Robotic Rover Research Articles

Automated Lunar Surface Image Classification Using Deep Convolutional Neural Networks for Geological Feature Detection

Robotic rovers have vastly expanded our understanding of the lunar surface, providing detailed imagery crucial for scientific research and future exploration. However, manually classifying this imagery is time-consuming and prone to errors, necessitating automated solutions. Automated classification of lunar surface imagery is vital for efficient data analysis, site selection for future missions, and advancing lunar exploration. Developing accurate and efficient image classification systems tailored for lunar terrain is thus imperative. The objective of this study is to develop and assess an image classification system utilizing Deep Convolutional Neural Networks (DCNNs) specifically for lunar surface images. The aim is to achieve high accuracy and efficiency in identifying geological features such as craters and dunes, as observed by robotic rovers. A curated dataset of lunar surface images was partitioned into training, testing, and validation subsets. DCNNs models were trained on the training dataset and evaluated using testing and validation datasets. Hyperparameter tuning and optimization techniques were employed to enhance model performance. The classification system based on DCNNs showed promising outcomes. Model B and F achieved an accuracy of 91.1%, while Model A and D achieved 87.5%. Model C attained an accuracy of 89.3%, and Model E reached 83.9%. Visualizations of training and validation metrics revealed distinct performance patterns across models, highlighting the potential for further advancements in lunar exploration research.

Solving higher dimensional expensive black box global optimization problems using sparse directional search on surrogates

We present a new algorithm Directional Optimization Search with Surrogate (DOSS), for optimizing problems with box constraints and a computationally expensive black-box objective function. DOSS is a radial basis function (RBF) based method that mainly focuses on higher dimensional and computationally expensive objective functions that can be multimodal. DOSS introduces three new techniques not previously used in earlier RBF algorithms, including using a combination of the coordinates knowledge level, fewer initial sampling points, and the surrogate’s gradient information. Numerical results on a test set including 14 test problems with 36, 48, and 60 dimensions show that DOSS outperforms two recently published algorithms RBFOpt and TuRBO, and earlier RBF algorithms such as DYCORS. TuRBO is a Gaussian process based optimization algorithm, which outperformed earlier state-of-the-art methods. DOSS algorithm also has a good performance on real-world optimization problems, including robot pushing and rover trajectory planning problems. Almost sure convergence for the DOSS algorithm is also proven in this paper. An implementation of DOSS is available at https://doi.org/10.5281/zenodo.13731558.

Common Ground: The Unique Synergy Between the Oil Field and Aerospace

Though disparate locations, outer space and the oil field have much more in common than one might think. Both can be taxing on operations and often redefine the idea of an isolated and, at times, hostile work environment. Harsh atmospheric conditions and wide-ranging pressure regimes call for unique technological applications and operations to achieve the best performance and results, whether it’s the gravitational and meteorological challenges of another planet or the crushing pressures and changing meta-ocean conditions of the deep offshore. Despite the obvious differences, operating in both the terran oil field and the blackness of space offer hurdles that can be cleared by similar means. Shared technologies between the two industries have been around for decades and center around disciplines like automation, robotics, and remote sensing. The National Aeronautics and Space Administration (NASA) itself has dabbled in oilfield studies, especially when it comes to greenhouse gas emissions and their impact on the atmosphere. In 2021, the agency’s Jet Propulsion Laboratory, along with the University of Arizona and Arizona State University, completed a study to identify methane super-emitters in the Permian Basin. The month-long, airborne study concluded that fixing the worst leaks identified in the area’s infrastructure could cut methane emissions by 55 tons an hour, equivalent to 5.5% of the US Environmental Protection Agency’s estimates of all methane emissions from hydrocarbon production across the entire US. The study pointed to malfunctioning equipment as the likely culprit for the 123 sources found. Conversely, NASA has also tapped into oilfield technology for some of its planned drilling operations on the moon. It will be the first such operation on any planetary body outside of the Earth. One of the earliest directives of NASA’s Artemis program is to try and find water near the lunar South Pole. Polar Resources Ice Mining Experiment-1 (PRIME-1) will be the first in-situ resource utilization demonstration on the moon. For the first time, NASA will robotically sample and analyze for ice from below the surface. PRIME-1 will use TRIDENT (The Regolith and Ice Drill for Exploring New Terrain) to drill in a single location at a site with a high likelihood of having water, whether in liquid or ice form. TRIDENT was developed and supplied by Honeybee Robotics, which also supplies geotechnical tools and sensors, among other tech, to the oil patch. The system, to be integrated into VIPER, NASA’s first robotic moon rover, will drill about a meter below the surface, each time bringing up samples that NASA will analyze with a mass spectrometer. The launch of the NOVA-C, which carries the PRIME-1, was previously delayed. At press time, the payload was due to blast off on board Space X’s Falcon 9 rocket in early 2024. NASA said in October the VIPER will reach its destination at Mons Mouton near the lunar South Pole in November 2024.

Shielding factors for a fission-powered mars exploration rover

Background: With the advances in compact fission power systems and Stirling converters, the efficiency and portability of electrical energy production systems has increased substantially thanks to NASA’s Kilopower project. These 1-10 kWe-class reactors are compact enough to be transportable by pressurized rovers, allowing an extended human reach across the surface of Mars to produce scientific data at a rate that greatly surpasses the rate of robotic rover data collection. If rovers were to harness fission power while mobile, it is possible for near-limitless range. This capability could allow one crew on Mars for under a “Conjunction” class mission as outlined in NASA’s Mars Design Reference Architecture (DRA) 5.0 to visit many geological sites of interest instead of requiring additional landings to explore distant features of the Martian surface. This study explored the parameters that affected the mass of the shielding required to protect the crew against a fission reactor embedded in the chassis of a pressurized rover. Methods: An analytical approach was devised to estimate the required mass of a hypothetical solid tungsten shield under various conditions. Results: Power levels below 3.4 kWe were found to be impractical for rover applications. Between 3.4 kWe and 10 kWe would be able to recharge the rover without returning to base camp. The increase in shielding mass from a 3.4 kWe reactor and a 10 kWe reactor was 6%. The reduction between a 10 kWe reactor at 3 m and 6 m was 7%. Varying the shield thickness in accordance with astronaut activities resulted in a 19% reduction. Powering the reactor off before exiting the vehicle resulted in an additional 65% reduction. Conclusions: Knowledge of the crew activities and locations had the greatest impact on the required shielding mass and the mission activities should be well-understood before finalizing a shield design.

Design and Study of an AI-Powered Autonomous Stair Climbing Robot

Mobile robots are frequently utilized in the surveillance sector for both industrial and military purposes. The ability to navigate stairs is crucial for carrying out surveillance jobs like urban search and rescue operations. The research paper shows that the design methodology for a six-wheeled rover robot that can adapt to various stairs and maintain its stability based on the robot's specifications, kinematics restrictions, the maximum height, and the lowest step length needed to climb up and down the stairs is proposed. Based on a Raspberry Pi, camera, and LIDAR distance sensor, the suggested robot has the capacity to measure the stair height before starting to climb. A Convolutional Neural Networks (CNN) deep learning model is developed for the purpose of stair recognition. Additionally, stair alignment was estimated using statistical filtering on pictures and LIDAR distance reading. The robot can then decide whether it can climb the stairs or not based on its kinematics limitations and the height of the stairs as measured by our system. Result shows that our stair detection algorithm achieved an accuracy of 99.46% and a mean average precision of 99.64%. The proposed AI-Powered Robot-based stair recognition system, according to final results, effectively climbed stairs with a height range between 13 and 23 cm.

Theoretical study on a modified rocker-bogie suspension for robotic rovers

AbstractRobotic rovers equipped with articulated rocker-bogie suspension have aroused great interest after the explorations on Mars; this interest has also shifted to different types of terrestrial applications such as in the agriculture, military, and rescue fields. The suspension can be designed so that, when the rover is on flat and horizontal ground, the weight is evenly distributed among the wheels; in this way, all wheels have the same traction capability and offer the same rolling resistance. As the operating conditions vary due to sloping ground, uneven ground surface, or different payload position, the weight distribution can undergo considerable variations. This type of suspension is statically determined with respect to weight, but it is indeterminate with respect to traction forces; the traction control system aims to avoid the wheels slippage. In this paper, the traction contribution that each wheel can provide, to overcome a step obstacle, is shown. Furthermore, the possibility of regulating the distribution of vertical loads among the wheels adopting a torsion spring, with adjustable preload, arranged between rocker and bogie, is evaluated. A suitable spring preload facilitates the initial phase of the obstacle overcoming if the rover advances with the bogie forward. Numerical simulations show that to increase the possibility of overcoming an obstacle it is sufficient for the spring preload to reduce the vertical load on the front wheel; in any case, a higher load variation would not be advisable as it could involves an excessive load difference among the wheels.

Design of Deliberative and Reactive Hybrid Control System for Autonomous Stuff-Delivery Robot Rover

ABSTRAK Saat ini, robot otonom memiliki peranan signifikan di berbagai bidang. Robot otonom meningkatkan efektivitas dan produktivitas sekaligus menurunkan risiko dan tingkat kesalahan secara signifikan. Dua paradigma dapat digunakan saat merancang robot otonom, yaitu paradigma reaktif dan deliberatif. Paper ini merancang sistem kontrol hybrid untuk menggabungkan elemen terbaik dari sistem kontrol deliberatif dan reaktif untuk robot pengiriman otonom. Model tersebut dibuktikan dengan misi untuk memindahkan tiga objek berwarna, dari posisinya ke tujuan. Dari perancangan dan pengujian, sistem hybrid dapat meminimalisir kelemahan dari masing-masing sistem, sehingga proses pengiriman barang dapat tercapai sesuai dengan rencana dan dapat bereaksi terhadap kondisi yang sebelumnya tidak diketahui dalam perencanaan, seperti hambatan. Penggunaan sistem hybrid membuka kemungkinan untuk merancang sebuah mobile robot otonom yang dapat beroperasi di lingkungan apapun. Kata kunci: deliberative, reactive, hybrid, autonomous, robot rover ABSTRACT Recently, autonomous robots have become increasingly significant in numerous fields. Robots with autonomy increase effectiveness and productivity while significantly lowering risk and error rates. Two paradigms can be used when creating an autonomous robot, namely reactive and deliberative paradigm. This paper proposes a hybrid control system to combine the best elements of deliberative and reactive control system for an autonomous delivery robot rover. The model was proved with a mission to move the three colored objects, from their respective positions to the goal cells. From the design and testing the hybrid systems can minimize the weaknesses of each system, so that the stuff-delivery process can be achieved in accordance with the plan and can react to conditions that were not previously known in planning, such as the obstacle. The use of a hybrid system opens up the possibility of designing an autonomous mobile robot that can operate in any environment. Keywords: deliberative, reactive, hybrid, autonomous, robot rover

Multitask robotic rover for agricultural activities (R2A2): a robotic platform for peach orchards

Multitask robotic rover for agricultural activities (R2A2): a robotic platform for peach orchards

Navigation system of autonomous multitask robotic rover for agricultural activities on peach orchards based on computer vision through tree trunk detection

Navigation system of autonomous multitask robotic rover for agricultural activities on peach orchards based on computer vision through tree trunk detection

GPS-based autonomous navigation system for multitask robotic rover for agricultural activities with augmented reality web application for supervision support on peach orchards

ISHS X International Peach Symposium GPS-based autonomous navigation system for multitask robotic rover for agricultural activities with augmented reality web application for supervision support on peach orchards

Real‐Time Remodeling of Granular Terrain for Robot Locomotion

Terrain irregularities in natural environments present mobility challenges for autonomous robots and vehicles. Loosely consolidated sandy slopes flow unpredictably when perturbed, often leading to locomotion failure. Systematic experiments with various robot morphologies on flowable terrains feature open‐loop quasistatic gait strategies that remodel the terrain to aid locomotor kinematics. On a sloped terrain of granular media near the critical angle, a laboratory‐scale rover robot induces a flow via a localized fluidization gait to remodel local terrain and succeed in locomotion. A Bayesian optimization machine learning approach that modulates this gait strategy then finds a pattern of selectively fluidizing and solidifying terrain to climb slopes rapidly. In a biped walker robot, a cleated foot design dynamically manipulates the stress fields of flowable slopes. The deeply submerged cleats remodel the shear response of the material by creating jammed regions behind them which then improve forward progression by reducing slip when compared to a flat foot. The “robophysics” approach of systematic experiments exploring terrain reconfiguration combined with future machine learning models of flowable terrain evolution can augment gait discovery for future robots.

Miniature semiconductor neutron spectrometer HardPix for surface mapping of lunar water

A current renaissance of lunar exploration enables to search for lunar water deposits directly on the surface of the Moon with robotic rovers. We present a novel miniature semiconductor neutron spectrometer capable of mapping the water deposits using non-invasive detection of neutrons created underground by cosmic rays and thermalized by hydrogen. This prospecting package consists of a radiation detector to monitor the cosmic rays background, a thermal/epithermal neutron detector to measure flux of neutrons moderated by water, and a gamma spectrometer suitable for monitoring local changes of major elemental components of the lunar regolith. Using miniature semiconductor detectors allows to deploy them even on small commercial rovers where resources are extremely limited. The prospecting package is being developed for ispace lunar rover and studied for ESA EL3 rover. It is based on Timepix pixel sensors, with space heritage onboard NASA, ESA and JAXA vessels.

Simultaneous Localization and Calibration for Cooperative Radio Navigation

Cooperative radio localization and navigation systems can be used in scenarios where the reception of global navigation satellite system (GNSS) signals is not possible or impaired. While the benefit of cooperation has been highlighted by many papers, calibration is not widely considered, but equally important in practice. Utilizing the signal propagation time requires group delay or ranging bias calibration and estimating the directions-of-arrival (DoAs) requires antenna response calibration. Often, calibration parameters are determined only once before operation. However, the calibration parameters are influenced by e.g. changing temperatures of radio frequency (RF) components or changing surroundings of antennas. To cope with that, we derive a cooperative simultaneous localization and calibration (SLAC) algorithm based on Bayesian filtering, which estimates antenna responses and ranging biases simultaneously with positions and orientations. By simulations, we show that the calibration parameters can be estimated during operation without additional sensors. We further proof practical applicability of SLAC by evaluating measurement data from robotic rovers. With SLAC, both ranging and DoAs estimation performance is improved, resulting in better position and orientation estimation accuracy. SLAC is thus able to provide reliable calibration and to mitigate model mismatch. Finally, we discuss open research questions and possible extensions of SLAC.

Artificial Intelligence Based patrol Rover Robot with Night Vision & Object Detection Technology

Artificial Intelligence Based patrol Rover Robot with Night Vision & Object Detection Technology

Front and Back Covers, Volume 38, Number 3. June 2022

Front and back cover caption, volume 38 issue 3SPACE ANTHROPOLOGYA day on Mars, also known as a sol, lasts approximately 24 hours, 39 minutes, 35 seconds. In order to operate robotic rovers on the red planet, teams of scientists back on earth have to abandon terrestrial rhythms and work according to a new temporality: Mars time. This process is at the heart of Zara Mirmalek's Making time on Mars (2020) and is the inspiration for the front cover illustration by Uni Pang. This ethnography chronicles how the National Aeronautics and Space Administration (NASA) scientists and engineers forged new relationships with time, technology and each other in order to manage a novel multi‐planetary work system.Mirmalek's work, and others like it, are part of the emerging field of space anthropology. While humanity's various relations with the cosmos have been a running thread throughout the discipline's history, contemporary developments, such as the rapid growth of the private space sector and the looming threat of climate change, have pushed celestial matters to the fore. Recent scholarship has examined the collaborative practices of technical experts working on deep space probes, has shed light on the continuing colonial legacies of spaceports around the world and has asked how indigenous ontologies and decolonial thought can challenge techno‐scientific designs for unchecked human expansion into the stars.In this issue, members of the ARIES project — an international research team based at Jagiellonian University — draw on their experience designing and teaching an undergraduate course on the social science of outer space to discuss the current state of space‐oriented research. Engaging with outer space poses distinct methodological and theoretical questions that complicate some of the most fundamental tenets of anthropology. Yet, approaching these issues is crucial for understanding many contemporary social, ecological and political matters across local, planetary and multi‐planetary scales.‘DRIVE AND TALK’ FIELDWORKIn Langhorne Creek, South Australia, seasonal streams cut through a broad floodplain with giant eucalypts and grazing cows, interspersed with vineyards growing shiraz and cabernet sauvignon grapes. On this rich landscape, the descendants of settler‐colonial families have farmed for almost two centuries, irrigating in part with floodwaters from the Angas and Bremer Rivers. These precious waters are collaboratively shared between farms through sluice gates and earthworks systems.In this issue, Georgina Drew, William Skinner and Douglas Bardsley reflect upon the importance of the ‘drive and talk’ for fieldwork in an agricultural landscape: not only to generate empirical data but also phenomenologically, as the farm is felt through the sand and gravel passing under the wheels, the scrubby bushes scraping the chassis, and the muddy embankments navigated by a driver who knows their land inside out.Farming is physical work that requires mobility. At the scale of an Australian farm, mobility involves driving. Ethnographic engagement then is not just mobility but also auto‐mobility, as farmers bounce around their paddocks in pickup trucks with researchers in tow, driving between properties, fording streams, stopping here and there to point out pieces of historic infrastructure, examine vineyards, and explain the country and how it is changing.Water is front of mind in the region. In recent decades, groundwater depletion and rising salinity have represented an existential risk to Langhorne Creek, exacerbated by the major ‘Millennium Drought’. Now, a new pipeline drawing water from further afield provides increased surety. Yet, farmers maintain their vigilance, concerned about climatic fluctuations and changes to ground and surface water flows.By relating to farmer concerns in the intimate setting of the automobile, researchers can generate new understandings of the risks and opportunities for adaptation.

Computational Simulation of an Agricultural Robotic Rover for Weed Control and Fallen Fruit Collection—Algorithms for Image Detection and Recognition and Systems Control, Regulation, and Command

The continuous rise in the world’s population has increased the need for food, resulting in a rise of agricultural holdings to ensure the supply of these goods directly to the populations and indirectly to all processing industries in the food business. This situation has led agriculture to reinvent itself and introduce new technics and tools to ensure tighter control of the crops and increase yields in food production. However, the lack of labor coupled with the evolution of weeds resistant to herbicides created a crisis in agricultural food production. However, with the growing evolution in electronics, automation, and robotics, new paths are emerging to solve these problems. A robotic rover was designed to optimize the tasks of weed control and collection of fallen fruits of an orchard. In weed control, a localized spraying system is proposed, therefore reducing the amount of applied herbicides. With fruit collection, it is possible to direct fallen fruits for animal feeding and possible to reduce microbial activity on the next campaign crops, therefore avoiding damage. This study proposes the simulation of this robotic rover on robotic simulation software. It also proposes the replication of a similar environment of an orchard to generate an algorithm that controls the rover on the tasks of localized spraying and fallen fruit collection. Creating and testing these algorithms by using a robotic simulator speed up and ease the evaluation of different scenarios and hypotheses, with the added benefit of being able to test two tasks simultaneously. This method also allows greater freedom and creativity because there are no concerns about hardware damage. It should also be noted that development costs are very low.

Dynamic path planning over CG-Space of 10DOF Rover with static and randomly moving obstacles using RRT* rewiring

AbstractDynamic path planning is a core research content for intelligent robots. This paper presents a CG-Space-based dynamic path planning and obstacle avoidance algorithm for 10 DOF wheeled mobile robot (Rover) traversing over 3D uneven terrains. CG-Space is the locus of the center of gravity location of Rover while moving on a 3D terrain. A CG-Space-based modified RRT* samples a random space tree structure. Dynamic rewiring this tree can handle the randomly moving obstacles and target in real time. Simulations demonstrate that the Rover can obtain the target location in 3D uneven dynamic environments with fixed and randomly moving obstacles.

Bayesian In-Situ Calibration of Multiport Antennas for DoA Estimation: Theory and Measurements

The DoA of radio waves is used for many applications, e.g. the localization of autonomous robots and smart vehicles. Estimating the DoA is possible with a multiport antenna, e.g. an antenna array or a multi-mode antenna (MMA). In practice, DoA estimation performance decisively depends on accurate knowledge of the antenna response, which makes antenna calibration vital. As the antenna surroundings influence its response, it is necessary to measure the entire device with installed antenna to obtain the installed antenna response. Antenna calibration is often done in a dedicated measurement chamber, which can be inconvenient and costly, especially for larger devices. Thus, auto- and in-situ calibration methods aim at making antenna calibration in a measurement chamber redundant. However, existing auto- and in-situ calibration methods are restricted to certain antenna types and certain calibrations. In this paper, we propose a Bayesian in-situ calibration algorithm based on a maximum a posteriori (MAP) estimator, which is suitable for arbitrary multiport antennas. The algorithm uses received signals from a transmitter, noisy external DoA observations, takes multipath propagation into account and does not require synchronization. Furthermore, we take an estimation theoretic perspective and provide an in-depth theoretical discussion of in-situ antenna calibration in unknown propagation conditions based on Bayesian information and the Bayesian Cramér-Rao bound (BCRB). Extensive simulations show that the proposed algorithm operates close to the BCRB and the achieved DoA estimation performance asymptotically approaches the case of a perfectly known antenna response. Finally, we provide an experimental validation, where we calibrate the antenna on a robotic rover and evaluate the DoA estimation performance using measurement data. With the proposed in-situ antenna calibration algorithm, DoA estimation performance is considerably improved compared to using an antenna response obtained by simulation or in a measurement chamber.

Detection of biosignatures in terrestrial Mars analogs: Strategical and technical assessments

The search for potential signs of Martian life has been planned and implemented by worldwide countries for decades. Due to the high expenditure on Mars exploration, more easily accessible Mars-like regions on Earth are invaluable targets for astrobiology research to understand the detection of potential Martian biosignatures. In order to detect potential life signals beyond Earth, questions on how to define life and biosignatures need to be carefully inspected. This review summarizes scientific instrumental techniques, our “eyes” and “hands”, that facilitate identifying and quantifying biosignatures on Mars. Scientific devices that can be applied in astrobiology include electromagnetic spectrum-based spectrometers, mass spectrometers, redox potential indicators, circular dichroism polarimeters, in situ nucleic acid sequencers, life isolation/cultivation systems, and imagers. These techniques should be first tested in Mars analog extreme environments on Earth to validate their practicality on Mars. To better understand the instrumental detectability of biosignatures on Mars through its evolutionary history, terrestrial Mars analogs are divided into four major categories according to their similarities to different geological ages of Mars (the Early-Middle Noachian Period, the Late Noachian-Early Hesperian Period, the Late Hesperian-Early Amazonian Period, and the Middle-Late Amazonian Period). Future missions are suggested to explore more on the early terrains in Mars’ Southern Hemisphere once the landing issue is solved engineeringly, since these explorations permit investigating a continuum of the habitability shift through Mars geological history. Moreover, practical applications of scientific instruments listed above are briefly reviewed based on the four categories of Mars analogs, and instruments applied for autonomous robotic rover tests in Mars analogs are further discussed. For engineering efficiency, a Mars rover ought to be equipped with as few assemblable instruments as possible. Therefore, once candidate landing regions on Mars are defined, the portable suites of instruments should be smartly devised on the basis of the geological, geochemical, geomorphological, and chronological characteristics of the landing regions. Laboratory-based experiments without engineering restrictions are further encouraging and appealing if Mars sample-return missions are successfully completed. To exclude false positive and false negative conclusions in life discovery, the combined use and replication studies of multiple analytical techniques must be performed to confirm the observational results.

Desain Robot Pengintai Segala Medan dengan Kendali Wireless PS2

A mobile robots is one of the solution to overcome the deficiency of security surveillance camera systems that are static in nature, which are vulnerable to blind spots on the results of their observations. In this research, the surveillance robot is made to resemble the shape of a mars rover robot that is applied to be able to move more freely to stalk areas and be able to navigate on uneven surfaces. The movement of the surveillance robot wheel uses a wireless PS 2 remote control and is driven by a DC motor rotation as its main drive. The connection between the PS2 Remote Control and the surveillance robot is by using the Arduino Uno. In addition, this robot will be equipped with a camera that will send visual surveillance results from the robot to the smartphone.