Highly Accurate Visual Method of Mars Terrain Classification for Rovers Based on Novel Image Features.

It is important for Mars exploration rovers to achieve autonomous and safe mobility over rough terrain. Terrain classification can help rovers to select a safe terrain to traverse and avoid sinking and/or damaging the vehicle. Mars terrains are often classified using visual methods. However, the accuracy of terrain classification has been less than 90% in read operations. A high-accuracy vision-based method for Mars terrain classification is presented in this paper. By analyzing Mars terrain characteristics, novel image features, including multiscale gray gradient-grade features, multiscale edges strength-grade features, multiscale frequency-domain mean amplitude features, multiscale spectrum symmetry features, and multiscale spectrum amplitude-moment features, are proposed that are specifically targeted for terrain classification. Three classifiers, K-nearest neighbor (KNN), support vector machine (SVM), and random forests (RF), are adopted to classify the terrain using the proposed features. The Mars image dataset MSLNet that was collected by the Mars Science Laboratory (MSL, Curiosity) rover is used to conduct terrain classification experiments. The resolution of Mars images in the dataset is 256 × 256. Experimental results indicate that the RF classifies Mars terrain at the highest level of accuracy of 94.66%.

Learning-Based End-to-End Path Planning for Lunar Rovers with Safety Constraints.

Path planning is an essential technology for lunar rover to achieve safe and efficient autonomous exploration mission, this paper proposes a learning-based end-to-end path planning algorithm for lunar rovers with safety constraints. Firstly, a training environment integrating real lunar surface terrain data was built using the Gazebo simulation environment and a lunar rover simulator was created in it to simulate the real lunar surface environment and the lunar rover system. Then an end-to-end path planning algorithm based on deep reinforcement learning method is designed, including state space, action space, network structure, reward function considering slip behavior, and training method based on proximal policy optimization. In addition, to improve the generalization ability to different lunar surface topography and different scale environments, a variety of training scenarios were set up to train the network model using the idea of curriculum learning. The simulation results show that the proposed planning algorithm can successfully achieve the end-to-end path planning of the lunar rover, and the path generated by the proposed algorithm has a higher safety guarantee compared with the classical path planning algorithm.

Integrated Navigation System Design for Micro Planetary Rovers: Comparison of Absolute Heading Estimation Algorithms and Nonlinear Filtering.

This paper provides algorithms to fuse relative and absolute microelectromechanical systems (MEMS) navigation sensors, suitable for micro planetary rovers, to provide a more accurate estimation of navigation information, specifically, attitude and position. Planetary rovers have extremely slow speed (~1 cm/s) and lack conventional navigation sensors/systems, hence the general methods of terrestrial navigation may not be applicable to these applications. While relative attitude and position can be tracked in a way similar to those for ground robots, absolute navigation information is hard to achieve on a remote celestial body, like Moon or Mars, in contrast to terrestrial applications. In this study, two absolute attitude estimation algorithms were developed and compared for accuracy and robustness. The estimated absolute attitude was fused with the relative attitude sensors in a framework of nonlinear filters. The nonlinear Extended Kalman filter (EKF) and Unscented Kalman filter (UKF) were compared in pursuit of better accuracy and reliability in this nonlinear estimation problem, using only on-board low cost MEMS sensors. Experimental results confirmed the viability of the proposed algorithms and the sensor suite, for low cost and low weight micro planetary rovers. It is demonstrated that integrating the relative and absolute navigation MEMS sensors reduces the navigation errors to the desired level.

New species of redbait from the Philippines (Teleostei, Emmelichthyidae, Emmelichthys).

We describe a new species of redbait in the genus Emmelichthys collected from fish markets on Panay and Cebu islands in the Visayas region of the Philippines. The species is externally similar to E.struhsakeri but is diagnosable by two prominent fleshy papillae associated with the cleithrum and fewer pectoral-fin rays (18-19 vs. 19-21) and gill rakers (30-33 vs. 34-41). Additionally, mitochondrial DNA differentiates this taxon from other species of Emmelichthys. We generate mitochondrial genomes for two of the three type specimens and several other emmelichthyids to place the new taxon in a phylogenetic context. Analysis of the protein-coding mitochondrial loci calls into question the monophyly of two emmelichthyid genera (Emmelichthys and Erythrocles) and highlights the need for subsequent analyses targeting the intrarelationships of the Emmelichthyidae.

Enabling robustness to failure with modular field robots.

Actuator failure on a remotely deployed robot results in decreased efficiency or even renders it inoperable. Robustness to these failures will become critical as robots are required to be more independent and operate out of the range of repair. To address these challenges, we present two approaches based on modular robotic architecture to improve robustness to actuator failure of both fixed-configuration robots and modular reconfigurable robots. Our work uses modular reconfigurable robots capable of modifying their style of locomotion and changing their designed morphology through ejecting modules. This framework improved the distance travelled and decreased the effort to move through the environment of simulated and physical robots. When the deployed robot was allowed to change its locomotion style, it showed improved robustness to actuator failure when compared to a robot with a fixed controller. Furthermore, a robot capable of changing its locomotion and design morphology statistically outlasted both tests with a fixed morphology. Testing was carried out using a gazebo simulation and validated in multiple tests in the field. We show for the first time that ejecting modular failed components can improve the overall mission length.

Multi-robot cooperation for lunar In-Situ resource utilization.

This paper presents a cooperative, multi-robot solution for searching, excavating, and transporting mineral resources on the Moon. Our work was developed in the context of the Space Robotics Challenge Phase 2 (SRCP2), which was part of the NASA Centennial Challenges and was motivated by the current NASA Artemis program, a flagship initiative that intends to establish a long-term human presence on the Moon. In the SRCP2 a group of simulated mobile robots was tasked with reporting volatile locations within a realistic lunar simulation environment, and excavating and transporting these resources to target locations in such an environment. In this paper, we describe our solution to the SRCP2 competition that includes our strategies for rover mobility hazard estimation (e.g. slippage level, stuck status), immobility recovery, rover-to-rover, and rover-to-infrastructure docking, rover coordination and cooperation, and cooperative task planning and autonomy. Our solution was able to successfully complete all tasks required by the challenge, granting our team sixth place among all participants of the challenge. Our results demonstrate the potential of using autonomous robots for autonomous in-situ resource utilization (ISRU) on the Moon. Our results also highlight the effectiveness of realistic simulation environments for testing and validating robot autonomy and coordination algorithms. The successful completion of the SRCP2 challenge using our solution demonstrates the potential of cooperative, multi-robot systems for resource utilization on the Moon.

An embarrassingly simple approach for visual navigation of forest environments.

Navigation in forest environments is a challenging and open problem in the area of field robotics. Rovers in forest environments are required to infer the traversability of a priori unknown terrains, comprising a number of different types of compliant and rigid obstacles, under varying lighting and weather conditions. The challenges are further compounded for inexpensive small-sized (portable) rovers. While such rovers may be useful for collaboratively monitoring large tracts of forests as a swarm, with low environmental impact, their small-size affords them only a low viewpoint of their proximal terrain. Moreover, their limited view may frequently be partially occluded by compliant obstacles in close proximity such as shrubs and tall grass. Perhaps, consequently, most studies on off-road navigation typically use large-sized rovers equipped with expensive exteroceptive navigation sensors. We design a low-cost navigation system tailored for small-sized forest rovers. For navigation, a light-weight convolution neural network is used to predict depth images from RGB input images from a low-viewpoint monocular camera. Subsequently, a simple coarse-grained navigation algorithm aggregates the predicted depth information to steer our mobile platform towards open traversable areas in the forest while avoiding obstacles. In this study, the steering commands output from our navigation algorithm direct an operator pushing the mobile platform. Our navigation algorithm has been extensively tested in high-fidelity forest simulations and in field trials. Using no more than a 16 × 16 pixel depth prediction image from a 32 × 32 pixel RGB image, our algorithm running on a Raspberry Pi was able to successfully navigate a total of over 750 m of real-world forest terrain comprising shrubs, dense bushes, tall grass, fallen branches, fallen tree trunks, small ditches and mounds, and standing trees, under five different weather conditions and four different times of day. Furthermore, our algorithm exhibits robustness to changes in the mobile platform's camera pitch angle, motion blur, low lighting at dusk, and high-contrast lighting conditions.

ROMA: A Database of Rock Reflectance Spectra for Martian In Situ Exploration.

The ROMA database (ROck reflectance for MArtian in situ exploration, https://roma.univ-lyon1.fr) provides the reflectance spectra between 0.4 and 3-4 µm of various terrestrial, Martian, and synthetic samples, as a means to document reference measurements for comparison with data acquired by visible and near-infrared spectrometers on planetary surfaces, with a focus on current and future Martian observations by the Perseverance (Mars 2020 mission) and Rosalind Franklin (ExoMars) rovers. The main specificity of this database is to include a significant fraction of spectra of unprocessed rock, which are more realistic analogs and often have different spectral features than the fine powders more commonly analyzed in reflectance spectroscopy. Additionally, these measurements were acquired with a spectrometer whose spot size is similar to those of the SuperCam instrument (Mars 2020 mission) at a few meters from a target. Supplementary information are provided in the ROMA database: higher-level data (such as absorption band parameters) as well as sample mineralogy estimated by whole-rock X-ray diffraction analyses. Future comparisons with this database will help improve the interpretation of spectral measurements acquired on the Martian surface. This work introduces the aim of the library and its current state, but additional data on intact natural rock surfaces will likely be added in the future.

Novelty detection in rover-based planetary surface images using autoencoders.

In the domain of planetary science, novelty detection is gaining attention because of the operational opportunities it offers, including annotated data products and downlink prioritization. Using a variational autoencoder (VAE), this work improves upon state-of-the-art novelty detection performance in the context of Martian exploration by > 7 % (measured by the area under the receiver operating characteristic curve (ROC AUC)). Autoencoders, especially VAEs, perform well across all classes of novelties defined for Martian exploration. VAEs are shown to have high recall in the Martian context, making them particularly useful for on-ground processing. Convolutional autoencoders (CAEs), on the other hand, demonstrate high precision making them good candidates for onboard downlink prioritization. In our implementation adversarial autoencoders (AAEs) are also shown to perform on par with state-of-the-art. Dimensionality reduction is a key feature of autoencoders for novelty detection. In this study the impact of dimensionality reduction on detection quality is explored, showing that both VAEs and AAEs achieve comparable ROC AUCs to CAEs despite observably poorer (blurred) image reconstructions; this is observed both in Martian data and in lunar analogue data.

Slip-Based Autonomous ZUPT through Gaussian Process to Improve Planetary Rover Localization.

The zero-velocity update (ZUPT) algorithm provides valuable state information to maintain the inertial navigation system (INS) reliability when stationary conditions are satisfied. Employing ZUPT along with leveraging non-holonomic constraints can greatly benefit wheeled mobile robot dead-reckoning localization accuracy. However, determining how often they should be employed requires consideration to balance localization accuracy and traversal rate for planetary rovers. To address this, we investigate when to autonomously initiate stops to improve wheel-inertial odometry (WIO) localization performance with ZUPT. To do this, we propose a 3D dead-reckoning approach that predicts wheel slippage while the rover is in motion and forecasts the appropriate time to stop without changing any rover hardware or major rover operations. We validate with field tests that our approach is viable on different terrain types and achieves a 3D localization accuracy of ~97% over 650 m drives on rough terrain.

The Mars 2020 Engineering Cameras and Microphone on the Perseverance Rover: A Next-Generation Imaging System for Mars Exploration.

The Mars 2020 Perseverance rover is equipped with a next-generation engineering camera imaging system that represents an upgrade over previous Mars rover missions. These upgrades will improve the operational capabilities of the rover with an emphasis on drive planning, robotic arm operation, instrument operations, sample caching activities, and documentation of key events during entry, descent, and landing (EDL). There are a total of 16 cameras in the Perseverance engineering imaging system, including 9 cameras for surface operations and 7 cameras for EDL documentation. There are 3 types of cameras designed for surface operations: Navigation cameras (Navcams, quantity 2), Hazard Avoidance Cameras (Hazcams, quantity 6), and Cachecam (quantity 1). The Navcams will acquire color stereo images of the surface with a 96 ∘ × 73 ∘ field of view at 0.33 mrad/pixel. The Hazcams will acquire color stereo images of the surface with a 136 ∘ × 102 ∘ at 0.46 mrad/pixel. The Cachecam, a new camera type, will acquire images of Martian material inside the sample tubes during caching operations at a spatial scale of 12.5 microns/pixel. There are 5 types of EDL documentation cameras: The Parachute Uplook Cameras (PUCs, quantity 3), the Descent stage Downlook Camera (DDC, quantity 1), the Rover Uplook Camera (RUC, quantity 1), the Rover Descent Camera (RDC, quantity 1), and the Lander Vision System (LVS) Camera (LCAM, quantity 1). The PUCs are mounted on the parachute support structure and will acquire video of the parachute deployment event as part of a system to characterize parachute performance. The DDC is attached to the descent stage and pointed downward, it will characterize vehicle dynamics by capturing video of the rover as it descends from the skycrane. The rover-mounted RUC, attached to the rover and looking upward, will capture similar video of the skycrane from the vantage point of the rover and will also acquire video of the descent stage flyaway event. The RDC, attached to the rover and looking downward, will document plume dynamics by imaging the Martian surface before, during, and after rover touchdown. The LCAM, mounted to the bottom of the rover chassis and pointed downward, will acquire 90 ∘ × 90 ∘ FOV images during the parachute descent phase of EDL as input to an onboard map localization by the Lander Vision System (LVS). The rover also carries a microphone, mounted externally on the rover chassis, to capture acoustic signatures during and after EDL. The Perseverance rover launched from Earth on July 30th, 2020, and touchdown on Mars is scheduled for February 18th, 2021.

AMADEE-18: Vision-Based Unmanned Aerial Vehicle Navigation for Analog Mars Mission (AVI-NAV).

As a part of the AMADEE-18 analog Mars mission, designed to study challenges associated with human-based exploration of the Red Planet, we focused our team efforts on testing means to localize an unmanned aerial vehicle (UAV) on Mars. Robot helicopters, such as the one selected for a technology demonstration as a part of NASA's Mars 2020 mission, are small and their performance is computationally limited. An essential aspect of navigation and path planning of an autonomous helicopter is accurate localization of the robot. In the absence of a global positioning system, a computationally efficient localization technology that can be applied on Mars is visual-inertial odometry (VIO). The AMADEE-18 mission provided an opportunity to test the feasibility of a state-of-the-art VIO algorithm and the camera in a Mars-like analog environment. The flight datasets included different terrain structures that challenged the functionality of VIO algorithms. The experiment has yielded valuable insights into the desired surface structure, texture, and mission times for surface relative navigation of UAV on Mars.

In Situ Geochronology on Mars and the Development of Future Instrumentation.

We review the in situ geochronology experiments conducted by the Mars Science Laboratory mission's Curiosity rover to understand when the Gale Crater rocks formed, underwent alteration, and became exposed to cosmogenic radiation. These experiments determined that the detrital minerals in the sedimentary rocks of Gale are ∼4 Ga, consistent with their origin in the basalts surrounding the crater. The sedimentary rocks underwent fluid-moderated alteration 2 Gyr later, which may mark the closure of aqueous activity at Gale Crater. Over the past several million years, wind-driven processes have dominated, denuding the surfaces by scarp retreat. The Curiosity measurements validate radiometric dating techniques on Mars and guide the way for future instrumentation to make more precise measurements that will further our understanding of the geological and astrobiological history of the planet.

Astrobiology - an opposing view.

The use of quantum computers and Artificial Intelligence (AI) is imperative for use in space exploration and astrobiology investigations. Considerable progress has been made since the commencement of origin of life laboratory and theoretical studies in the mid 20th century. However, the sheer amount of data amassed to date in all these studies including exoplanetary and astrobiological studies is enormous and increasing steadily. Thus, there is the need for AI and quantum computers. As AI develops, it will become crucial in the development of the statistical and database programs that are indispensable to analyze the huge quantity of cumulative data. Diverse biotic and geochemical processes have been shown to produce methane on the Earth. Elsewhere in the solar system, on other planets (e.g. Mars) and moons (e.g. Titan), as well as on exoplanets, abiotic processes are considered the primary sources of methane. Astronomers and astro-biologists infer that the presence of methane supports the possibility of the presence of at least microbial life. In addition, on the Earth, there are also degradative reactions that include smog-related compounds and hazes that are produced as artefacts of intrinsic methane geochemistry as well as due to human footprint. Astronomers and astro-biologists envision life, away from the Earth, elsewhere in the solar system and on exoplanets, to occur under conditions similar or related to terrestrial life (goldilocks zone) conditions. These properties that are compatible with life as we know it on the Earth, include planetary orbits, gravitation, star radiant energy, presence of liquid water, and compatible temperatures and pressures, found on Earth. Generally, extraterrestrial life is also considered to resemble the biochemistry, molecular biology, and physiology of life on Earth - thus the focus on detection of supposed biosignatures of microbial life that resemble the Earth's. Nevertheless a crucial factor is absent in these deliberations - viruses. On the Earth, viruses that infect Archaea and bacteria form local and widespread global ecosystems. These viruses play a crucial role and facilitate the molecular transfer of host genes among various hosts. This essential function is underestimated in evolutionary as well as astrobiological speculations. Thus, it is of substantial importance to consider the roles that viruses may have played during the origin of life as well as in any exobiology.