Robotic Vehicle Research Articles

Rationale for the Choice of a Positioning System for Mobile Agricultural Robot Movement Controlling

A correctly selected positioning system for controlling the mobile robotic means movement ensures high positioning accuracy of the robotic platform in the garden, allows to automate precise operations in the garden and systematize route planning algorithms.(Research purpose) To substantiate the rational choice of a positioning system for controlling the mobile robotic device movement.(Materials and methods) The author formulated requirements for the positioning system to perform precise operations in the garden: mechanized collection of fruits and berries, diff erentiated application of fertilizers and chemical plant protection products. The main ones were: the positioning error was no more than 5 centimetres, the stability of information transfer to the server for building traffi c maps, the movement of a robotic device along a given trajectory, equipping beacons with a mobile power source with a capacity of at least 800 milliampere-hour, information exchange between the beacon and the built-in robotic means with a microprocessor controller according to the RS-485 standard, the signal coverage area was at least 100 square meter.(Results and discussion) The six most relevant positioning systems of the following manufacturers were described: RealTrac, Rusoft CKT, Neomatic, ISBC, Avtosensor, Marvelmind. The author compared their technical and operational parameters: operating frequencies, range, data transfer interface, location accuracy and cost of ready-made kits. He showed that Marvelmind provided uninterrupted operation at frequencies of 433 and 915 megahertz with a positioning error of no more than 2 centimetres. The tests were carried out on a small robotic vehicle with the following characteristics: maximum transport speed – 30 kilometre per hour, operating weight – 500 kilograms, length 2 metres, width – 1.2 metres, height – 1.6 metres.(Conclusions) The author substantiated the choice of the most suitable and aff ordable Marvelmind positioning system and experimentally confi rmed the positioning accuracy declared by the manufacturer. When driving in a loop-free and looped turn, the positioning accuracy did not exceed 1.5 centimetres, which met the agrotechnical requirements for mechanized collection of fruits and berries, for diff erentiated application of fertilizers and chemical plant protection products

Watertight integrity of underwater robotic vehicles by self-healing mechanism

Self-healing mechanism (SHM) application has attracted interest due to ability to self-heal as response to damage situations in various conditions, and is being actively explored. However, the application of SHM that can be autonomously triggered for temporarily keeping structural integrity of underwater robotic vehicle (URV) under flooding condition is still scarce publicly. This paper describes an investigation in watertight integrity performance of URV’s hull under damaged stability criteria. The main goal is to investigate the characterization of a rapid SHM through an experiment for identifying progressive flooding in a damaged URV’s hull. Here, it is demonstrated that the effectiveness of sodium polyacrylate, a kind of superabsorbent polymers (SAP), had been studied by applying the polymer on an experimental model of damaged URV’s hull. A comparison is studied for the stability of the flooded URV and the mass of water accumulated inside the URV’s hull between the cases of before and after applying the SHM in the damaged model under different damaged conditions. The results showed that the SHM application had rapidly blocked the damaged leak hole and prevented severe water flow ingress in the damaged URV’s hull. Swift recovery of buoyancy was obtained, as the volume of absorbed water by SHM was converted into equivalent buoyancy loss. These findings are establishing a fundamental knowledge for implementation of SHM in underwater robotic structures.

Design experimental of RF controlled beach cleaner robotic vehicle

The research article on vortex tube, which deals with the operation of statistic parts. The project, tried it best to brief the RF control beach cleaner which is robotic vehicle that helps in cleaning the shores. It helps to collect the Garbage’s, plastics etc near the shore. The concept of this project is to find solutions to help the marine life environment that garbage and litter is affecting the environment and everything surrounding it. This machine system is specifically focused to pick up litter from beaches and shores to serve the organizations and volunteers related to this issue. This project can be used in all different shores and beaches which will help organizations to achieve more and clean better with our project’s prototype.

Special issue on 6G wireless systems

While 5G is currently being deployed around the globe, research on 6G is under way aiming at addressing the coming challenges of drastic increase of wireless data traffic and support of other usage scenarios. 6G is expected to extend 5G capabilities even further. Higher bitrates (up to Tbps) and lower latency (less than 1ms) will allow introducing new services — such as pervasive edge intelligence, ultra-massive machine-type communications, extremely reliable low-latency communications, holographic rendering and high-precision communications — and meet more stringent requirements, especially in the following dimensions: energy efficiency; intelligence; spectral efficiency; security, secrecy and privacy; affordability; and customization. Artificial intelligence approaches and techniques, such as machine learning (of which deep learning and reinforcement learning are specific examples), and machine reasoning (which includes planning, scheduling, knowledge representation and reasoning, search and optimization), are the new fundamental enablers to operate networks more efficiently, enhance the overall end user experience and provide innovative service applications. Quantum Optics Computing (QOC) and Quantum Key Distribution (QKD) are almost ready for industrial applications. In particular, massive Internet of Things (mIoT), Industrial IoT (IloT), fully automated robotic platforms (which include control, perception, sensors and actuators, as well as the integration of other techniques into cyber-physical systems), vehicles and multisensory extended reality are examples of the new data-demanding applications, which will impose new performance targets and motivate 6G design and deployment.

Arduino Based Voice Controlled Robot Vehicle

This project was developed in a way that the robot is controlled by voice commands. An android application with a microcontroller is used for required tasks. The connection between the android app and the vehicle is facilitated with Bluetooth technology. The robot is controlled by buttons on the application or by spoken commands of the user. The movement of the robot is facilitated by the two dc servo motors connected with microcontroller at the receiver side. The commands from the application is converted in to digital signals by the Bluetooth RF transmitter for an appropriate range (about 100 meters) to the robot. At the receiver end the data gets decoded by the receiver and is fed to the microcontroller which drives the DC motors for the necessary work. The aim of Voice Controlled Robotic Vehicle is to perform the required task by listening to the commands of the user. A prior preparatory session is needed for the smooth operation the robot by the user. For the same a code is used for giving instruction to the controller.

Automated terrain mapping based on mask R-CNN neural network

PurposeThe purpose of this paper is to analyze the development of a novel approach for automated terrain mapping a robotic vehicles path tracing.Design/methodology/approachThe approach includes stitching of images, obtained from unmanned aerial vehicle, based on ORB descriptors, into an orthomosaic image and the GPS-coordinates are binded to the corresponding pixels of the map. The obtained image is fed to a neural network MASK R-CNN for detection and classification regions, which are potentially dangerous for robotic vehicles motion. To visualize the obtained map and obstacles on it, the authors propose their own application architecture. Users can any time edit the present areas or add new ones, which are not intended for robotic vehicles traffic. Then the GPS-coordinates of these areas are passed to robotic vehicles and the optimal route is traced based on this dataFindingsThe developed approach allows revealing impassable regions on terrain map and associating them with GPS-coordinates, whereas these regions can be edited by the user.Practical implicationsThe total duration of the algorithm, including the step with Mask R-CNN network on the same dataset of 120 items was 7.5 s.Originality/valueCreating an orthophotomap from 120 images with image resolution of 470 × 425 px requires less than 6 s on a laptop with moderate computing power, what justifies using such algorithms in the field without any powerful and expensive hardware.

Developing Future Wearable Interfaces for Human-Drone Teams through a Virtual Drone Search Game

Autonomous robotic vehicles (i.e., drones) are potentially transformative for search and rescue (SAR). This paper works toward wearable interfaces, through which humans team with multiple drones. We introduce the Virtual Drone Search Game as a first step in creating a mixed reality simulation for humans to practice drone teaming and SAR techniques. Our goals are to (1) evaluate input modalities for the drones, derived from an iterative narrowing of the design space, (2) improve our mixed reality system for designing input modalities and training operators, and (3) collect data on how participants socially experience the virtual drones with which they work. In our study, 17 participants played the game with two input modalities (Gesture condition, Tap condition) in counterbalanced order. Results indicated that participants performed best with the Gesture condition. Participants found the multiple controls challenging, and future studies might include more training of the devices and game. Participants felt like a team with the drones and found them moderately agentic. In our future work, we will extend this testing to a more externally valid mixed reality game.

Trajectory Path Analysis of Three Omnidirectional Wheel Robot (TODWR)

Presently there is a demand for vehicle robot in automated industry, military and hospital areas etc. Three omnidirectional wheel robot (TODWR) is basically a holonomic mobile vehicle which can achieve rotational and translational motions simultaneously and autonomously. This study exhibits the analysis of kinematics and dynamic motion of the three omnidirectional wheeled robot (TODWR). The TODWR robot is prepared by three wheels which are omnidirectional and set at the corners of triangle geometry shape chassis which is basically equilateral. This TODWR robot was performed by experimentally with different combination of wheel’s movement and it is also noted, different trajectory motion of TODWR robot.

Self-driving cars are coming. Chemical makers are racing to keep up

A convergence of new technologies will finally bring self-driving cars to the mass market in the next decade. Experts think the robot vehicles will start by delivering packages within limited areas. Then, bit by bit, they’ll make it out onto the open road with humans inside. This future hinges on sensors that let computers see the road. The sensors need to become more robust and sensitive while coming down in cost. An increasingly electric fleet will also demand lighter-weight materials and designs alongside improvements in cooling and lubrication. It’s a big set of changes that will challenge the chemical industry—and create opportunities. Talk with businesspeople and policy makers involved in mobility, and it becomes clear that self-driving cars are not a matter of if, but when. These vehicles will be front and center in a future where cars are connected, autonomous, shared, and electric—what advocates call CASE. Any one of

Feedback linearization control for a tandem rotor UAV robot equipped with two 2-DOF tiltable coaxial-rotors

In this paper, computed torque control as one method of feedback linearization techniques is considered for an unmanned aerial vehicle (UAV) robot that has two tiltable coaxial rotors so as to realize multifunctional locomotion modes, where each rotor has 2-DOF tilt mechanism. First, a dynamical model of such an UAV robot is derived following the Newton–Euler law. Next, under the assumptions that the anti-torque of the tiltable coaxial rotors is zero and the gyro moment effect of the tiltable coaxial rotors can be ignored, a computed torque controller is derived, because the resultant model of the UAV robot can be simplified to a fully actuated model, which has six motion inputs and six generalized coordinate outputs. In addition, a control allocation problem of the system, in which the control inputs designed using the dynamical model are assigned to all motors for tilting the rotor as well as rotating it, is solvable by using a Moore–Penrose pseudo-inverse, where a coordinate transformation is used to simply the allocation problem. Finally, some simulations are demonstrated to verify the effectiveness of the computed torque control strategy for the robot.

Improved localization in a corn crop row using a rotated laser rangefinder for three-dimensional data acquisition

Small robotic vehicles have been navigating agricultural fields in the pursuit of new possibilities to increase agricultural production and to meet the increasing food and energetic demands. However, a perception system with reliable awareness of the surroundings remains a challenge to achieve autonomous navigation. Camera and single-layer laser scanners have been the primary sources of information, yet the first suffers from outdoor light sensibility and both from occlusion by leaves. This paper describes a three-dimensional system acquisition for corn crops. The sensing core is a single-layer UTM30-LX laser scanner rotating around its axis, while an inertial sensor provides angular measurements. With the rotation, multiple layers are used to compose a 3D point cloud, which is represented by a two-dimensional occupancy grid. Each cell is filled according to the number of readings, and their weights derive from two procedures: firstly, a mask enhances vertical entities (stalks); secondly, two Gaussian functions on the expected position of the immediate neighboring rows weaken readings in the middle of the lane and farther rows. The resulting occupancy grid allows the representation of the cornrows by virtual walls, which are used as references to a wall follower algorithm. According to experimental results, the virtual walls are segmented with reduced influence from straying leaves and sparse weeds when compared to the segmentation done with single-layer laser scanner data. Indeed, 64.02% of 3D outputs are within 0.05 m limit error from expected lane width, while only 11.63% of single-layer laser data are within same limit.

Controlling the autonomous vehicle using computer vision and cloud server

Implementing the unmanned cars has been given much importance from the recent past years. These cars have been designed by the automobile industries and are in the stage to test their rides on the roads. With being implemented with automated cars, the problem arises when there is any technical issue of how the backup works. So, in this paper, we are presenting the implementation of the miniature model of the automated robotic vehicle using the Raspberry Pi and how the data can be sent to the cloud. So that a person can be able to observe and maintain the Speed, Distance Covered and the Movement of the Vehicle on the Roads of the city. This model is designed on the applications of the safety measures to be taken for these unmanned vehicles that are almost a reality in the coming days. The Raspberry Pi development board is used as the core processor, camera module for the identification of the traffic signals and the Ultrasonic sensor for the identification of any of the vehicle nearby, and if so the direction of the vehicle changes from which it is moving and all the remaining data regarding the data posted in the cloud is well described through the paper.

Voice Controlled Fire Fighting Robot

Even though there are a lot of advancements in technology, there have been an increased number of devastating losses in the field of fire-fighting. Fire accidents that occur in industries like atomic power plants, petroleum refineries, chemical factories and other large-scale fire industries end in quite serious consequences which can cause injuries or even death of individuals. Therefore, this paper is enhanced to develop an automated fire extinguishing robotic vehicle that saves the lives of firefighters and other persons in those areas. The proposed robotic vehicle is controlled using specified speech commands. The language input is more familiar which makes interaction with the robotic vehicle much easier. The advantages of voice-controlled robots are hands-free and rapid data input operations. The speech recognition process is done in such a way that it recognizes specified commands from the user and the designed robot navigates based on the instructions via the speech commands. The fire can be extinguished using a water tank that is fitted along with the robotic vehicle. Consequently, the site of fire is live monitored using ESP 32 and the status of the fire zone is updated to the user through message.

Application of DEA models in efficiency evaluation of the KAMAZ vehicle robotic system

The problem of evaluating the effectiveness of a robotic system of agricultural vehicles is described. A robotic system is considered, including robotic chassis for fieldwork, for transporting goods in the territories of agrarian production and specialized cars. An important task is to evaluate the reliability of robotic vehicles during the operation. A model-oriented approach to monitoring and analyzing the technical condition of the vehicle is proposed. The data envelopment analysis technique is used with the solution of a non-parametric linear programming problem. The selection of input and output parameters of a model of a robotic vehicle is described. The mathematical formulation of the linear programming problem by the integral criterion for the functioning of a robotic car in different periods is given. The results of the experimental studies are presented. The application of the data envelopment analysis allows determining the vehicle parameter’s target changes. The results will be used in the decision-making system for the operation and maintenance of KAMAZ agricultural vehicles.

Wrinkle-Enabled Highly Stretchable Strain Sensors for Wide-Range Health Monitoring with a Big Data Cloud Platform.

Flexible and stretchable strain sensors are vital for emerging fields of wearable and personal electronics, but it is a huge challenge for them to possess both wide-range measurement capability and good sensitivity. In this study, a highly stretchable strain sensor with a wide strain range and a good sensitivity is fabricated based on smart composites of carbon black (CB)/wrinkled Ecoflex. The sensor exhibits a maximum recoverable strain of up to 500% and a high gauge factor of 67.7. It has a low hysteresis, a fast signal response (as short as 120 ms), and a high reproducibility (up to 5000 cycles with a strain of 150%). The sensor is capable of detecting and capturing wide-range human activities, from speech recognition and pulse monitoring to vigorous motions. It is also applicable for real-time monitoring of robot movements and vehicle security crash in an anthropomorphic field. More importantly, the sensor is successfully used to send signals of a volunteer's breathing data to a local hospital in real time through a big data cloud platform. This research provides the feasibility of using a strain sensor for wearable Internet of things and demonstrates its exciting prospect for healthcare applications.

Adaptive neural network output-feedback control of multiple Ackermann steering vehicles formation including motor dynamics with a guaranteed performance

A prescribed performance output-feedback formation control of electrically driven Ackermann steering robotic vehicles is addressed in this paper. Some constraints are imposed to relative distance and angle errors between the cars and a leader. Then, constrained errors are transformed into a new second-order Euler–Lagrange formulation of unconstrained errors via the prescribed performance function technique which inherits all structural properties of the robot dynamics. Based on dynamic surface control design, an observer-based proportional–integral–derivative virtual controller with a prescribed performance is proposed at the first step. Then, an actual controller is proposed at the actuator level to generate input voltage control signals. The proposed controller takes the following advantages: (1) the possible overshoots and controller singularities are avoided based on some predefined performances of relative distance and angle errors, (2) the controller does not require linear and angular velocity measurements, (3) the unknown nonlinearities and exogenous disturbances are effectively compensated by combining a neural network and adaptive robust controller, and (4) the actuator dynamics is compensated in the inner-loop while voltage control signals are directly generated for each robot motors. Lyapunov’s stability analysis proves the stability of the closed-loop control system. Finally, numerical simulation results will show the controller performance.

On infusing reachability-based safety assurance within planning frameworks for human–robot vehicle interactions

Action anticipation, intent prediction, and proactive behavior are all desirable characteristics for autonomous driving policies in interactive scenarios. Paramount, however, is ensuring safety on the road: a key challenge in doing so is accounting for uncertainty in human driver actions without unduly impacting planner performance. This article introduces a minimally interventional safety controller operating within an autonomous vehicle control stack with the role of ensuring collision-free interaction with an externally controlled (e.g., human-driven) counterpart while respecting static obstacles such as a road boundary wall. We leverage reachability analysis to construct a real-time (100 Hz) controller that serves the dual role of (i) tracking an input trajectory from a higher-level planning algorithm using model predictive control, and (ii) assuring safety by maintaining the availability of a collision-free escape maneuver as a persistent constraint regardless of whatever future actions the other car takes. A full-scale steer-by-wire platform is used to conduct traffic-weaving experiments wherein two cars, initially side-by-side, must swap lanes in a limited amount of time and distance, emulating cars merging onto/off of a highway. We demonstrate that, with our control stack, the autonomous vehicle is able to avoid collision even when the other car defies the planner’s expectations and takes dangerous actions, either carelessly or with the intent to collide, and otherwise deviates minimally from the planned trajectory to the extent required to maintain safety.

Hydraulic Pressure-Flow Rate Control of a Pallet Handling Robot for an Autonomous Freight Delivery Vehicle

The current paper presents an upgrade of a pre-installed hydraulic system for the operation of a pallet handling robot for a freight delivery vehicle known as FURBOT (freight urban robotic vehicle). The automated forklift installed on FURBOT for loading/unloading of cargo is powered with the help of hydraulics. The previous hydraulic system worked via a classical approach with a fixed displacement pump and a bypass valve, making it work on full power when in use. An alternative design was proposed, simulated and installed on FURBOT; it uses a fixed displacement pump and changes the rotation speed in real time using a pressure sensor. Novelty was attained with the use of gear pumps for said scenario. A control algorithm is implemented in the processing unit for controlling the speed of the motor driving the pump. The main advantage of this approach is better use of energy for the vehicle’s battery. The aim of this research is to control both the speed and maximum force exerted by the actuators with the help of a single sensor and an inexpensive pump.

DEEP SEMANTIC SEGMENTATION FOR THE OFF-ROAD AUTONOMOUS DRIVING

Abstract. This paper is devoted to the problem of image semantic segmentation for machine vision system of off-road autonomous robotic vehicle. Most modern convolutional neural networks require large computing resources that go beyond the capabilities of many robotic platforms. Therefore, the main drawback of such models is extremely high complexity of the convolutional neural network used, whereas tasks in real applications must be performed on devices with limited resources in real-time. This paper focuses on the practical application of modern lightweight architectures as applied to the task of semantic segmentation on mobile robotic systems. The article discusses backbones based on ResNet18, ResNet34, MobileNetV2, ShuffleNetV2, EfficientNet-B0 and decoders based on U-Net and DeepLabV3 as well as additional components that can increase the accuracy of segmentation and reduce the inference time. In this paper we propose a model using ResNet34 and DeepLabV3 decoding with Squeeze & Excitation blocks that was optimal in terms of inference time and accuracy. We also demonstrate our off-road dataset and simulated dataset for semantic segmentation. Furthermore, we present that using pre-trained weights on simulated dataset achieves to increase 2.7% mIoU on our off-road dataset compared pre-trained weights on the Cityscapes. Moreover, we achieve 75.6% mIoU on the Cityscapes validation set and 85.2% mIoU on our off-road validation set with a speed of 37 FPS for a 1,024×1,024 input on one NVIDIA GeForce RTX 2080 card using NVIDIA TensorRT.

Scientific Challenges and Present Capabilities in Underwater Robotic Vehicle Design and Navigation for Oceanographic Exploration Under-Ice

This paper reviews the scientific motivation and challenges, development, and use of underwater robotic vehicles designed for use in ice-covered waters, with special attention paid to the navigation systems employed for under-ice deployments. Scientific needs for routine access under fixed and moving ice by underwater robotic vehicles are reviewed in the contexts of geology and geophysics, biology, sea ice and climate, ice shelves, and seafloor mapping. The challenges of under-ice vehicle design and navigation are summarized. The paper reviews all known under-ice robotic vehicles and their associated navigation systems, categorizing them by vehicle type (tethered, untethered, hybrid, and glider) and by the type of ice they were designed for (fixed glacial or sea ice and moving sea ice).