Grid Map Research Articles

Novel reconstruction technique of omnipolar signals in high density electrode arrays

Abstract Funding Acknowledgements Type of funding sources: Public grant(s) – EU funding. Main funding source(s): National Research Program, Ministerio de Ciencia e Innovación, Spanish Government; Instituto de Salud Carlos III. Background Novel multi-electrode array catheters with equidistant spacing between the electrodes, have emerged in recent years - e.g. Advisor™ HD Grid Mapping Catheter, Sensor Enabled™ (SE). These systems typically use unipolar signals, sensitive to low-frequency noise, and bipolar signals - highly dependent on the direction of propagation. Thus, the full potential of these new devices is not yet fully exploited. We hypothesise that, a new clique (4-electrode in a squared 2x2 matrix) configuration for the computation of omnipolar signals allows to take full advantage of novel multi-electrode catheters, more robust to the direction of propagation of the wavefront against the one currently proposed in literature – thus helpful in the clinic given the challenging positioning of the catheter in the heart cavity during electrophysiologic studies. Methods In the current 3-electrode clique, the centre of the signal obtained does not correspond to the centre of the area of the clique, being less robust to wavefront propagation direction (see fig. 1A). A new configuration, the cross clique, is proposed for calculating the electrogram to improve the robustness and reduce the errors in the estimation local activation time (LAT) and others – see figure 1. One thousand simulated signals with stratified propagation angles and variable parameters were implemented to emulate flat waves and homogeneous propagation over cardiac tissue. The methods used to calculate the signal with the proposed shape are: obtaining the bipoles, 45 degree correction of the signal, detection of the propagation angle, rotation of the detected angle and estimation of the LAT. Results The average amplitude of the bipolar loop increased from the old triangular clique configuration: 600.36 ± 116.40 mV; to the novel one cross-clique: 840.47 ± 160.09 mV. Regarding the local activation time estimation, a decrease in the error is observed from the current omnipolar reconstruction: 207.50 ± 256.91 μs, to the one proposed 22.75 ± 29.426 μs. When the bEGM propagation angle estimation is activated, the angle estimation error is 2.77 ± 25.26o for the current reconstruction method, in contrast to 1.09 ± 11.35o in the proposed one – see figure 1B. Conclusion Our novel configuration considerably reduces the LAT estimation error and, on average, captures a larger signal amplitude than the classic triangular clique method. Thus, it allows using the full potential of new catheters, improving the omnipolar analysis. hen applying automatic angle detection to the methods, in the case of the traditional method, it is influenced by the desynchronisation of the components of the traditional model as it widens the bipolar EGM loop – see figure 1.B. Thus, a novel omnipolar reconstruction method is proposed to better estimate intracardiac EGMs, more robustly against the direction of the wavefront propagation. Further studies are under consideration with clinical signals.

A Novel Algorithm for Ship Route Planning Considering Motion Characteristics and ENC Vector Maps

Global route planning is a pivotal function of unmanned surface vehicles (USVs). For ships, the safety of navigation is the priority. This paper presents the VK-RRT* algorithm as a way of designing the planned route automatically. Different from other algorithms or studies, this study employs electronic navigation chart (ENC) vector data instead of grid maps as the basis of the search, which reduces data error when converting the vector map into the grid map. In addition, Delaunay triangulation is employed to organize vector data, in which the depth value is taken as a factor to ensure the safety of the planning route. Furthermore, the initial planned route is not suitable for ship tracking as it does not consider the ship motion characteristics. Therefore, the planned route needs to be further optimized. In the final part, we also conducted experiments to verify the effectiveness and advantages of the proposed algorithm. The results show that the proposed algorithm could reduce the lengths of paths by about 23% on average and save planning time; these are largely dependent on the environment.

Path Planning Algorithm for a Wheel-Legged Robot Based on the Theta* and Timed Elastic Band Algorithms

Aimed at the difficulty of path planning resulting from the variable configuration of the wheel-legged robot for future deep space explorations, this paper proposes a path planning algorithm based on the Theta* algorithm and Timed Elastic Band (TEB) algorithm. Firstly, the structure of the wheel-legged robot is briefly introduced, and the workspace of a single leg is analyzed. Secondly, a method to judge complete obstacles and incomplete obstacles according to the height of the obstacles is proposed alongside a method to search for virtual obstacles, to generate a grid map of the wheel and a grid map of the body, respectively. By dividing obstacles into complete obstacles and incomplete obstacles, the path planning of the wheel-legged robot is split into the planning of the body path and the planning of the wheel path. The body can be still simplified as a point by searching for the virtual obstacle, which avoids the difficulty of a planning path of a variable shape. Then, we proposed hierarchical planning and multiple optimization algorithms for the body path and wheel path based on the Theta* algorithm and TEB algorithm. The path can be optimized and smoothed effectively to obtain a shorter length and higher safety. On that basis, the proposed algorithm is simulated by Matlab. The results of simulations show that the algorithm proposed in this paper can effectively plan the path of the wheel-legged robot by using variable configurations for different types of obstacles. The path-planning algorithm of the wheel-legged robot proposed in this paper has a broad prospect for deep space exploration.

A Comparison of Multiple Odor Source Localization Algorithms

There are two primary algorithms for autonomous multiple odor source localization (MOSL) in an environment with turbulent fluid flow: Independent Posteriors (IP) and Dempster–Shafer (DS) theory algorithms. Both of these algorithms use a form of occupancy grid mapping to map the probability that a given location is a source. They have potential applications to assist in locating emitting sources using mobile point sensors. However, the performance and limitations of these two algorithms is currently unknown, and a better understanding of their effectiveness under various conditions is required prior to application. To address this knowledge gap, we tested the response of both algorithms to different environmental and odor search parameters. The localization performance of the algorithms was measured using the earth mover’s distance. Results indicate that the IP algorithm outperformed the DS theory algorithm by minimizing source attribution in locations where there were no sources, while correctly identifying source locations. The DS theory algorithm also identified actual sources correctly but incorrectly attributed emissions to many locations where there were no sources. These results suggest that the IP algorithm offers a more appropriate approach for solving the MOSL problem in environments with turbulent fluid flow.

Dynamic Parallel Mapping and Trajectory Planning of Robot Arm in Unknown Environment

A high real-time robot arm mapping and dynamic shortest path planning algorithm is proposed, which is used for low-cost depth cameras and robot arms. First of all, an inverse kinematics solution algorithm for a non-spherical wrist joint is proposed for the Kinova Mico2 manipulator. Based on the idea of position and attitude decoupling combined with the numerical solution, the solution of multiple sets of inverse kinematics is acquired. Secondly, a hand-eye system is established on the basis of the depth camera-RealSense. The point cloud is inversely solved through the depth map, which is pre-processed by the pass-through filtering and outlier removal algorithm. A scene parallel mapping method is designed to achieve the real-time reconstruction of the working scene for the robot arm, in which the maintenance of map and large matrix operations can be completed by GPU. Thirdly, a path planning algorithm with the shortest path for the manipulator end in Cartesian space is designed based on D* method and grid map. The attitude interpolation and smoothing are performed on the path points to obtain the executable joint trajectories on the time axis. Finally, the ROS system is used to build a simulation test verification environment, and the effectiveness of the related algorithms is verified through multiple simulation cases.

Sea surface height data reconstruction via inter and intra layer features based on dual attention

Understanding of geoscience relies on spatio-temporal continuous fields, such as Sea Surface Height (SSH). Data reconstruction for restoring spatio-temporal continuous and gridded maps from incomplete observations and inaccuracy interpolation products has long been a crucial challenge in the marine geoscience. Despite remarkable progress, most existing learning-based reconstruction methods neglect to fully and discriminatively utilize the inter-layer and intra-layer features. The inter-layer semantics are complementary, and the significance of intra-layer components varies with frequency. To address these issues, we propose a multi-layer Feature Combination Network based on Attention mechanism (FCANet) for SSH data reconstruction. Specifically, a novel trainable Multi-layer Feature Combination Block (MFCB) is developed to enrich the features through inter-layer dependencies. Dual attention mechanism is introduced into the MFCB to enhance saliency of intra-layer features by adaptively rescaling the spatial-wise and channel-wise features. Furthermore, experimental results on SSH variable demonstrate the superiority of our FCANet over state-of-the-art reconstruction methods in the metrics of RMSE and SSIM.

Occupancy Grid Mapping via Resource-Constrained Robotic Swarms: A Collaborative Exploration Strategy

This paper addresses the problem of building an occupancy grid map of an unknown environment using a swarm comprising resource-constrained robots, i.e., robots with limited exteroceptive and inter-robot sensing capabilities. Past approaches have, commonly, used random-motion models to disperse the swarm and explore the environment randomly, which do not necessarily consider prior information already contained in the map. Herein, we present a collaborative, effective exploration strategy that directs the swarm toward ‘promising’ frontiers by dividing the swarm into two teams: landmark robots and mapper robots, respectively. The former direct the latter, toward promising frontiers, to collect proximity measurements to be incorporated into the map. The positions of the landmark robots are optimized to maximize new information added to the map while also adhering to connectivity constraints. The proposed strategy is novel as it decouples the problem of directing the resource-constrained swarm from the problem of mapping to build an occupancy grid map. The performance of the proposed strategy was validated through extensive simulated experiments.

New data on the morphological and anatomical structure, chemical composition and distribution area of a rare species <em>Komarovia anisosperma</em> in Uzbekistan

For the first time, the morphological and anatomical structure of vegetative and generative organs, the localization of secretory ducts in the underground and aboveground parts of the species plants were studied. New GIS technologies were used to elucidate the spatial structure of the rare endemic species Komarovia anisosperma of the monotypic genus Komarovia Korovin of the Apiaceae family. The performed analysis showed the most significant diagnostic features of the studied organs, such as a deep taproot system, the presence of a multi-branched caudex, underdeveloped stem leaves or stem leaves reduced to sheaths, the central cylinder of the main root showing separate concentric circles of large and small vascular bundles, the presence of numerous secretory ducts in the secondary root cortex, strongly elongated palisade leaf cells etc. As a result of phytochemical study, extracts of Komarovia anisosperma roots and inflorescences were analyzed. According to our data, the main component of underground organs from terpenes was α-muurolene, and for inflorescences it was α-curcumene. Grid mapping showed that the species is mainly concentrated in the Samarkand and Kashkadarya regions, where the most favorable conditions for its growth are found. These areas are the natural area of origin of the species, and the establishment of a protected natural area has led to an increase in the number of natural populations.

PO-02-205 ELECTROGRAPHIC FLOW CONSISTENCY CORRELATES WITH HIGH-DENSITY BIPOLAR VOLTAGE MAPS IN SINUS RHYTHM AND ATRIAL FIBRILLATION

In patients with atrial fibrillation (AF), left atrial scar revealed by low voltage areas on 3D electroanatomic mapping have been correlated with scar on late gadolinium enhanced cardiac magnetic resonance imaging, which is recognized as a surrogate for fibrosis. Electrographic Flow (EGF) mapping reconstructs global atrial wavefront propagations in near real-time. Electrographic flow consistency (EGFC) quantifies concordance of observed wavefront patterns and may provide insight into the nature of atrial substrate where diseased substrate shows more chaotic wavefront propagation and lower FC. Correlate EGFC with regional bipolar voltage values in patients during AF and sinus rhythm (SR). FLOW EVAL-AF is a single-center, prospective study of 10 AF patients who underwent concomitant high-density bipolar voltage mapping with HD Grid and EGF mapping with 64-pole basket catheter. Biatrial voltage maps and 1-minute EGF maps from 2-3 standard basket positions per atria were made prior to any induction or ablation. Atrial surface area with voltage >0.5 mV was computed from 2D voltage map projections. EGF fields computed per 2-sec segment of recording. Overall EGFC per atrium computed as average of the modulus of individual EGF vectors, where vector length represents consistency of flow patterns in arbitrary units. We compared % atrial surface area with normal voltage v. mean EGFC across EGF recordings per atria in a given rhythm. Data from 8 patients (2 AF; 6 SR) was analyzed; 2 excluded for non-comparable voltage map acquisition parameters. Mean age 70±11 years; 1 female; mean LA size 4.5±0.35 cm. Surface area % with voltage >0.5 mV was 0.24±0.08 in AF v. 0.36±0.05 in SR. Mean EGFC in AF 0.74±0.14 and in SR 1.0±0.11. Intraprocedural rhythm change occurred in 5 (3 induced into AF; 2 converted to SR post-PVI), and all had higher voltage values overall and higher mean EGFC in SR v. AF. Pooling data from all pre-procedure voltage maps and EGF maps revealed overall correlation between EGFC and bipolar voltage from both atria and in both rhythms (r=0.67, p=4.8x10-3). Both EGFC and bipolar voltage values were higher in SR v. AF. EGFC correlated with voltage across both atria and in both SR and AF. Global EGFC can be obtained with 1-minute recordings in 2-3 basket positions per atria and may provide another measure of the degree of atrial myopathy similar to the information gained from high-density bipolar voltage mapping.

PO-04-134 STAR MAPPING METHOD TO IDENTIFY ENDO-EPICARDIAL DISSOCIATION AND DRIVING SITES IN PERSISTENT ATRIAL FIBRILLATION

Recurrence rates following ablation for persistent AF (psAF) remain high with the underlying mechanisms complex and poorly understood. Asynchronous activation of the endocardial and epicardial surfaces during AF, defined as endo-epicardial dissociation (EED) may be a driver for AF. We aim to investigate whether using the novel vector mapping approach, Stochastic Trajectory Analysis of Ranked (STAR) signals, endo- epicardial dissociation and early sites of activation (ESA) can be identified. Six (6) patients underwent endo-epicardial AF ablation utilizing the pericardial percutaneous CO2 insufflation technique. Two AdvisorTM HD Grid mapping catheters were placed in corresponding endocardial and epicardial positions in the left atrium. During AF, 30 second segments were recorded at the base of the left atrial appendage, anterior, inferior, left lateral and posterior LA wall. Fifteen (15) corresponding endo-epicardial segments were analysed using STAR maps and assessed for ESA and variation in direction of activation wavefront between the endocardium and epicardium. Activation wavefront direction was defined as dissociated if there was >40-degree difference between activation direction of simultaneous endo-epicardial wavefronts on STAR mapping. For each 30 second recording if there was more than 1 dominant wavefront direction, the 2 most common were used and an average taken. The overall mean difference in angulation of wavefront between the endocardium and epicardium was 71 ± 55 degrees. Nine (9) of 15 STAR maps (53%) showed activation angulation difference of >40 degrees between the endocardial and epicardial wavefront activation. Of these 9, 3 were on the posterior wall, 3 were at the base of the appendage, 2 were on the left lateral wall and 1 was on the anterior wall. ESA was identified in 6 STAR mapped endo and epicardial segments of AF, with 4 of these 6 (67%) ESAs in the epicardium. STAR mapping identifies activation wavefront discrepancy showing EED in multiple sites of the atrium with the majority of ESAs in the epicardial atrial surface.

Role of localized repolarization and conduction heterogeneities in ventricular arrhythmias and sudden cardiac death

Recent clinical studies have indicated the presence of localized tissue abnormalities in sudden cardiac death (SCD) survivors without apparent structural heart disease, including idiopathic ventricular fibrillation (VF) and J-wave Syndromes. The origin of these abnormalities, showing distinct electrical features on contact mapping, and mechanisms of associated arrhythmias are still a matter of debate. To determine the respective role of localized repolarization and conduction heterogeneities in vulnerability to arrhythmias and SCD, and to characterize their specific electrical signatures. Optical mapping was performed on porcine right ventricular models of either local (i) repolarization shortening, (ii) conduction slowing, or (iii) micro-structural heterogeneity which were created by locally perfusing (i) pinacidil (20 μM n = 13) or (ii) flecainide (2 μM n = 13) via an epicardial catheter (branch of right coronary artery), or (iii) by local epicardial tissue destruction through radiofrequency application (9 micro lesions 30W 1 sec n = 13). Pseudo-ECG were assessed and the number of induced and spontaneous arrhythmias were quantified and mapped in each preparation. An HD grid mapping catheter was used to record bipolar electrograms (n = 5 in each group). Electrograms were normal in model (i), but showed local fragmentation in 40% of preparations in model (ii) with greater effects observed at high pacing frequencies (3 Hz). In model (iii), the structural substrate alone increased the width and number of peaks in the electrograms, and addition of flecainide (2 μM) in this model induced pronounced fragmentation (≥ 3 peaks and ≥ 70ms duration) in 100% of the cases. Arrhythmogenicity was significantly increased in models (i) and (ii) which presented 82% and 45% more spontaneous arrhythmias (P < 0.0001 and 0.05 vs. baseline) and a reduced pacing frequency threshold to induce arrhythmias (−69% and −50%, P < 0.001 vs. baseline). In these models, the frequency of spontaneous activity was increased (+411% P < 0.01 and +181% P < 0.05 vs. baseline) and originated near the heterogeneous area. Microstructural substrates have the most pronounced impact on electrograms, especially when combined with sodium channel blockers, while repolarization heterogeneities do not lead to electrogram fragmentation but are associated with the highest prevalence of spontaneous arrhythmias. Both heterogeneities show increased ectopic activity.

A Lidar SLAM based on Improved Particle Filter and Scan Matching for Unmanned Delivery Robot

With the rapid development of robotics, intelligent robots have gradually entered human daily life and take responsibility for specific tasks, which brings tremendous convenience to people’s lives. In indoor places such as restaurants, hotels, logistics warehouses, SLAM technology can guide mobile robots to complete delivery tasks. Aiming at solving the problems of particle degradation in the traditional RBPF-based two-dimensional SLAM algorithm, our algorithm firstly proposes an improved particle filter method based on cross-mutation, which changes the information of the small weight particles in the system by designing cross-mutation operators. Thus, a certain amount of small weight particles are retained in the system to increase the diversity of particles. Secondly, our algorithm proposes a scan matching method based on point and line features, which makes full use of the geometric information of the two-dimensional point cloud by designing a new error function. Compared with traditional matching methods that only rely on point features, it has better matching accuracy. We conduct Two-dimensional SLAM experiments in the Gazebo simulation environment and the real natural environment. The results show that the proposed algorithm has higher mapping accuracy than the commonly used two-dimensional SLAM algorithm Gmapping at this stage. Using improved A* algorithm to conduct path planning experiments on the two-dimensional grid map built with our algorithm, the results prove the effectiveness of our algorithm.

CLONeR: Camera-Lidar Fusion for Occupancy Grid-Aided Neural Representations

Recent advances in neural radiance fields (NeRFs) achieve state-of-the-art novel view synthesis and facilitate dense estimation of scene properties. However, NeRFs often fail for outdoor, unbounded scenes that are captured under very sparse views with the scene content concentrated far away from the camera, as is typical for field robotics applications. In particular, NeRF-style algorithms perform poorly: (1) when there are insufficient views with little pose diversity, (2) when scenes contain saturation and shadows, and (3) when finely sampling large unbounded scenes with fine structures becomes computationally intensive. This paper proposes <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CLONeR</i> , which significantly improves upon NeRF by allowing it to model large unbounded outdoor driving scenes that are observed from sparse input sensor views. This is achieved by decoupling occupancy and color learning within the NeRF framework into separate Multi-Layer Perceptrons (MLPs) trained using LiDAR and camera data, respectively. In addition, this paper proposes a novel method to build differentiable 3D Occupancy Grid Maps (OGM) alongside the NeRF model, and leverage this occupancy grid for improved sampling of points along a ray for volumetric rendering in metric space. Through extensive quantitative and qualitative experiments on scenes from the KITTI dataset, this paper demonstrates that the proposed method outperforms state-of-the-art NeRF models on both novel view synthesis and dense depth prediction tasks when trained on sparse input data.

PO-04-038 ULTRA HIGH DENSITY MAPPING TO IDENTIFY MICRO-REENTRANT LEFT ATRIAL FLUTTER CIRCUITS WITHIN LOW BIPOLAR VOLTAGE REGIONS: A CASE SERIES

Micro-reentrant (MR) atrial flutter (AFL) circuits may not be evident with standard bipolar or multipolar mapping. We report 3 cases of left atrial (LA) AFL where HD Grid + Omnipolar technology (Ensite X, Abbott) revealed MR circuits within an area of scar as noted by standard multipolar mapping. N/A Three patients with prior LA ablation presented with symptomatic AFL. LA mapping was done using the Ensite X system in Voxel mode. Bipolar voltage cutoff was set at 0.3 to 0.05 mV. A 65-year-old presented with AFL CL of 335 ms. Mapping with an Advisor spiral showed a large posterior wall scar and no AFL circuit in LA or RA. Remapping with HD Grid identified a 12 mm MR circuit with entire CL in the low LA posterior wall which showed dense scar by spiral mapping (Figure 1A). A 59-year-old male presented with AFL CL of 340 ms with proximal to distal CS activation. HD grid mapping identified a 21 mm MR circuit in the mid LA posterior with fractionated mid-diastolic electrograms (Figure 1B and 1C). Third patient was a 54-year-old male who had a MR circuit in the posterolateral mitral annulus, otherwise noted as scar by bipolar mapping. Successful ablation sites in all 3 cases did not have an identifiable bipolar electrogram on ablation catheter (<0.05 mV, Figure 1 D). Low voltage cut off during HD mapping was manually adjusted and had to be lowered to 0.04 to identify the circuit in all cases. This case series demonstrates that ultra high-density mapping with HD Grid + Omnipolar technology, with dynamic adjustment of low voltage threshold, enables identification of MR AFL circuits, leading to successful ablation, where critical isthmi were not identified by standard bipolar or multipolar mapping.

Geospatial modelling of lymphatic filariasis and malaria co-endemicity in Nigeria.

Lymphatic filariasis (LF) and malaria are important vector-borne diseases that are co-endemic throughout Nigeria. These infections are transmitted by the same mosquito vector species in Nigeria and their transmission is similarly influenced by climate and sociodemographic factors. The goal of this study was to assess the relationship between the geospatial distribution of both infections in Nigeria to better coordinate interventions. We used national survey data for malaria from the Demographic and Health Survey dataset and site-level LF mapping data from the Nigeria Lymphatic Filariasis Control Programme together with a suite of predictive climate and sociodemographic factors to build geospatial machine learning models. These models were then used to produce continuous gridded maps of both infections throughout Nigeria. The R2 values for the LF and malaria models were 0.68 and 0.59, respectively. Also, the correlation between pairs of observed and predicted values for LF and malaria models were 0.69 (95% confidence interval [CI] 0.61 to 0.79; p<0.001) and 0.61 (95% CI 0.52 to 0.71; p<0.001), respectively. However, we observed a very weak positive correlation between overall overlap of LF and malaria distribution in Nigeria. The reasons for this counterintuitive relationship are unclear. Differences in transmission dynamics of these parasites and vector competence may contribute to differences in the distribution of these co-endemic diseases.

Autonomous docking trajectory optimization for unmanned surface vehicle: A hierarchical method

Docking trajectory planning for unmanned surface vehicles is challenging due to complicated obstacle-avoidance in the harbor and highly nonlinear motion equations. In this paper, a two-stage (i.e., searching and optimization) hierarchical method is developed for a safe and efficient solution. In the searching stage, we establish a grid map for the harbor environment. The unmanned surface vehicle is represented by multiple featured discs and an artificially-guided Hybrid A* algorithm is implemented to search a coarse collision-free path. In the optimization stage, we first estimate the total sailing time under time-optimal maneuvering assumptions. Given the discretization scheme, we resample state and control variables along the coarse path by interpolation. Then, we construct a series of safe sailing corridors along the interpolated results. The within-corridor constraints are used to reformulate the optimal control problem, and the interpolated results are used for warm-start. The developed method is numerically validated by two docking scenarios, where high-quality trajectory as well as profiles of control inputs can be obtained with satisfactory computational efficiency. Meanwhile, it shows superiority in robustness over traditional planning techniques in the presence of narrow waterways and concave harbor shores. An animation of the simulation results is available at www.bilibili.com/video/BV14D4y1t7QL/.

Investigation of Obstacle Prediction Network for Improving Home-Care Robot Navigation Performance

Home-care manipulation robot requires exploring and performing the navigation task safely to reach the grasping target and ensure human safety in the home environment. An indoor home environment has complex obstacles such as chairs, tables, and sports equipment, which make it difficult for robots that rely on 2D laser rangefinders to detect. On the other hand, the conventional approaches overcome the problem by using 3D LiDAR, RGB-D camera, or fusing sensor data. The convolutional neural network has shown promising results in dealing with unseen obstacles in navigation by predicting the unseen obstacle from 2D grid maps to perform collision avoidance using 2D laser rangefinders only. Thus, this paper investigated the predicted grid map from the obstacle prediction network result for improving indoor navigation performance using only 2D LiDAR measurement. This work was evaluated by combining the configuration of the various local planners, type of static obstacles, raw map, and predicted map. Our investigation demonstrated that using the predicted grid map enabled all the local planners to achieve a better collision-free path by using the 2D laser rangefinders only rather than the RGB-D camera with 2D laser rangefinders with a raw map. This advanced investigation considers that the predicted map is potentially helpful for future work in the learning-based local navigation system.

Emission accounting, sectoral contributions and gridded spatial distribution of greenhouse gases in a typical petrochemical district of Shanghai

In this study, a petrochemical industrial district (PID) in the megacity of Shanghai was selected as a case study to investigate the quantity and components, sectoral contributions, and spatial distribution of greenhouse gas (GHG) emissions, including carbon dioxide (CO2), methane (CH4), and nitrous oxide (N2O). The total GHG emissions from the PID were 25.86 million tonnes of carbon dioxide equivalent (CO2eq), of which CO2 made the largest contribution (96.9%), followed by N2O (2%) and CH4 (1.1%). In terms of the sectoral contributions, energy use and industrial processes and product use (IPPU) were the two major emission sources of GHGs, accounting for 76.14% and 23.17% of the total, respectively. Moreover, GHG emissions from energy use and IPPU in the petrochemical industry accounted for 36.1% of the total, indicating the significance of the petrochemical industry for GHG emissions. A high-resolution gridded (200 × 200 m) spatial distribution map of GHG emissions was created based on point source, line source, and area source databases, showing a clear difference in the emission levels of GHGs among the grids. Thirteen ultra-high grids with GHG emissions above 10,000 tonnes CO2eq, accounted for more than 90% of the total emissions in the PID, which should be given more attention in emission management programs. The results provided useful insights into the amount and composition, sectoral contributions, and gridded spatial distribution characteristics of GHG emissions in the petrochemical industry, and can be used by decision makers to develop refined management strategies for GHG emission reductions in typical petrochemical districts.

FORECASTING RAINFALL WITH MACHINE LEARNING

Rainfall is one of the most destructive natural disasters and is extremely difficult to model. As a result, a numerical analysis model based on a hydraulic theory and a machine learning algorithm were combined to produce a classification-based real-time rainfall prediction for the ground truth model. Using a two- dimensional inundation model and the environmental protection agency's storm model, the rainfall dataset is built in advance for various rainfall scenarios. The rainfall depth data for each map grid are divided by year based on the average rainfall prediction based on ground truth. If the observed rainfall is entered, a model is built to predict the representative cumulative volume. Rainfall-accuracy based on the actual situation in the proposed ADA SVM, ADA NB, MLP, and J48 algorithm. Keywords: ADA SVM,ADA NB,MLP, AND J48 ALGORITHM

A metaheuristic approach to optimal morphology in reconfigurable tiling robots

Reconfigurable robots are suitable for cleaning applications due to their high flexibility and ability to change shape according to environmental needs. However, continuous change in morphology is not an energy-efficient approach, with the limited battery capacity. This paper presents a metaheuristic-based framework to identify the optimal morphology of a reconfigurable robot, aiming to maximize the area coverage and minimize the energy consumption in the given map. The proposed approach exploits three different metaheuristic algorithms, namely, SMPSO, NSGA-II, and MACO, to generate the optimal morphology for every unique layout of a two-dimensional grid map by considering the path-length as the energy consumption. The novel feature of our approach is the implementation of the footprint-based Complete Coverage Path Planning (CCPP) adaptable for all possible configurations of reconfigurable robots. We demonstrate the proposed method in simulations and experiments using a Tetris-inspired robot with four blocks named Smorphi, which can reconfigure into an infinite number of configurations by varying its hinge angle. The optimum morphologies were identified for three settings, i.e., 2D indoor map with obstacles and free spaces. The optimum morphology is compared with the standard Tetris shapes in the simulation and the real-world experiment. The results show that the proposed framework efficiently produces non-dominated solutions for choosing the optimal energy-efficient morphologies.