Various Types Of Terrain Research Articles

JPSSL: SAR Terrain Classification Based on Jigsaw Puzzles and FC-CRF

Effective features play an important role in synthetic aperture radar (SAR) image interpretation. However, since SAR images contain a variety of terrain types, it is not easy to extract effective features of different terrains from SAR images. Deep learning methods require a large amount of labeled data, but the difficulty of SAR image annotation limits the performance of deep learning models. SAR images have inevitable geometric distortion and coherence speckle noise, which makes it difficult to extract effective features from SAR images. If effective semantic context features cannot be learned for SAR images, the extracted features struggle to distinguish different terrain categories. Some existing terrain classification methods are very limited and can only be applied to some specified SAR images. To solve these problems, a jigsaw puzzle self-supervised learning (JPSSL) framework is proposed. The framework comprises a jigsaw puzzle pretext task and a terrain classification downstream task. In the pretext task, the information in the SAR image is learned by completing the SAR image jigsaw puzzle to extract effective features. The terrain classification downstream task is trained using only a small number of labeled data. Finally, fully connected conditional random field processing is performed to eliminate noise points and obtain a high-quality terrain classification result. Experimental results on three large-scene high-resolution SAR images confirm the effectiveness and generalization of our method. Compared with the supervised methods, the features learned in JPSSL are highly discriminative, and the JPSSL achieves good classification accuracy when using only a small amount of labeled data.

Ski-orienteering: a scientific perspective on a multi-dimensional challenge

Ski-orienteering, which combines cross-country skiing with orienteering, dates back to the late 1800s, with the first World Championships in 1975. While researchers have explored the physiological and biomechanical determinants of success in cross-country skiing and orienteering separately in detail, scientific knowledge concerning ski-orienteering remains limited. Based on the information that is presently available together with interviews with elite ski-orienteers, we explore here for the first time the historical development, physiological, biomechanical, and psychological demands, certain training strategies, and future prospects and challenges associated with this sport, including its potential to become an Olympic event. A demanding endurance sport (with racing times of 12–120 min), ski-orienteering requires both considerable aerobic and anaerobic capacity, as well as well-trained upper and lower body muscles. In addition, ski-orienteering demands advanced skiing technique on various types of terrain, with frequent changes between sub-techniques, on both wide and narrow tracks and with numerous turns on downhill terrain. Moreover, success in this sport requires accurate and rapid orienteering—the ability to navigate a complex network of ski tracks with numerous intersections/crossings in a manner designed to pass the multiple control points in the order indicated on the map as rapidly as possible, i.e., advanced spatial cognition and highly developed navigational skills. Thus, ski-orienteering requires training designed to improve both relevant physiological characteristics and orienteering skills, which should become the focus of future interdisciplinary research on this complex sport.

Research on DEM geomorphic factor terrain recognition algorithm using probabilistic neural networks based on tactile systems

The accurate recognition of unknown terrain by robots plays a vital role in completing walking tasks. Haptic-based terrain recognition methods have their own advantages over visual, audio, and vibration-based terrain recognition methods. With the increasing complexity of robot application scenarios, there are still many technical difficulties in using tactile systems to recognize terrain. For real-time terrain detection technology, how to improve the accuracy of terrain recognition and shorten recognition time based on tactile systems is an urgent problem to be solved. In this paper, the digital elevation model (DEM) geomorphic factor terrain recognition algorithm using probabilistic neural networks (DGFTRA-PNN) based on tactile force-feedback system is proposed to solve this problem. First, the tactile force-feedback system is mounted on the foot ends of the hexapod robot to collect terrain data. Second, the feasibility of using DEM geomorphic factors as terrain features to identify terrain was demonstrated. Third, DGFTRA-PNNs are established based on the different walking gait of the hexapod robot, achieving terrain recognition based on DEM feature values. Finally, the accuracy and speed of DGFTRA-PNN were verified through field experiments. Compared with the terrain recognition algorithm based on back propagation neural network (BP) and extreme learning machine (ELM) algorithm, the DGFTRA-PNN has advantages in terms of terrain recognition accuracy and recognition time: the average recognition accuracy for various types of terrain is 96%, and the calculation time is 0.04 seconds.

Cyber Physical Systems: A Brief Survey and an Application of a MIR (Mobile Industrial Robot) for Inspection

This work refers to the realization of a Cyber Physical System (CPS), i.e. modeling, analysis, and integration of a MIR (Mobile Industrial Robot) platform with an industrial robot, in order to test its operating conditions. MIRs, although usually employed in industrial environment, can be used in sectors such as inspection, assistance, defense, production, remote exploration as well as search and rescue. In addition of being programmable, thanks to the provision of sensors and navigation systems, they can adapt in real time to various environmental contexts and purposes of use. The objective of the paper is to create a CPS of a MIR that can basically perform two fundamental actions. The first one is to carry out movements in predominantly external environments and therefore with various types of terrain. The second fundamental action is the pick and place operations, i.e. the robot must be able to carry out the manipulation of objects.

Predictive machine learning for optimal energy management in sustainable transportation systems

This study explores the use of predictive machine learning techniques to enhance energy management in sustainable transportation systems, with a specific emphasis on electric vehicles (EVs). The analysis of EV specifications has shown a wide variety of battery capacities, ranging from 55 kWh to 75 kWh. These capacities have a direct impact on the energy storage capacity and the possible driving range of the vehicles. The range of vehicle weights, ranging from 1400 kg to 1700 kg, emphasized the possible effects on energy consumption rates and overall efficiency. The performance capabilities were shown with maximum speeds ranging from 160 km/h to 200 km/h. The energy consumption rates ranged from 0.18 kWh/km to 0.25 kWh/km, suggesting different levels of efficiency. An analysis of energy management data revealed that the lengths traveled varied from 180 km to 220 km, while the average speeds ranged from 50 km/h to 60 km/h. These variations directly affected the rates at which energy was used. The vehicles exhibited higher efficiency metrics by attaining energy consumption rates of 4.0 km/kWh to 5.6 km/kWh. The analysis of ambient variables indicated temperature fluctuations ranging from 20°C to 30°C, as well as a variety of terrain types that impact driving conditions and energy requirements. Predictive machine learning models demonstrated high accuracies, with Mean Absolute Error (MAE) values ranging from 0.13 to 0.18 kWh/km, Root Mean Squared Error (RMSE) values ranging from 0.18 to 0.22 kWh/km, and R-squared (R^2) scores ranging from 0.80 to 0.88. These results emphasize the need of using predictive machine learning to estimate energy consumption, optimize energy management systems, and address sustainable transportation concerns in order to improve the efficiency and sustainability of electric vehicles.

Vibration-Based Recognition of Wheel-Terrain Interaction for Terramechanics Model Selection and Terrain Parameter Identification for Lugged-Wheel Planetary Rovers.

Identifying terrain parameters is important for high-fidelity simulation and high-performance control of planetary rovers. The wheel-terrain interaction classes (WTICs) are usually different for rovers traversing various types of terrain. Every terramechanics model corresponds to its wheel-terrain interaction class (WTIC). Therefore, for terrain parameter identification of the terramechanics model when rovers traverse various terrains, terramechanics model switching corresponding to the WTIC needs to be solved. This paper proposes a speed-independent vibration-based method for WTIC recognition to switch the terramechanics model and then identify its terrain parameters. In order to switch terramechanics models, wheel-terrain interactions are divided into three classes. Three vibration models of wheels under three WTICs have been built and analyzed. Vibration features in the models are extracted and non-dimensionalized to be independent of wheel speed. A vibration-feature-based recognition method of the WTIC is proposed. Then, the terrain parameters of the terramechanics model corresponding to the recognized WTIC are identified. Experiment results obtained using a Planetary Rover Prototype show that the identification method of terrain parameters is effective for rovers traversing various terrains. The relative errors of estimated wheel-terrain interaction force with identified terrain parameters are less than 16%, 12%, and 9% for rovers traversing hard, gravel, and sandy terrain, respectively.

Robust and adaptive terrain classification and gait event detection system

Real-time gait event detection (GED) system can be utilized for gait analysis and tracking fitness activities. GED for various types of terrains (e.g., stair-walk, uneven surfaces, etc.) is still an open research problem. This study presents an inertial sensor-based approach for real-time GED system that works for diverse terrains in an uncontrolled environment. The GED system classifies three types of terrains, i.e., flat-walk, stair-ascend and stair-descend, with an average classification accuracy of 99%. It also accurately detects various gait events, including, toe-strike, heel-rise, toe-off, and heel-strike. It is computationally efficient, implemented on a low-cost microcontroller, works in real-time and can be used in portable rehabilitation devices for use in dynamic environments.

Enhanced flood water depth estimation from Sentinel-1A images

ABSTRACT Floods, as a natural disaster, have severe consequences for all aspects of life and society, including but not limited to damaging harvests and transportation systems, and causing epidemic diseases. Estimating flood water depths has been a topic of great interest for several decades. Finding an effective solution to this problem is crucial for accurately estimating the impact of floods and making informed decisions to mitigate their consequences. The paper presents a novel approach to estimate flood water depths in Quang Binh province, Vietnam, by utilizing an improved Otsu algorithm to classify each image pixel as either water or non-water, and then applying the FwDET interpolation algorithm to compute the flood depth of each classified water pixel. The improved algorithm can improve the accuracy of water classification when compared to the traditional Otsu method by automatically dividing images into subregions of varying sizes, which are suitable for optimal Otsu computation.The estimated results for the study area in Quang Binh province were validated using ground measurement station data and demonstrated the relatively high accuracy of water classification (ranging from 91.4% to 92%) and estimated flood water depth (85.26%). Based on the positive results obtained from the investigation of the complex mountainous area mentioned above, it can be inferred that the proposed method has the potential to be applied to estimate flood depths in various types of terrains.

Analysis of Motion Characteristics and Stability of Mobile Robot Based on a Transformable Wheel Mechanism

In this research, we propose a novel wheel-legged mobile robot to address the problems of insufficient obstacle-crossing performance and poor motion flexibility of mobile robots in non-structural environments. Firstly, we designed the transformable wheel mechanism and tail adaptive mechanism. Secondly, the kinematic model of the robot is established and solved by analyzing the whole motion and wheel-legged switching motion for the operation requirements under different road conditions. By synthesizing the constraint relationships among the modules and analyzing the robot’s obstacle-crossing abilities, we systematically established the mechanical model of the robot when it encounters obstacles. Thirdly, we studied the stability of the robot based on the stable cone method in the case of slope and unilateral transformation wheel deployment and achieved the tipping condition in the critical state. Finally, we used ADAMS software to simulate and analyze the driving process of the robot in various types of terrain and obstacles in order to verify that it has superior performance through obstacles and motion flexibility. The analysis shows that the robot can passively adapt to various complex and variable obstacle-filled terrains with obstacle heights which are much higher than its center of gravity range. The results of the study can provide a reference for the structural optimization and the obstacle-crossing performance improvement of mobile robots.

A Reduced-Order-Model-Based Motion Selection Strategy in a Leg-Wheel Transformable Robot

This article reports on a model-based methodology for a leg-wheel transformable robot to autonomously determine the use of the wheeled or legged mode based on environmental RGB-Depth information. A concentric and reduced-order dual-leg-wheel model was developed to explore the dynamic interactions between the leg-wheel and terrain. The simulation results revealed that terrain height variation acts as the key factor in determining the model's terrain negotiability; therefore, it was utilized as the decision index for leg-wheel motion selection. To facilitate real-time motion selection on the empirical robot, a two-step selection strategy utilizing RGB-Depth information was proposed. The first step utilized RGB images to classify seven types of terrain. If the classified terrain was potentially rough, the second step utilized depth images to compute the terrain height variation, which was then compared to the index derived by the dual-leg-wheel model to select the final operation mode. The strategy was implemented on a leg-wheel transformable robot and experimentally validated on various types of terrain. The results confirm that the robot's behavior closely resembled the model's prediction, and using the proposed strategy to select leg-wheel motion in the robot yielded the most energy efficient locomotion.

MA3: Model-Accuracy Aware Anytime Planning with Simulation Verification for Navigating Complex Terrains

Off-road and unstructured environments often contain complex patches of various types of terrain, rough elevation changes, deformable objects, etc. An autonomous ground vehicle traversing such environments experiences physical interactions that are extremely hard to model at scale and thus very hard to predict. Nevertheless, planning a safely traversable path through such an environment requires the ability to predict the outcomes of these interactions instead of avoiding them. One approach to doing this is to learn the interaction model offline based on collected data. Unfortunately, though, this requires large amounts of data and can often be brittle. Alternatively, models using physics-based simulators can generate large data and provide a reliable prediction. However, they are very slow to query online within the planning loop. This work proposes an algorithmic framework that utilizes the combination of a learned model and a physics-based simulation model for fast planning. Specifically, it uses the learned model as much as possible to accelerate planning while sparsely using the physics-based simulator to verify the feasibility of the planned path. We provide a theoretical analysis of the algorithm and its empirical evaluation showing a significant reduction in planning times.

Powered Prosthesis Locomotion on Varying Terrains: Model-Dependent Control With Real-Time Force Sensing

Lower-limb prosthesis wearers are more prone to falling than non-amputees. Powered prostheses can reduce this instability of passive prostheses. While shown to be more stable in practice, powered prostheses generally use model-independent control methods that lack formal guarantees of stability and rely on heuristic tuning. Recent work overcame one of the limitations of model-based prosthesis control by developing a class of provably stable prosthesis controllers that only require the human interaction forces with the prosthesis, yet these controllers have not been realized with sensing of these forces in the control loop. Our work realizes the first model-dependent prosthesis knee controller that uses in-the-loop on-board real-time force sensing at the interface between the human and prosthesis and at the ground. The result is an optimization-based control methodology that formally guarantees stability while enabling human-prosthesis walking on a variety of terrain types. Experimental results demonstrate this force-based controller outperforms similar controllers not using force sensors, improving tracking across 4 terrain types.

Change in Force-based Metrics during Outdoor 2- and 4-Mile Runs.

The purpose of this study was to determine if peak ground reaction force (GRF), loading rate (LR), and impulse metrics change across an outdoor run using force sensing insoles. We hypothesize that over the course of the run there would be a decline in limb symmetry for all measures and a decrease in LR and GRF values. Thirty healthy participants (15 male, 15 female) were recruited for a two-visit study during which a 2- or 4-mile run was completed on the first visit and the other run distance was completed on the second visit (order was randomized). Force data were collected at 100 Hz for the duration of the run. Peak GRF, impulse, LR, and limb symmetry indices (LSI) of these variables were calculated at 25%, 50%, and 75% of the run. GRF decreased over the course of the runs, but the GRF LSI remained unchanged. No changes in LR were detected over the 2- or 4-mile run for either limb. The impulse LSI during the 2-mile run did indicate decreased symmetry from 25% of the run to 50% of the run, the LR LSI improved, and there was no difference in GRF LSI or any of the LSI metrics during the 4-mile run. We posit that the lack in change in LSI was due to the courses/distance not inducing fatigue in our population. Future studies should investigate the effect of outdoor fatigue protocols and various types of terrain on force metrics and potential injury risk factors.

Mars curiosity rover mobility trends during the first 7 years

AbstractNASA's Mars Science Laboratory (MSL) Curiosity rover landed on Mars on August 6, 2012. In the 7 years between landing and August 6, 2019 (sol 2488), Curiosity has driven 21,318.5 m over a variety of terrain types and slopes, employing multiple drive modes with varying amounts of onboard autonomy. Curiosity's drive distances each sol have ranged from its shortest drive of 2.6 cm to its longest drive of 142.5 m, with an average drive distance of 28.9 m. Real‐time human intervention is not possible during Curiosity's drives due to the latency in uplinking commands and downlinking telemetry. Instead, the operations team relies on Curiosity's fault protection, autonomous navigation, and visual odometry software to keep the rover safe during drives. During its first 7 years on Mars, Curiosity has attempted 738 drives. While 622 drives ran to completion, 116 drives were prevented or stopped early by Curiosity's fault protection software. The primary risks to mobility success have been wheel damage, wheel entrapment, progressive wheel sinkage, and the potential for hardware or cable failures that result in an inability to command one or more steer or drive actuators. In this paper, we describe Curiosity's mobility subsystem, mobility trends over the first 21.3 km of the mission, operational aspects of mobility fault protection, risks to continued mobility success, and risk mitigation strategies.

Design and Control of 7-DOF Omni-directional Hexapod Robot

Abstract Legged robots have great potential to travel across various types of terrain. Their many degrees of freedom enable them to navigate through difficult terrains, narrow spaces or various obstacles and they can move even after losing a leg. However, legged robots mostly move quite slowly. This paper deals with the design and construction of an omni-directional seven degrees of freedom hexapod (i.e., six-legged) robot, which is equipped with omnidirectional wheels (two degrees of freedom are used, one for turning the wheel and one for the wheel itself) usable on flat terrain to increase travel speed and an additional coxa joint that makes the robot more robust when climbing inclined terrains. This unique combination of omnidirectional wheels and additional coxa joint makes the robot not only much faster but also more robust in rough terrains and allows the robot to ride inclined terrains up to 40 degrees and remain statically stable in slopes up to 50 degrees. The robot is controlled by a terrain adaptive movement controller which adjusts the movement speed and the gait of the robot according to terrain conditions.

LocoGear: Locomotion Analysis of Robotic Landing Gear for Multicopters

Nowadays, there are few unmanned aerial vehicles (UAVs) that are capable of landing on uneven surfaces or moving on the complex ground. A drone having both of these functionalities can significantly improve its performance in accomplishing difficult tasks, such as monitoring and exploring various types of terrain, searching for survivors, and delivering medical aid or repair kits in an unstructured dynamic environment, e.g., rescue operation following an earthquake. This article presents a motion analysis of the gait of an adaptive landing platform for multicopters. This landing gear has four robotic legs facilitated with torque sensors in the knee joints. Though it had been developed to provide adaptive landing on uneven surfaces, we decided to exploit the system for terrain locomotion purposes. For this purpose, we have analyzed the center of mass trajectory to evaluate the possible trajectory of the robot. Based on the result of this experimental analysis, we propose a LocoGear, a novel algorithm for locomotion of UAV equipped with the robotic landing gear. The servomotor torques were estimated using Lagrangian dynamic formulation and kinetostatic methods. We conducted experiments to verify the LocoGear approach based on feedforward control that proves the capability of landing gear to move along the desired trajectory. We achieved the robot motion along the straight line with the standard deviation of length in each step of 9.8 mm and standard deviation in yaw of 9°.

Simulation model of a transport vehicle with a fixed-ratio transmission and a flywheel energy storage in case of random external action

The purpose of this study is to evaluate the dynamic qualities and efficiency of a heavy-duty transport vehicle equipped with a mechanical transmission, using a combined power plant (CPP) with a flywheel energy storage (FES), establish an acceptable level of power reduction of the main internal combustion engine (ICE), determine the range of installed power of the FES drive and its average value of efficiency, as well as the calculation of the level of required energy capacity of the flywheel when driving in various types of terrain. A universal technique for simulating statistical modeling of external disturbances acting on the transport vehicle has been developed. Using the developed methodology, the vehicles’ characteristics have been compared according to the criterion of average speed and an assessment of the efficiency of the use of CPP has been carried out. The results obtained allow us to carry out a comparative analysis of vehicles equipped with a conventional or combined power plant with a random external action of the road, as well as optimize their parameters.

The operational impact of nodes on large-scale seismic operations

The global acceptance of recording nodes in seismic operations is gradually increasing. Many regions of the world have either switched or are in the process of transitioning to nodal operations. Several factors have encouraged this transition among seismic contractors and their respective clients. High among these factors are cost of operations, flexibility of operations in a variety of terrain types, higher HSE requirements of field personnel, changes in the methods of acquisition and the demand for higher density shooting and single sensor recording. In Canada and the United States, the transition to nodal operations for seismic data recording is nearly complete. Whereas, adoption of nodes on the very large-scale projects of the Middle East and North Africa is in its infancy. This is partially due to the existence of enormous volumes of cable equipment in the inventories of seismic contractors but is also due in part to the fact that these projects span many years of continuous operations. The motivation to increase the recorded trace density while decreasing HSE exposure, cost of operations and environmental impact is driving new interest in nodal operations on large-scale projects. Nodes promise to positively impact many if not all of these motivational factors during this transition.

Permafrost distribution in steep rock slopes in Norway: measurements, statistical modelling and implications for geomorphological processes

Abstract. Permafrost in steep rock slopes has been increasingly studied since the early 2000s in conjunction with a growing number of rock slope failures, which likely resulted from permafrost degradation. In Norway, rock slope destabilization is a widespread phenomenon and a major source of risk for the population and infrastructure. However, a lack of precise knowledge of the permafrost distribution in steep slopes hinders the assessment of its role in these destabilizations. This study proposes the first nationwide permafrost probability map for the steep slopes of Norway (CryoWall map). It is based on a multiple linear regression model fitted with multi-annual rock surface temperature (RST) measurements, collected at 25 rock slope sites, spread across a latitudinal transect (59–69∘ N) over mainland Norway. The CryoWall map suggests that discontinuous permafrost widely occurs above 1300–1400 and 1600–1700 m a.s.l. in the north and south rock faces of southern Norway (59∘ N), respectively. This lower altitudinal limit decreases in northern Norway (70∘ N) by about 500±50 m, with a more pronounced decrease for south faces, as a result of the insolation patterns largely driven by midnight sun in summer and polar night in winter. Similarly, the mean annual RST differences between north and south faces of similar elevation range around 1.5 ∘C in northern Norway and 3.5 ∘C in southern Norway. The CryoWall map is evaluated against direct ice observations in steep slopes and discussed in the context of former permafrost studies in various types of terrain in Norway. We show that permafrost can occur at much lower elevations in steep rock slopes than in other terrains, especially in north faces. We demonstrate that the CryoWall map is a valuable basis for further investigations related to permafrost in steep slopes in terms of both practical concerns and fundamental science.

Universal mathematical model of SAR signals for natural surfaces

The implementation of the basic version of the universal mathematical model of the formation of reflected signals for various airborne radar systems, including the synthetic antenna aperture radar, when working on natural surfaces are discussed in the article. A number of parameters are required to study, which must be taken into account for the correct modeling of echo signals, which must then be processed to calculate radar images. A method for constructing such a mathematical model in MATLAB is presented with some modeling results for a homogeneous rough surface and two typical pulse and continuous modulation signals. But the facet parameter structure of the simulated surface can take into account the possibilities of representing various types of terrain and objects created by man.