA, and regression equations were established to estimate cutting force and surface roughness under different parametric conditions. The regression model was validated for other test conditions and the maximum deviation observed was ±10%. Main effects plots and response surface plots were developed to analyze the machining parameters’ individual and combined effects on the RZ5/8 wt.% TiB₂ composite’s machinability. The chip morphology and tool wear of the RZ5/8 wt.% TiB₂ composite were analyzed using FESEM under different machining conditions.