Mobile Robot Applications Research Articles

Decentralized P2P Federated Learning for Privacy-Preserving and Resilient Mobile Robotic Systems

Swarms of mobile robots are being widely applied for complex tasks in various practical scenarios toward modern smart industry. Federated learning (FL) has been developed as a promising privacy-preserving paradigm to tackle distributed machine learning tasks for mobile robotic systems in 5G and beyond networks. However, unstable wireless network conditions of the complex and harsh working environment may lead to poor communication quality and bring big challenges to traditional centralized global training in FL models. In this article, a Peer-to-Peer (P2P) based Privacy-Perceiving Asynchronous Federated Learning (PPAFL) framework is introduced to realize the decentralized model training for secure and resilient modern mobile robotic systems in 5G and beyond networks. Specifically, a reputation-aware coordination mechanism is designed and addressed to coordinate a group of smart devices dynamically into a virtual cluster, in which the asynchronous model aggregation is conducted in a decentralized P2P manner. A secret sharing based communication mechanism is developed to ensure an encrypted P2P FL process, while a Secure Stochastic Gradient Descent (SSGD) scheme is integrated with an Autoencoder and a Gaussian mechanism is developed to ensure an anonymized local model update, communicating within a few neighboring clients. The case study based experiment and evaluation in three different application scenarios demonstrate that the PPAFL can effectively improve the security and resilience issues compared with the traditional centralized approaches for smart mobile robotic applications in 5G and beyond networks.

Assessing the Limits of Equivalent Circuit Models and Kalman Filters for Estimating the State of Charge: Case of Agricultural Robots

The battery State of Charge (SoC) is critical information to overcome agricultural robots’ limitations related to battery and energy management. Although several SoC estimation methods have been proposed in the literature, the performance of these methods has not been validated for different battery chemistries in agricultural mobile robot applications. Compared to previous work, this paper evaluates the limits of the SoC estimation using the RC model and the Thevenin model for a Lithium Iron Phosphate (LFP) battery and a Sealed Lead Acid (SLA) battery. This evaluation used a custom agricultural robot in a controlled indoor environment. Consequently, this work assessed the limitations of two ECM-based SoC estimation methods using battery packs, low-cost sensors and discharge cycles typically used in agricultural robot applications. Finally, the results indicate that the RC model is not suitable for SoC estimation for LFP battery; however, it achieved a mean absolute error (MAE) of 2.2% for the SLA battery. On the other hand, the Thevenin model performed properly for both chemistries, achieving MAE lower than 1%.

Development of a Three-Mobile-Robot System for Cooperative Transportation

AbstractThe transportation of large-scale objects in a narrow space is a challenging, but useful application for mobile robots. We have developed a three-mobile-robot system to cooperatively lift, support, and transport a large object on a mobile robot system. To facilitate the manipulation involved with loading an object onto the robots, where the robots must maintain firm contact with the object and anchor at its location, we designed an adaptable mechanism for the object-loading platform and a liftable brake to ensure that the robot remains stationary when necessary. Furthermore, each robot is designed to act as an omnidirectional wheel; therefore, all three robots can work as an omnidirectional block when collectively loading an object. The kinematic constraints of the object–robot system and forward kinematics of the robots’ cooperative motion are proposed, and experiments are conducted to confirm the designed mechanisms and confirm that the robots can load an object and cooperatively transport it along the expected trajectory.

Precision-Driven Multi-Target Path Planning and Fine Position Error Estimation on a Dual-Movement-Mode Mobile Robot Using a Three-Parameter Error Model

The multi-target path planning problem is a universal problem to mobile robots and mobile manipulators. The two movement modes of forward movement and rotation are universally implemented in integrated, commercially accessible mobile platforms used in logistics robots, construction robots, etc. Localization error in multi-target path tracking is one of the crucial measures in mobile robot applications. In this article, a precision-driven multi-target path planning is first proposed. According to the path's odometry error evaluation function, the precision-optimized path can be discovered. Then, a three-parameter odometry error model is proposed based on the dual movement mode. The error model describes localization errors in terms of the theoretical motion command values issued to the mobile robot, the forward moving distances, and the rotation angles. It appears that the three error parameters follow the normal distribution. The error model is finally validated using a mobile robot prototype. The error parameters can be identified by analyzing the actual moving trajectory of arbitrary movements. The experimental localization error is compared to the simulated localization error in order to validate the proposed error model and the precision-driven path planning method. The OptiTrack motion capture device was used to capture the prototype mobile robot's pose and position data.

Practical considerations in reinforcement learning-based MPC for mobile robots*

In mobile robot applications, the trajectory tracking task hides several difficulties, including the choice of the setpoint and the search for an acceptable trade-off between performance and computational constraints. In this work, we discuss practical issues of a Reinforcement Learning (RL) based Model Predictive Control (MPC) tuning approach by focusing on a specific mobile robot application, where the objective is to maximize the velocity, while keeping the robot within the track bounds. Among others, we show that softening the latter constraints allows us to obtain a RL-tuned tracking controller with the same performance of an economic nonlinear MPC formulation, but requiring significantly less computational resources.

Object-Aware View Planning for Autonomous 3-D Model Reconstruction of Buildings Using a Mobile Robot

Active mapping ranks among the most critical applications of autonomous mobile robots. In this article, we focus on 3D model reconstruction of buildings using an outdoor ground robot equipped with a solid-state LiDAR and a gimbal. A view-planning approach is proposed to generate and evaluate view sequences with reference to the characteristics of solid-state LiDAR and the robot configuration. To reconstruct the specific buildings while ignoring unrelated objects in the environment, we introduce object awareness into the map representation, and frontier- and sampling-based strategies are combined to plan the view sequences for the effective observation of a target building. Instead of greedily maximizing information gain, frontier clusters indicating the mapped object’s incomplete surfaces are used to evaluate the sampled views, and sampling the minimum view set generates view sequences able to efficiently cover the clusters. Moreover, using object awareness to partition the area of sampled views around the building facilitates a divide-and-conquer strategy that overcomes local characteristics and guides a complete reconstruction. Simulation and real-world experiments revealed that our approach allows the thorough and efficient active reconstruction of various buildings and even outperforms state-of-the-art approaches.

Differential drive kinematics and odometry for a mobile robot using TwinCAT

<abstract><p>In this paper, we propose a motion control system for a low-cost differential drive mobile robot. The robotic platform is equipped with two driven wheels powered by Beckhoff motors, instrumented with incremental encoders. The control system is designed and implemented using Beckhoff's TwinCAT 3 automation software, running on an industrial PC. The system is tested and experimentally tuned to achieve optimal performance. The method allows addressing both odometry motion accuracy and motion correction in order to obtain minimum trajectory errors. Test results on linear and angular robot trajectories show errors below 0.02 and 0.03%, respectively, after tuning of the motion parameters. The proposed approach can be expanded, tweaked and applied to other differential drive TwinCAT 3 based robotic solutions. This will contribute to expanding mobile robot applications to a variety of fields, such as industrial automation, logistics, warehouse management, health care, ocean and space exploration and a variety of other industrial and non-industrial activities.</p></abstract>

Comparison of path planning methods for robot navigation in simulated agricultural environments

Path planning is a research topic that is still being studied for the area of mobile robotics. However, path-planning algorithms for mobile robot applications depend strongly on the environment and its complexity. In this work, we implemented three different path-planning algorithms for a simulated agricultural process. The selected algorithms are Breadth First search (BFS), Depth first search (DFS), and A*. We compare and evaluate such algorithms by using different accuracy metrics. The results demonstrate that the A* path planning method outperforms the other methods considering processing time, travel time, distance, and battery consumption.

Mobile Robot Gas Source Localization Using SLAM-GDM with a Graphene-Based Gas Sensor

Mobile olfaction is one of the applications of mobile robots. Metal oxide sensors (MOX) are mobile robots’ most popular gas sensors. However, the sensor has drawbacks, such as high-power consumption, high operating temperature, and long recovery time. This research compares a reduced graphene oxide (RGO) sensor with the traditionally used MOX in a mobile robot. The method uses a map created from simultaneous localization and mapping (SLAM) combined with gas distribution mapping (GDM) to draw the gas distribution in the map and locate the gas source. RGO and MOX are tested in the lab for their response to 100 and 300 ppm ethanol. Both sensors’ response and recovery times show that RGO resulted in 56% and 54% faster response times, with 33% and 57% shorter recovery times than MOX. In the experiment, one gas source, 95% ethanol solution, is placed in the lab, and the mobile robot runs through the map in 7 min and 12 min after the source is set, with five repetitions. The results show the average distance error of the predicted source from the actual location was 19.52 cm and 30.28 cm using MOX and 25.24 cm and 30.60 cm using the RGO gas sensor for the 7th and 12th min trials, respectively. The errors show that the predicted gas source location based on MOX is 1.0% (12th min), much closer to the actual site than that predicted with RGO. However, RGO also shows a larger gas sensing area than MOX by 0.35–8.33% based on the binary image of the SLAM-GDM map, which indicates that RGO is much more sensitive than MOX in the trial run. Regarding power consumption, RGO consumes an average of 294.605 mW, 56.33% less than MOX, with an average consumption of 674.565 mW. The experiment shows that RGO can perform as well as MOX in mobile olfaction applications but with lower power consumption and operating temperature.

Design of Sub-Systems for GPS-Guided Autonomous Delivery Robot System

The use of autonomous robots for delivery services is a new potential goldmine. Furthermore, since the e-commerce and delivery industry are growing at a rapid rate, it is recommended that a system that could handle the high-volume traffic as well serve as a new customer attraction, be implemented. Therefore, this work aims to develop the Autonomous Delivery Robot System (ADRS) that could be utilized for delivery services. The ADRS uses the Arduino microcontroller to run a program. The developed system consists of three main components (sub-systems), namely, mobile robot, cloud server and mobile application. The mobile robot is equipped with a tracking and an obstacle detection system to maneuver it autonomously. The ultrasonic sensors are used for obstacle detection, coupled with a Global Positioning System (GPS) to enable it deliver packages to customers in a typical outdoor environment. The ADRS ensures a human-contactless and secure delivery by using a password protected container to carry the delivery packages. Only the customer can unlock the container using the provided password via mobile application. The mobile application with customized map based on Google Maps is created to provide the user with an interactive interface. A camera is also attached on the robot for real-time monitoring purpose. The performance of the ADRS has been evaluated to determine the functionality of the developed system.

Efficient Hardware Accelerator Design of Non-Linear Optimization Correlative Scan Matching Algorithm in 2D LiDAR SLAM for Mobile Robots.

Simultaneous localization and mapping (SLAM) is the major solution for constructing or updating a map of an unknown environment while simultaneously keeping track of a mobile robot's location. Correlative Scan Matching (CSM) is a scan matching algorithm for obtaining the posterior distribution probability for the robot's pose in SLAM. This paper combines the non-linear optimization algorithm and CSM algorithm into an NLO-CSM (Non-linear Optimization CSM) algorithm for reducing the computation resources and the amount of computation while ensuring high calculation accuracy, and it presents an efficient hardware accelerator design of the NLO-CSM algorithm for the scan matching in 2D LiDAR SLAM. The proposed NLO-CSM hardware accelerator utilizes pipeline processing and module reusing techniques to achieve low hardware overhead, fast matching, and high energy efficiency. FPGA implementation results show that, at 100 MHz clock, the power consumption of the proposed hardware accelerator is as low as 0.79 W, while it performs a scan match at 8.98 ms and 7.15 mJ per frame. The proposed design outperforms the ARM-A9 dual-core CPU implementation with a 92.74% increase and 90.71% saving in computing speed and energy consumption, respectively. It has also achieved 80.3% LUTs, 84.13% FFs, and 20.83% DSPs saving, as well as an 8.17× increase in frame rate and 96.22% improvement in energy efficiency over a state-of-the-art hardware accelerator design in the literature. ASIC implementation in 65 nm can further reduce the computing time and energy consumption per scan to 5.94 ms and 0.06 mJ, respectively, which shows that the proposed NLO-CSM hardware accelerator design is suitable for resource-limited and energy-constrained mobile and micro robot applications.

Robot path planner based on deep reinforcement learning and the seeker optimization algorithm

Path planning is one of the key technologies for mobile robot applications. However, the traditional robot path planner has a slow planning response, which leads to a long navigation completion time. In this paper, we propose a novel robot path planner (SOA+A2C) that produces global and local path planners with the seeker optimization algorithm (SOA) and the advantage actor-critic (A2C) algorithm, respectively. In addition, to solve the problems of poor convergence performance when training deep reinforcement learning (DRL) agents in complex path planning tasks and path redundancy when metaheuristic algorithms, such as SOA, are used for path planning, we propose the incremental map training method and path de-redundancy method. Simulation results show that first, the incremental map training method can improve the convergence performance of the DRL agent in complex path planning tasks. Second, the path de-redundancy method can effectively alleviate path redundancy without sacrificing the search capability of the metaheuristic algorithm. Third, the SOA+A2C path planner is superior to the Dijkstra & dynamic window approach (Dijkstra+DWA) and the Dijkstra & timed elastic band (Dijkstra+TEB) path planners provided by the robot operating system (ROS) in terms of path length, path planning response time, and navigation completion time. Therefore, the developed SOA+A2C path planner can serve as an effective tool for mobile robot path planning.

Manufacturing operations as services by robots with skills

Abstract This work considers flexible manufacturing operations based on reconfigurable robotic skills and their usage in fully automated service manufacturing. In agile and ultra-flexible manufacturing operations, where lot sizes go down to one, the setup and execution of new tasks must be instant. We extend service manufacturing towards applications of multi-purpose autonomous mobile robots. We take digital data and service-oriented approach to configure and utilize re-usable robot operations formulated as robot skills. We integrate service requests, and system and robot skill models for an easily executable manufacturing service system. We show the feasibility of our approach by experimental tests with merged indoor logistics, assembly, and finishing tasks.

Optimal PID Control of a Brushed DC Motor with an Embedded Low-Cost Magnetic Quadrature Encoder for Improved Step Overshoot and Undershoot Responses in a Mobile Robot Application.

The development of a proportional–integral–derivative (PID) control system is a simple, practical, highly effective method used to control the angular rotational velocity of electric motors. This paper describes the optimization of the PID control of a brushed DC motor (BDCM) with an embedded low-cost magnetic quadrature encoder. This paper demonstrates empirically that the feedback provided by low-cost magnetic encoders produces some inaccuracies and control artifacts that are not usually considered in simulations, proposing a practical optimization approach in order to improve the step overshoot and undershoot controller response. This optimization approach is responsible for the motion performances of a human-sized omnidirectional mobile robot using three motorized omnidirectional wheels.

A Reconfigurable Visual-Inertial Odometry Accelerated Core with High Area and Energy Efficiency for Autonomous Mobile Robots.

With the wide application of autonomous mobile robots (AMRs), the visual inertial odometer (VIO) system that realizes the positioning function through the integration of a camera and inertial measurement unit (IMU) has developed rapidly, but it is still limited by the high complexity of the algorithm, the long development cycle of the dedicated accelerator, and the low power supply capacity of AMRs. This work designs a reconfigurable accelerated core that supports different VIO algorithms and has high area and energy efficiency, precision, and speed processing characteristics. Experimental results show that the loss of accuracy of the proposed accelerator is negligible on the most authoritative dataset. The on-chip memory usage of 70 KB is at least 10× smaller than the state-of-the-art works. Thus, the FPGA implementation’s hardware-resource consumption, power dissipation, and synthesis in the 28 nm CMOS outperform the previous works with the same platform.

An improved beetle antennae search path planning algorithm for vehicles.

With the development of society, the application of mobile robots in industry and life is increasingly extensive, and the local path planning of mobile robots in unknown environments is a problem that needs to be solved. Aiming at the problem that the traditional beetle antennae search (BAS) algorithm can easily fall into local optimum and the optimization accuracy is low, we propose an improved beetle antennae search. It introduces a map safety threshold, the addition of virtual target points, and the smoothing of the path. Map safety threshold means extra space with obstacles at all times, improving path reliability by avoiding collisions. Adding virtual target points reduces situations where the vehicle gets stuck in local optima. The B-spline smoothing path reduces the original path’s straight turns to improve the path’s robustness. The effectiveness and superiority of the algorithm are verified by comparing and testing the existing path planning algorithms through simulation in different environments.

HVIOnet: A deep learning based hybrid visual–inertial odometry approach for unmanned aerial system position estimation

Sensor fusion is used to solve the localization problem in autonomous mobile robotics applications by integrating complementary data acquired from various sensors. In this study, we adopt Visual–Inertial Odometry (VIO), a low-cost sensor fusion method that integrates inertial data with images using a Deep Learning (DL) framework to predict the position of an Unmanned Aerial System (UAS). The developed system has three steps. The first step extracts features from images acquired from a platform camera and uses a Convolutional Neural Network (CNN) to project them to a visual feature manifold. Next, temporal features are extracted from the Inertial Measurement Unit (IMU) data on the platform using a Bidirectional Long Short Term Memory (BiLSTM) network and are projected to an inertial feature manifold. The final step estimates the UAS position by fusing the visual and inertial feature manifolds via a BiLSTM-based architecture. The proposed approach is tested with the public EuRoC (European Robotics Challenge) dataset and simulation environment data generated within the Robot Operating System (ROS). The result of the EuRoC dataset shows that the proposed approach achieves successful position estimations comparable to previous popular VIO methods. In addition, as a result of the experiment with the simulation dataset, the UAS position is successfully estimated with 0.167 Mean Square Error (RMSE). The obtained results prove that the proposed deep architecture is useful for UAS position estimation.

Green smart manufacturing: energy-efficient robotic job shop scheduling models

ABSTRACT Smart manufacturing has boosted the wide application of mobile robots in robotic cells for automated material delivery. However, the mismatching between machine production process and robot movement process causes extensive energy waste. Nevertheless, most existing robotic job-shop scheduling (RJSP) studies mainly focus on minimising makespan but overlook the low energy efficiency problem faced by robotic cells. Motivated by the importance of green smart manufacturing, in this study, we innovatively propose to achieve robotic cell energy saving through coordinating the machine production process and robot movement process. Specifically, both machines and the mobile robot can flexibly adjust operating speeds with a V-scale speed framework. Two novel energy-efficient RJSP approaches (i.e. the RJSP-E and the RJSP-EM) are thus proposed. The RJSP-E focuses on minimising energy consumption, while the RJSP-EM simultaneously considers makespan (i.e. productivity) and energy consumption. Through computational experiments, the RJSP-E demonstrates superior performances in reducing energy consumption (15% on average), at a loss of productivity (20% on average). On the other hand, the RJSP-EM can select the most suitable energy-saving operating speeds without much sacrifice in productivity. Notably, the RJSP-EM can reduce energy consumption by a mean of 10% even without increasing makespan. The RJSP-EM also demonstrates higher solution efficiency.

Intelligent Energy Management System for Mobile Robot

Mobile robots used for search and rescue suffer from uncertain time duration for sustainable operation. Solar energy has the drawback that it fluctuates depending on the weather. By integrating the battery and supercapacitor, the energy management system eliminates this shortcoming. Managing power sharing between the battery and the supercapacitor is conducted by the fuzzy logic controller and proportional integral controller. The fuzzy logic controller provides a reference value to the proportional integral controller to keep the supercapacitor voltage at a certain value. It provides sufficient space to store solar energy and at the same time helps the battery to stay longer for operation. Moreover, the proposed energy management system offers a feature for providing a load power reference recommendation and offers the hibernate mode to save energy when the main power source is too weak, and it is suitable for mobile robot application. The simulation and experiment show that the energy management system design maintains the supercapacitor voltage and regulates the power sharing. Moreover, it also provides a percentage power reference recommendation for the central controller to manage its load current. It reduces the battery power consumption up to 35% and reduces peak current up to 5%, depending on the existing photovoltaic current and load management.

Touchless Hand Sanitizer Mobile Robot Application: Survey and Dataset Preparation for Deep Learning Recognition

The COVID-19 pandemic spreads throughout the world, many sanitizer dispenser devices included robots designed to minimize human contact and as less as possible to minimize the speared of this pandemic or any germs among humans. In many positions, these sanitizers dispensers are important to sterilize and help people from infection such as patients and medical staff in hospitals, teachers, and students in schools or universities, etc. In this paper, many studies of sanitizer dispenser devices including mobile robot applications for touchless hand sanitizers especially in the coronavirus pandemic have been explained. The major aim of this survey is to compare and contrast many previous survey methodologies. This study covered the introduction to robot applications, hand sanitizers dispenser device including a mobile robot, and object detection-based deep learning techniques that recognizes people. Object detection with the deep learning method is discussed because it is the most important feature of the hand sanitizer device, which is based on a mobile robot application. Furthermore, in this work, the proposed block diagram of dataset processing has been instigated using the mini-computer Raspberry Pi version 4, Raspberry Pi camera system, and LabelImg graphical tool. These dataset outputs files of each image (label.xml and image.jpg) are prepared and classed into 7 classes to use as inputs to the next future work of deep learning. In future work, we want to create a mobile robot hand sanitizer that recognizes the people using a deep learning approach. The python programing language has been used. The contribution of this work is to create, annotate and prepare the dataset for Deep Learning while the previous related works depended on existing dataset that taken from website .