Planetary Rovers Research Articles

Proprioceptive Slip Detection for Planetary Rovers in Perceptually Degraded Extraterrestrial Environments

Slip detection is of fundamental importance for the safety and efficiency of rovers driving on the surface of extraterrestrial bodies. Current planetary rover slip detection systems rely on visual perception on the assumption that sufficient visual features can be acquired in the environment. However, visual-based methods are prone to suffer in perceptually degraded planetary environments with dominant low terrain features such as regolith, glacial terrain, salt evaporites, and poor lighting conditions such as dark caves and permanently shadowed regions. Relying only on visual sensors for slip detection also requires additional computational power and reduces the rover traversal rate. This paper answers the question of how to detect wheel slippage of a planetary rover without depending on visual perception. In this respect, we propose a slip detection system that obtains its information from a proprioceptive localization framework that is capable of providing reliable, continuous, and computationally efficient state estimation over hundreds of meters. This is accomplished by using zero velocity update, zero angular rate update, and non-holonomic constraints as pseudo-measurement updates on an inertial navigation system framework. The proposed method is evaluated on actual hardware and field tested in a planetary-analog environment. The method achieves greater than 92% slip detection accuracy for distances around 150 m using only an inertial measurement unit and wheel encoders.

The results of analysis of traction dynamics and stability of planetary rover’s motion for determination of special wheel chassis’ boundary design parameters

The analysis of the influence of the design parameters of the rover chassis on the traction dynamics, as well as the static and dynamic stability is presented. The analysis was carried out on the basis of the design parameters of the following rovers: Lunokhod-1, LRV, Sojourner, Spirit and Opportunity, as well as Curiosity. The results of the analysis of the influence of the radius and width of the rover wheel on the specific thrust coefficient are presented. An approach has been formed for determining the permissible displacement of the center of gravity of the rover in the longitudinal direction, which provides static stability. The choice of the formula for determining the maximum permissible speed of movement of automatic research planetary rovers has been substantiated. A number of recommendations have been drawn up for working out the design of the rover at the early stages of design. Boundary values of the rover wheel width, depending on the wheel radius, are proposed. The influence of the load on a separate wheeled propulsion unit on the specific thrust coefficient has been determined.

Design and multi-body dynamic analysis of the Archimede space exploration rover

In this work we present the novel planetary rover prototype “Archimede”. The rover is a four wheel steering vehicle where each wheel is connected to the chassis by means of an articulated leg. These also act as a suspension system, exploiting the function of complex elastic joints named S-Structures, a series of preloaded components constituting the elastic joints. These aggregates have shown to be capable of providing compliance to otherwise stiff structures. The Kane’s method is used to derive an analytical model for the dynamics of the rover, treated as a multi-body system. In the model we implement a lumped-parameters model for the S-Structure as a revolute joint with an applied non-linear torque. The soil is modeled as a rigid body and the wheel–soil interaction follows the Kelvin–Voigt model. The analytical model is validated numerically – via comparison with MSC Adams simulation software – in case of ground impact and obstacle negotiation; the experimental validation is performed on ground impact tests with a Motion Amplification high speed camera and dedicated image processing software. Results show good adherence between the models, thus validating the approach.

Wheel’s Slip Ratio and Sinkage Estimation for Planetary Rovers Moving on Deformable Terrain

Planetary rover plays a significant role in the lunar and Mars exploration missions and wheel’s move status such as sinkage and slip ratio are the critical Factor to estimate the moving ability of the Mars rover. A method is proposed to estimate wheel’s sinkage and skid angle based on terramechanic model and estimate slip ratio based on rover’s dynamic model using Extended Kalman Filter algorithm. The proposed method can avoid the errors caused by Visual Odometry and improves the estimation accuracy of rover state through the fusion with other sensors’ data. The effectiveness of the estimation method for planetary rovers is verified by comparing with the results obtained from dynamic simulation of Mars rovers.

An In-Orbit Stereo Navigation Camera Self-Calibration Method for Planetary Rovers with Multiple Constraints

In order to complete the high-precision calibration of the planetary rover navigation camera using limited initial data in-orbit, we proposed a joint adjustment model with additional multiple constraints. Specifically, a base model was first established based on the bundle adjustment model, second-order radial and tangential distortion parameters. Then, combining the constraints of collinearity, coplanarity, known distance and relative pose invariance, a joint adjustment model was constructed to realize the in orbit self-calibration of the navigation camera. Given the problem of directionality in line extraction of the solar panel due to large differences in the gradient amplitude, an adaptive brightness-weighted line extraction method was proposed. Lastly, the Levenberg-Marquardt algorithm for nonlinear least squares was used to obtain the optimal results. To verify the proposed method, field experiments and in-orbit experiments were carried out. The results suggested that the proposed method was more accurate than the self-calibration bundle adjustment method, CAHVOR method (a camera model used in machine vision for three-dimensional measurements), and vanishing points method. The average error for the flag of China and the optical solar reflector was only 1 mm and 0.7 mm, respectively. In addition, the proposed method has been implemented in China’s deep space exploration missions.

Planetary Rover Path Planning Method with Robustness against Digital Elevation Model's Uncertainty

Planetary rovers need to plan a safe route to ensure the success of their mission. Many missions to the Moon and Mars use existing remote sensing data to plan their exploration routes before launch under the assumption that the data is correct. For example, digital elevation models (DEMs) are biased in their accuracy depending on the density of their source data. Most studies of advance path planning using DEMs do not account for that uncertainty. Therefore, the path planned in advance is not necessarily safe for the actual rover. In this paper, we propose a path planning method that is robust against the uncertainty of terrain data generated from remote sensing data. Simulations using real data confirmed that the route planned by this method is safer than these two conventional methods: 1) route planning that assumes the topographic data is correct, and 2) route planning that adds Gaussian noise to the DEM to generate multiple DEMs and treats their variance as uncertainty.

Behavior Mode Selection based on Environment Map Understanding by Deep Learning for Planetary Rover

Behavior Mode Selection based on Environment Map Understanding by Deep Learning for Planetary Rover

Neural Path Planning With Multi-Scale Feature Fusion Networks

Path planning is critical for planetary rovers that perform observation and exploration missions in unknown and dangerous environment. And due to the communication delay, it is difficult for the planet rover to receive instructions from Earth in time to guide its own movement. In this work, we present a novel neural network-based algorithm to solve the global path planning problem for planetary rovers. Inspired by feature pyramid networks used for object detection, we construct a deep neural network model, termed the Pyramid Path Planning Network (P3N), which has a well-designed backbone that efficiently learns a global feature representation of the environment, and a feature pyramid branch that adaptively fuses multi-scale features from different levels to generate the local feature representation with rich semantic information. The P3N learns environmental dynamics from terrain images of planetary surface taken by satellites, without using additional elevation information to construct an explicit environmental model in advance, and can perform path planning policy after end-to-end training. We evaluate the effectiveness of the proposed method on synthetic grid maps and a realistic data set constructed from the lunar terrain images. Experimental results demonstrate that our P3N has higher prediction accuracy and faster computation speed compared to the baseline methods, and generalize better in large-scale environments.

MarsSim: A high-fidelity physical and visual simulation for Mars rovers

Simulation has deeply infiltrated into the development and validation of planetary rover technologies concerning mobility and autonomy, by providing large amounts of data in a variety of conditions and environments, as well as high-fidelity prototypes. Prevalent approaches for rover simulation focus either on physical behaviors or visual scenarios. In this paper, we present a simulator named MarsSim developed upon ROS/Gazebo platform that supports both physical and visual realistic simulations. The interaction between the wheel and the rough deformable terrain is modeled with improved contact solutions, and the model is integrated into a refined physical simulation architecture as an independent terramechanics plugin. Using multi-scale planetary data and representation models, Martian scenarios are constructed, considering characteristics in terms of the surface, rock and atmosphere. Compared with experiments, the terramechanics plugin shows great modelling accuracy in fitting interactive force/torque and slip-sinkage phenomenon. The simulation of traverses with a six- wheeled planetary rover on Martian landscape are demonstrated with near-photoreal images, coupled with physical-realistic locomotive data under different terrains.

Deterministic Heading-Independent Celestial Localization Measurement Model

<h3>Abstract</h3> Planetary rover navigation frequently relies on dead reckoning and external infrastructure such as orbiting satellites. Celestial navigation techniques combine measurements of the Sun, stars, and gravity to provide autonomous absolute localization. This study examines the performance of digital star sextants (DSS)—a suite of sensors combining a star tracker and an inclinometer—on estimating position on the planetary surface. In particular, we discuss the estimation, calibration, and error analysis for an elevation-only measurement formulation that does not rely on ground-truth heading information. Field tests and Monte Carlo simulations provide validation of the proposed techniques. The real-world performance of the experimental system gives a mean single-orientation error of 296 m. The relative agreement between the predicted and observed error reveals a clear roadmap to help evaluate the impact of prospective sensor improvements on DSS performance.

Occupancy grid mapping for rover navigation based on semantic segmentation

Obstacle mapping is a fundamental building block of the autonomous navigation pipeline of many robotic platforms such as planetary rovers. Nowadays, occupancy grid mapping is a widely used tool for obstacle perception. It foreseen the representation of the environment in evenly spaced cells, whose posterior probability of being occupied is updated based on range sensors measurement. In more classic approaches, the cells are updated to occupied at the point where the ray emitted by the range sensor encounters an obstacle, such as a wall. The main limitation of this kind of methods is that they are not able to identify planar obstacles, such as slippery, sandy, or rocky soils. In this work, we use the measurements of a stereo camera combined with a pixel labeling technique based on Convolution Neural Networks to identify the presence of rocky obstacles in planetary environment. Once identified, the obstacles are converted into a scan-like model. The estimation of the relative pose between successive frames is carried out using ORB-SLAM algorithm. The final step consists of updating the occupancy grid map using the Bayes’ update Rule. To evaluate the metrological performances of the proposed method images from the Martian analogous dataset, the ESA Katwijk Beach Planetary Rover Dataset have been used. The evaluation has been performed by comparing the generated occupancy map with a manually segmented ortomosaic map, obtained by drones’ survey of the area used as reference.

Value Iteration Networks with Double Estimator for Planetary Rover Path Planning.

Path planning technology is significant for planetary rovers that perform exploration missions in unfamiliar environments. In this work, we propose a novel global path planning algorithm, based on the value iteration network (VIN), which is embedded within a differentiable planning module, built on the value iteration (VI) algorithm, and has emerged as an effective method to learn to plan. Despite the capability of learning environment dynamics and performing long-range reasoning, the VIN suffers from several limitations, including sensitivity to initialization and poor performance in large-scale domains. We introduce the double value iteration network (dVIN), which decouples action selection and value estimation in the VI module, using the weighted double estimator method to approximate the maximum expected value, instead of maximizing over the estimated action value. We have devised a simple, yet effective, two-stage training strategy for VI-based models to address the problem of high computational cost and poor performance in large-size domains. We evaluate the dVIN on planning problems in grid-world domains and realistic datasets, generated from terrain images of a moon landscape. We show that our dVIN empirically outperforms the baseline methods and generalize better to large-scale environments.

Rock Segmentation in the Navigation Vision of the Planetary Rovers

Visual navigation is an essential part of planetary rover autonomy. Rock segmentation emerged as an important interdisciplinary topic among image processing, robotics, and mathematical modeling. Rock segmentation is a challenging topic for rover autonomy because of the high computational consumption, real-time requirement, and annotation difficulty. This research proposes a rock segmentation framework and a rock segmentation network (NI-U-Net++) to aid with the visual navigation of rovers. The framework consists of two stages: the pre-training process and the transfer-training process. The pre-training process applies the synthetic algorithm to generate the synthetic images; then, it uses the generated images to pre-train NI-U-Net++. The synthetic algorithm increases the size of the image dataset and provides pixel-level masks—both of which are challenges with machine learning tasks. The pre-training process accomplishes the state-of-the-art compared with the related studies, which achieved an accuracy, intersection over union (IoU), Dice score, and root mean squared error (RMSE) of 99.41%, 0.8991, 0.9459, and 0.0775, respectively. The transfer-training process fine-tunes the pre-trained NI-U-Net++ using the real-life images, which achieved an accuracy, IoU, Dice score, and RMSE of 99.58%, 0.7476, 0.8556, and 0.0557, respectively. Finally, the transfer-trained NI-U-Net++ is integrated into a planetary rover navigation vision and achieves a real-time performance of 32.57 frames per second (or the inference time is 0.0307 s per frame). The framework only manually annotates about 8% (183 images) of the 2250 images in the navigation vision, which is a labor-saving solution for rock segmentation tasks. The proposed rock segmentation framework and NI-U-Net++ improve the performance of the state-of-the-art models. The synthetic algorithm improves the process of creating valid data for the challenge of rock segmentation. All source codes, datasets, and trained models of this research are openly available in Cranfield Online Research Data (CORD).

Sky and Ground Segmentation in the Navigation Visions of the Planetary Rovers.

Sky and ground are two essential semantic components in computer vision, robotics, and remote sensing. The sky and ground segmentation has become increasingly popular. This research proposes a sky and ground segmentation framework for the rover navigation visions by adopting weak supervision and transfer learning technologies. A new sky and ground segmentation neural network (network in U-shaped network (NI-U-Net)) and a conservative annotation method have been proposed. The pre-trained process achieves the best results on a popular open benchmark (the Skyfinder dataset) by evaluating seven metrics compared to the state-of-the-art. These seven metrics achieve 99.232%, 99.211%, 99.221%, 99.104%, 0.0077, 0.0427, and 98.223% on accuracy, precision, recall, dice score (F1), misclassification rate (MCR), root mean squared error (RMSE), and intersection over union (IoU), respectively. The conservative annotation method achieves superior performance with limited manual intervention. The NI-U-Net can operate with 40 frames per second (FPS) to maintain the real-time property. The proposed framework successfully fills the gap between the laboratory results (with rich idea data) and the practical application (in the wild). The achievement can provide essential semantic information (sky and ground) for the rover navigation vision.

Linear Expressions of Drawbar Pull and Driving Torque for Grouser-Wheeled Planetary Rovers Without Terrain Mechanical Parameters

Drawbar pull and driving torque are usually applied to characterize the mobility and energy consumption, respectively, of wheeled planetary rovers (WPRs) traversing sandy terrain. Owing to the complexity of the grouser-terrain interaction, neither can be modeled as a closed-form analytical expression of the terrain mechanical parameters. Complexity limits their online applications. Moreover, it is difficult to estimate the terrain mechanical parameters. To solve these issues, based on equivalent wheel sinkage, both the drawbar pull and driving torque can be modeled as a linear function of physically measurable quantities in the absence of terrain mechanical parameters, which is demonstrated using single-wheel experiments conducted with four types of wheels and two sand types. The influence of a sophisticated grouser-terrain interaction on wheel sinkage can be explicitly determined using the linear driving torque model. Furthermore, the validated linear drawbar pull equation is used to estimate the slope-climbing capability of a four-wheeled planetary rover prototype by computing the slope-climbing coefficient, and the relative error can be limited to 10%. In addition, the wheel driving torque of the rover prototype can also be accurately predicted.

Simultaneous Control of Terrain Adaptation and Wheel Speed Allocation for a Planetary Rover With an Active Suspension System

Active suspensions are important features of many recent planetary rovers. For such a rover, the control strategy is crucial to its performance. This letter presents the control method for a planetary rover equipped with an active suspension system. The control algorithm is based on the estimation of terrain geometry and a mapping relation among the motions of rover body, suspension, and wheels. It realizes a simultaneous control of terrain adaptation and wheel speed allocation. The algorithm allows the posture and height of the rover body to be controlled and the slippage of driving wheels to be reduced while the rover traverse uneven, unstructured terrain. Another advantage of the proposed method is that the control system operates only based on proprioceptive sensors with improved efficiency and moderate memory allocation. The proposed control algorithm is applied to a rover prototype. The experiments conducted in a testing field of rovers validate the proposed algorithm and system.

Dimensional optimization of rocker-bogie suspension for planetary rover based on kinetostatics and terramechanics

Dimensional optimization is important for planetary rovers to reach good performance, such as high mobility, stability, and low energy consumption. The paper presents a dimensional optimization for a planetary rover with rocker-bogie suspension. During the optimization process, the influence of dimensions on the actuation requirements is studied based on kinetostatics and terramechanics. The objective function is built considering the average driving torque requirements in the most common type of windblown terrain in Mars called megaripples. The optimal dimension design is reached through the genetic algorithm, and the influences of dimensional parameters on rover performances are studied by drawing performance atlases. This work realizes the consideration of energy consumption in the design phase of a planetary rover. Finally, the results guide the design of a rover prototype and are validated by a series of experiments.

GMSRI: A Texture-Based Martian Surface Rock Image Dataset

CNN-based Martian rock image processing has attracted much attention in Mars missions lately, since it can help planetary rover autonomously recognize and collect high value science targets. However, due to the difficulty of Martian rock image acquisition, the accuracy of the processing model is affected. In this paper, we introduce a new dataset called “GMSRI” that is a mixture of real Mars images and synthetic counterparts which are generated by GAN. GMSRI aims to provide a set of Martian rock images sorted by the texture and spatial structure of rocks. This paper offers a detailed analysis of GMSRI in its current state: Five sub-trees with 28 leaf nodes and 30,000 images in total. We show that GMSRI is much larger in scale and diversity than the current same kinds of datasets. Constructing such a database is a challenging task, and we describe the data collection, selection and generation processes carefully in this paper. Moreover, we evaluate the effectiveness of the GMSRI by an image super-resolution task. We hope that the scale, diversity and hierarchical structure of GMSRI can offer opportunities to researchers in the Mars exploration community and beyond.

Energy-aware trajectory planning for planetary rovers

Planetary rovers are becoming indispensable for exploration activities and science missions. The rover used in such mission is often limited in its operation time owing to power and computational resources of the rover. In this paper, a trajectory planning method for a planetary rover is proposed that considers vehicle dynamics, and energy management of the rover. The vehicle dynamics is approximated from a dynamic simulation of the rover, which can estimate the power consumption in accordance with terrain traversability of the rover. The power generation of the solar array panel mounted on the rover is also taken into account. The simulation study confirmed the usefulness of the proposed method, especially in scenarios where slopes could be observed, and one result indicated that the energy margin could be improved by 4.1 kJ, 13.9 at maximum.

Automatic Rocks Segmentation Based on Deep Learning for Planetary Rover Images

Accurate detection and segmentation of obstacles is the key to the smooth operation of the planetary rovers and the basic guarantee of scientific exploration mission. The traditional method of rock segmentation based on boundary detector is affected by the change of illumination and dust storms. To address this problem, this paper proposes an improved U-net-based architecture combined with Visual Geometry Group (VGG) and dilated convolutional neural network for the segmentation of rocks from images of planetary exploration rovers. The proposed method also has a contracting path and an expansive path to get high-resolution output similar with U-Net. In the contracting path, the convolution layers in U-Net are replaced by the convolutional layers of VGG16. Inspired by the dilated convolution, the multiscale dilated convolution in the expansive path is proposed. Furthermore, our method is further optimized in the expansive path. To evaluate the proposed method, extensive experiments on segmentation with the Mars dataset have been conducted. The experimental results demonstrate that the proposed method produces accurate semantic segmentation and identification results automatically and outperforms state-of-the-art methods.