Mobile Robot Platform Research Articles

A New Coastal Crawler Prototype to Expand the Ecological Monitoring Radius of OBSEA Cabled Observatory

The use of marine cabled video observatories with multiparametric environmental data collection capability is becoming relevant for ecological monitoring strategies. Their ecosystem surveying can be enforced in real time, remotely, and continuously, over consecutive days, seasons, and even years. Unfortunately, as most observatories perform such monitoring with fixed cameras, the ecological value of their data is limited to a narrow field of view, possibly not representative of the local habitat heterogeneity. Docked mobile robotic platforms could be used to extend data collection to larger, and hence more ecologically representative areas. Among the various state-of-the-art underwater robotic platforms available, benthic crawlers are excellent candidates to perform ecological monitoring tasks in combination with cabled observatories. Although they are normally used in the deep sea, their high positioning stability, low acoustic signature, and low energetic consumption, especially during stationary phases, make them suitable for coastal operations. In this paper, we present the integration of a benthic crawler into a coastal cabled observatory (OBSEA) to extend its monitoring radius and collect more ecologically representative data. The extension of the monitoring radius was obtained by remotely operating the crawler to enforce back-and-forth drives along specific transects while recording videos with the onboard cameras. The ecological relevance of the monitoring-radius extension was demonstrated by performing a visual census of the species observed with the crawler’s cameras in comparison to the observatory’s fixed cameras, revealing non-negligible differences. Additionally, the videos recorded from the crawler’s cameras during the transects were used to demonstrate an automated photo-mosaic of the seabed for the first time on this class of vehicles. In the present work, the crawler travelled in an area of 40 m away from the OBSEA, producing an extension of the monitoring field of view (FOV), and covering an area approximately 230 times larger than OBSEA’s camera. The analysis of the videos obtained from the crawler’s and the observatory’s cameras revealed differences in the species observed. Future implementation scenarios are also discussed in relation to mission autonomy to perform imaging across spatial heterogeneity gradients around the OBSEA.

Identification of shielded sources using a CZT detector and an unmanned ground vehicle

This work is dedicated to ability of a coplanar cadmium zinc telluride (CZT) detector to identify lost/orphan radioactive sources hidden inside soil layers. Considering point-like sources placed in soil and the CZT detector fixed on an unmanned ground vehicle (UGV), relevant measurement geometries were proposed. Full-energy peak efficiency (FEPE) calibrations of the CZT detector were prepared using the MCNP6.1 radiation transport code. In order to check the simulation set-up, control measurements were performed and compared with the Monte Carlo simulations.FEPEs obtained were used for estimations of minimum detectable activities (MDA) and their dependencies on the source depth in soil. Thereafter, field tests of the CZT detector were performed. Within field measurements, radioactive sources with known activities slightly above the MDA values were placed in upper layers of soil of a grassed meadow. The meadow surface was scanned by the CZT detector mounted on a mobile ground robotic platform remotely controlled by an operator. Results of the radiation mapping with the CZT detector were depicted as maps of count rates. On the basis of the maps created, positions of shielded sources were clearly revealed.

Mechanical Design, Planning, and Control for Legged Robots in Distillation Columns

Abstract Dexterous robots have great potential to execute industrial tasks that are not suited to humans. In this work, a novel robotic mobility platform is proposed for use in the chemical industry to enable autonomous distillation column inspection—a tedious and dangerous task for humans. A roller arm mechanism is designed for a quadrupedal robot that enables moving across the distillation column. Required dynamic behaviors are generated with full-body motion planning and low-level control. The holistic process of mechanical design, planning, and control leads to desired behavior, as demonstrated by high-fidelity simulations. This marks a key step toward operating legged robots inside distillation columns.

Learning Type-2 Fuzzy Logic for Factor Graph Based-Robust Pose Estimation With Multi-Sensor Fusion

Although a wide variety of high-performance state estimation techniques have been introduced recently, the robustness and extension to actual conditions of the estimation systems have been challenging. This paper presents a robust adaptive state estimation framework based on the Type-2 fuzzy inference system and factor graph optimization for autonomous mobile robots. We use the hybrid solution to connect the advantages of the tightly and loosely coupled technique by providing an inertial sensor and other extrinsic sensors such as LiDARs and cameras. In order to tackle the uncertainty input covariance and sensor failures problems, a learnable observation model is introduced by joining the Type-2 FIS and factor graph optimization. In particular, the use of Type-2 Takagi-Sugeno FIS can learn the uncertainty by using particle swarm optimization before adding the observation model to the factor graph. The proposed design consists of four parts: sensor odometry, up-sampling, FIS based-learning observation model, and factor graph-based smoothing. We evaluate our system by using a mobile robot platform equipped with a sensor setup of multiple stereo cameras, an IMU, and a LiDAR sensor. We imitate the LiDAR odometry in structure environments without needing other bulky motion capture systems to learn the observation model of the visual-inertial estimators. The experimental results are deployed in real-world environments to present the accuracy and robustness of the algorithm.

MIRRAX: A Reconfigurable Robot for Limited Access Environments

The development of mobile robot platforms for inspection has gained traction in recent years with the rapid advancement in hardware and software. However, conventional mobile robots are unable to address the challenge of operating in extreme environments where the robot is required to traverse narrow gaps in highly cluttered areas with restricted access. This paper presents MIRRAX, a robot that has been designed to meet these challenges with the capability of re-configuring itself to both access restricted environments through narrow ports and navigate through tightly spaced obstacles. Controllers for the robot are detailed, along with an analysis on the controllability of the robot given the use of Mecanum wheels in a variable configuration. Characterisation on the robot's performance identified suitable configurations for operating in narrow environments. The minimum lateral footprint width achievable for stable configuration ($<2^\text{o}$~roll) was 0.19~m. Experimental validation of the robot's controllability shows good agreement with the theoretical analysis. A further series of experiments shows the feasibility of the robot in addressing the challenges above: the capability to reconfigure itself for restricted entry through ports as small as 150mm diameter, and navigating through cluttered environments. The paper also presents results from a deployment in a Magnox facility at the Sellafield nuclear site in the UK - the first robot to ever do so, for remote inspection and mapping.

Multi-Sensor Fusion Tomato Picking Robot Localization and Mapping Research

To address the current problem of unsatisfactory localization and map building of an intelligent picking robot mobile platform in an unstructured picking environment, a multi-sensor fusion localization and map building method is proposed to fuse the visual odometer position estimation results with IMU and wheel odometer. And the pre-fusion processing of wheel odometer data is proposed to solve the problem of large errors of wheel odometers on uneven ground. The multi-sensor fusion scheme is proposed to fuse vision and laser SLAM methods to build a more information-rich point cloud and raster fusion map for the problem of non-closure caused by sparse branches. The experimental results show that the multi-sensor fusion SLAM method can obtain more accurate, richer, and more robust maps.

2D LIDAR SLAM Localization System for a Mobile Robotic Platform in GPS Denied Environment

Agricultural mobile robots using Global Navigation Satellite System (GNSS)–based signal for navigation can be easily occluded and the position and attitude errors calculated by inertial navigation sensor (INS) will accumulate over time, which will seriously affect functions like localization and navigation. Therefore, based on the above shortcomings, this research uses 2D LIDAR (two-dimensional, Light Detection and Ranging) SLAM (Simultaneous Localization and Mapping) as the scheme for the outdoor positioning of the mobile robot. The Cartographer SLAM algorithm was selected in this study and was operated under the ROS (Robot Operating System) platform. After a series of comparative experiments, it can be concluded that the positioning accuracy at the normal speed of 1.5 km/h is about 0.2–0.3 m considering the error of human manipulation and the accuracy of attitude around 3–4 degrees. This 2D LIDAR-based localization framework helps for developing an autonomous navigation system for the static agricultural environment that can be operated under GNSS denied environment.

Simulation Modeling of Mobile Robotic Complexes Tool Analysis According to Physical Laws (a Review)

This article is about the technologies of simulation modeling of mobile robotic complexes. The basic demands for a simulation environment are defined such as realistic results, open-source code, extensibility, performance of system, possibility of usage of low-level code for simulation. Moreover, the most significant characteristics for physics engines are described in the article, specifically solid-state physics, torque setup, stability of "axle" connection, stability of the simulated many-body system. The frequently used physics engines such as PhysX, ODE, MuJoCo, Bullet, Havok are analyzed and the search of modeling services is made in order to make the comparative table. The platform Unity is in focus of this work to show its abilities in modeling of mechanical and electronic parts of mobile robots. The aim of this work is minimizing mobile robots development outgoings. Programming product is given as result of simulation modeling of robotic complexes. The Unity platform is used as the engine for development of simulation tools for mechanical and electronic parts of robotic complex. The set of tools based on Unity engine is developed in order to create virtual models of mobile robots. The architecture of the project was developed in order to determine aspects of creating mobile robots in a simulation modeling environment. The logic of scripts for modeling the solid-state physics, kinematic chains and joints with different degrees of freedom is presented as a result of developing architecture of the project. The package was tested, a model of a mobile four-wheeled robotic platform was built as a result of the test.

Developing a Machine Learning Algorithm for Service Robots in Industrial Applications

Robots, which have mostly been effective in areas such as industrial, agricultural, and production facilities, have started to take a place in the service sector, as their technologies have become lower in cost and more easily accessible. This situation has attracted the attention of companies and researchers and has accelerated studies on this subject. In this study, an algorithm was developed for the autonomous mobile robot to serve in industrial areas. In line with this study, it was ensured that the autonomous mobile robot mapped the working environment, determined the working station in this environment, and then carried out transport operations between these working stations in accordance with a given work order. After the mobile robot fulfilled the work order, it went into a waiting state until a new work order was received. For the mobile robot to save energy, it was ensured that it waited close to the point where the work order came in the most, by means of machine learning in the waiting position. The developed algorithms were designed using the NI LabVIEW environment and then simulated in the RobotinoSIM environment and physically tested using the Robotino autonomous mobile robot platform. The experimental results showed that mapping and location reporting using an RGB camera, odometry, and a QR code eliminated permanent location errors, and the robot completed 50 work orders with 100% accuracy.

Development and Verification of an Autonomous and Controllable Mobile Robot Platform

In this paper, we design a mobile robot platform, which employs a fully autonomous mechanical structure and electrical control system. Two driving wheels realize flexible steering movement with four universal wheels. A variety of sensors are built on the mobile robot platform, including the Inertial Measurement Unit (IMU) used to establish the inertial navigation coordinate system and the Velodyne’s Puck lidar sensor (VLP-16) used to obtain the three-dimensional (3D) point cloud information of the environment. Then, we build a software control architecture based on the Robot Operating System (ROS), using multi-node communication to perform positioning, environment perception, dynamic obstacle avoidance, path planning and motion control. Furthermore, a method of actively exploring the environment and constructing a map is proposed, using multi-path evaluation for real-time path planning and obstacle avoidance. In the end, we conduct autonomous exploration experiments to verify the performance of the designed mobile robot platform in indoor multi-obstacle scenes.

6D Object Localization in Car-Assembly Industrial Environment

In this work, a visual object detection and localization workflow integrated into a robotic platform is presented for the 6D pose estimation of objects with challenging characteristics in terms of weak texture, surface properties and symmetries. The workflow is used as part of a module for object pose estimation deployed to a mobile robotic platform that exploits the Robot Operating System (ROS) as middleware. The objects of interest aim to support robot grasping in the context of human-robot collaboration during car door assembly in industrial manufacturing environments. In addition to the special object properties, these environments are inherently characterised by cluttered background and unfavorable illumination conditions. For the purpose of this specific application, two different datasets were collected and annotated for training a learning-based method that extracts the object pose from a single frame. The first dataset was acquired in controlled laboratory conditions and the second in the actual indoor industrial environment. Different models were trained based on the individual datasets and a combination of them were further evaluated in a number of test sequences from the actual industrial environment. The qualitative and quantitative results demonstrate the potential of the presented method in relevant industrial applications.

Artificial Potential Field Path Planning Algorithm in Differential Drive Mobile Robot Platform for Dynamic Environment

Mobile robots need path-planning abilities to achieve a collision-free trajectory. Obstacles between the robot and the goal position must be passed without crashing into them. The Artificial Potential Field (APF) algorithm is a method for robot path planning that is usually used to control the robot for avoiding obstacles in front of the robot. The APF algorithm consists of an attractive potential field and a repulsive potential field. The attractive potential fields work based on the predetermined goals that are generated to attract the robot to achieve the goal position. Apart from it, the obstacle generates a repulsive potential field to push the robot away from the obstacle. The robot's localization in producing the robot's position is generated by the differential drive kinematic equations of the mobile robot based on encoder and gyroscope data. In addition, the mapping of the robot's work environment is embedded in the robot's memory. According to the experiment's results, the mobile robot's differential drive can pass through existing obstacles. In this research, four test environments represent different obstacles in each environment. The track length is 1.5 meters. The robot's tolerance to the goal is 0.1 m, so when the robot is in the 1.41 m position, the robot's speed is 0 rpm. The safe distance between the robot and the obstacle is 0.2 m, so the robot will find a route to get away from the obstacle when the robot reaches that safe distance. The speed of the resulting robot decreases as the distance between the robot and the destination gets closer according to the differential drive kinematics equation of the mobile robot.

Monitoring the Current Provided by a Hall Sensor Integrated in a Drive Wheel Module of a Mobile Robot

This article describes a method for the real-time monitoring of the current consumed by a Dynamixel MX 64 AT servomotor used in the actuation system of modular mobile robotic platforms having differential locomotion and conventional wheels. The data acquisition method is based on an Arduino Mega 2560 development board interfaced with Matlab Simulink and the ASC712-5A hall sensor for current detection. A Simulink model is presented that performs the detection of a sensor reference voltage, which needs to be calibrated for a correct reading of the current. Due to the low resolution of the analog-to-digital converter with which the Arduino Mega is equipped, current monitoring is difficult to achieve, having large fluctuations and a lower resolution than the current absorbed by the servomotor. The solution to this problem is achieved by implementing, in the hardware construction, an ADS115 conversion module with 16-bit resolution, which leads to an increase in the measurement range of the ASC712-5A sensor. The current acquisition model with the Hall sensor is experimentally validated using measurements on the physical model of the drive wheel. This article further deals with the CAD and digital block modeling of mobile platforms with four and two wheels. The dynamic model of the robot is created in the Simulink–Simscape–Multibody environment and is used to determine the servomotor torques when the robot is moving along the predefined path. The torque variations are entered as variables in the Simulink digital block model of the robot. The Simulink model is simulated when moving along a square path, which determines the variation in the current absorbed by the motors. Experimental validation of the model is carried out using measurements on the functional models that operate in real conditions. A power consumption method is further proposed.

Low-cost depth/IMU intelligent sensor fusion for indoor robot navigation

AbstractThis paper presents a mobile robot platform, which performs both indoor and outdoor localization based on an intelligent low-cost depth–inertial fusion approach. The proposed sensor fusion approach uses depth-based localization data to enhance the accuracy obtained by the inertial measurement unit (IMU) pose data through a depth–inertial fusion. The fusion approach is based on feedforward cascade correlation networks (CCNs). The aim of this fusion approach is to correct the drift accompanied by the use of the IMU sensor, using a depth camera. This approach also has the advantage of maintaining the high frequency of the IMU sensor and the accuracy of the depth camera. The estimated mobile robot dynamic states through the proposed approach are deployed and examined through real-time autonomous navigation. It is shown that using both the planned path and the continuous localization approach, the robot successfully controls its movement toward the destination. Several tests were conducted with different numbers of layers and percentages of the training set. It is shown that the best performance is obtained with 12 layers and 80% of the pose data used as a training set for CCN. The proposed framework is then compared to the solution based on fusing the information given by the XSens IMU–GPS sensor and the Kobuki robot built-in odometry solution. As demonstrated in the results, an enhanced performance was achieved with an average Euclidean error of 0.091 m by the CCN, which is lower than the error achieved by the artificial neural network by 56%.

Global trends in the development of agricultural robotics

Agriculture is one of the most difficult and unpredictable industries. Despite this, technological advances in related industries can significantly reduce the negative impact of external factors by improving agricultural technologies and agricultural equipment, including through the introduction of unmanned mobile energy vehicles and robotic platforms for performing various agricultural operations. The interest of the scientific community in research on robotic systems for agricultural purposes is growing every year. Most of the reviewed publications are devoted to the development and improvement of computer vision systems, a description of the design of the developed robots and the results of their tests, as well as the development of autonomous control systems for robotic platforms, navigation and communication systems. At the same time, not a single solution for the development of agricultural robotic systems has currently reached the level of an economically accessible industrial design. This is due primarily to the high complexity and cost of development, applied technological solutions and equipment. The industrial introduction of agricultural robots will become possible only with the further significant development and cost reduction of the technologies and components used in them.

A Dual Forward–Backward Algorithm to Solve Convex Model Predictive Control for Obstacle Avoidance in a Logistics Scenario

In recent years, the logistics sector expanded significantly, leading to the birth of smart warehouses. In this context, a key role is represented by autonomous mobile robots, whose main challenge is to find collision-free paths in their working environment in real-time. Model Predictive Control Algorithms combined with global path planners, such as the A* algorithm, show great potential in providing efficient navigation for collision avoidance problems. This paper proposes a Dual Forward–Backward Algorithm to find the solution to a Model Predictive Control problem in which the task of driving a mobile robotic platform into a bi-dimensional semi-structured environment is formulated in a convex optimisation framework.

Error State Extended Kalman Filter Localization for Underground Mining Environments

The article addresses the issue of mobile robotic platform positioning in GNSS-denied environments in real-time. The proposed system relies on fusing data from an Inertial Measurement Unit (IMU), magnetometer, and encoders. To get symmetrical error gauss distribution for the measurement model and achieve better performance, the Error-state Extended Kalman Filter (ES EKF) is chosen. There are two stages of vector state determination: vector state propagation based on accelerometer and gyroscope data and correction by measurements from additional sensors. The error state vector is composed of the velocities along the x and y axes generated by combining encoder data and the orientation of the magnetometer around the axis z. The orientation angle is obtained from the magnetometer directly. The key feature of the algorithm is the IMU measurements’ isolation from additional sensor data, with its further summation in the correction step. Validation is performed by a simulation in the ROS (Robot Operating System) and the Gazebo environment on the grounds of the developed mathematical model. Trajectories for the ES EKF, Extended Kalman Filter (EKF), and Unscented Kalman Filter (UKF) algorithms are obtained. Absolute position errors for all trajectories are calculated with an EVO package. It is shown that using the simplified version of IMU’s error equations allows for the achievement of comparable position errors for the proposed algorithm, EKF and UKF.

Multimodal Few-Shot Target Detection Based on Uncertainty Analysis in Time-Series Images

The ability to interpret multimodal data, and map the targets and anomalies within, is important for an automatic recognition system. Due to the expensive and time-consuming nature of multimodal time-series data annotation in the training stage, multimodal time-series image understanding, from drone and quadruped mobile robot platforms, is a challenging task for remote sensing and photogrammetry. In this regard, robust methods must be computationally low-cost, due to the limited data on aerial and ground-based platforms, yet accurate enough to meet certainty measures. In this study, a few-shot learning architecture, based on a squeeze-and-attention structure, is proposed for multimodal target detection, using time-series images from the drone and quadruped robot platforms with a small training dataset. To build robust algorithms in target detection, a squeeze-and-attention structure has been developed from multimodal time-series images from limited training data as an optimized method. The proposed architecture was validated on three datasets with multiple modalities (e.g., red-green-blue, color-infrared, and thermal), achieving competitive results.

Smart agriculture: Development of a skid-steer autonomous robot with advanced model predictive controllers

The agricultural domain has been experiencing extensive automation interest over the past decade. The established process for measuring physiological and morphological traits (phenotypes) of crops is labour-intensive and error-prone. In this paper, a mobile robotic platform, namely The Autonomous Robot for Orchard Surveying (AROS), was developed to automate the process of collecting spatial and visual data autonomously. Furthermore, six different control frameworks are presented to evaluate the feasibility of using a kinematic model in agricultural environments. The kinematic model does not consider wheel slippage or any forces associated with dynamic motion. Thus, the following six controllers are evaluated: Proportional-Derivative (PD) controller, Sliding Mode Controller (SMC), Control-Lyapunov Function (CLF), Nonlinear Model Predictive Controller (NMPC), Tube-Based Nonlinear Model Predictive Controller (TBNMPC), and Model Predictive Sliding Mode Control (MPSMC). This paper provides insight into the degree of disturbance rejection that the mentioned control architectures can achieve in outdoor environments. Experimental results validate that all control architectures are capable of rejecting the present disturbances associated with unmodelled dynamics and wheel slip on soft ground conditions. Additionally, the optimal-based controllers managed to perform better than the non-optimal controllers. Performance improvements of the TBNMPC of up to 209.72% are realized when compared to non-optimal methods. Results also show that the non-optimal controllers had low performance due to the underactuated constraint present in the kinematic model.

БАЗОВА СТРУКТУРА СИСТЕМИ НЕЙРОНЕЧІТКОГО УПРАВЛІННЯ ГРУПОЮ МОБІЛЬНИХ РОБОТОТЕХНІЧНИХ ПЛАТФОРМ

It is shown that the following approaches can be used for group management of mobile robotic platforms (MRP): centralized (concentrated), decentralized (distributed) and hybrid. It was determined that an urgent task is the development of a neurofuzzy management system for the MRP group, which must perform the distribution of tasks between the MRPs, the determination of MRP movement routes, joint planning of works and their synchronization. The requirements for the system of neurofuzzy management of the MRP group are formulated, the main of which are the provision of: effective management of the MRP group; minimization of time for tasks; flexibility and adaptability to changing working conditions; reliable and stable operation when implementing various scenarios; expansion of functions and scaling relative to the number of MRPs; accuracy and reliability of traffic management of each MRP; response to changes in working conditions; uninterrupted work of the MRP group; effective use of MRP resources; reduction of dimensions, weight and energy consumption; management in real time; collecting data on the environment and the state of the MRP; wireless communication between MRP; development of software tools taking into account the distributed architecture; implementation of a programming interface with the possibility of developing additional software and integration with other systems; saving data on the status of all MRPs for further analysis and improving the management of the MRP group. The following main stages of the development of the neurofuzzy control system by the MRP group were identified: problem formulation; analysis of system requirements; hardware design; development of a neurofuzzy control algorithm; software development; testing and tuning; implementation and operation. It is suggested that the development of the system of neurofuzzy control of the MRP group be carried out on the basis of an integrated approach, which includes: methods of neurofuzzy control of the MRP group, artificial neural networks and fuzzy logic; navigation methods, methods of pre-processing and image recognition; methods of intellectual processing and evaluation of data from sensors in conditions of interference and incomplete information; modern methods and algorithms of intelligent traffic control of MRP; modern element base (microcontrollers, systems-on-chip, FPGA, etc.); methods and means of automated design of hardware and software of MRP. It is proposed to implement the neurofuzzy control system by the MRP group on the basis of a problem-oriented approach, which involves a combination of universal software and specialized hardware, which ensures high efficiency of equipment use. The method of time allocation of resources of the storage medium of multiport memory has been improved, which, due to the consideration of the speed of the storage medium and external devices, ensures an increase in the number of devices with conflict-free access to the storage medium.