Standard methods for autonomous navigation in unstructured terrain are prone to myopic behaviors in long-horizon scenarios. The use of metric maps built from LiDAR or cameras provides necessary local geometry and semantic information but is strictly limited by depth sensing range. By discarding data beyond the mapping horizon robots suffer from suboptimal, short-sighted decisions. To recover this lost information, we focus on extracting long-range traversability-aware frontiers directly from first-person-view (FPV) images. By leveraging satellite imagery, we compute the set of feasible navigation paths for a dataset of image/pose pairs and use them to supervise our network, reducing the need for extensive human demonstration data. We demonstrate that this approach improves performance in long-range off-road navigation over existing methods by more than 10

Autonomous navigation in complex, unstructured outdoor environments requires robots to operate over long ranges without prior maps and limited depth sensing. In such settings, relying solely on geometric frontiers for exploration is often insufficient. In such settings, the ability to reason semantically about where to go and what is safe to traverse is crucial for robust, efficient exploration. This work presents WildOS, a unified system for long-range, open-vocabulary object search that combines safe geometric exploration with semantic visual reasoning. WildOS builds a sparse navigation graph to maintain spatial memory, while utilizing a foundation-model-based vision module, ExploRFM, to score frontier nodes of the graph. ExploRFM simultaneously predicts traversability, visual frontiers, and object similarity in image space, enabling real-time, onboard semantic navigation tasks. The resulting vision-scored graph enables the robot to explore semantically meaningful directions while ensuring geometric safety. Furthermore, we introduce a particle-filter-based method for coarse localization of the open-vocabulary target query, that estimates candidate goal positions beyond the robot's immediate depth horizon, enabling effective planning toward distant goals. Extensive closed-loop field experiments across diverse off-road and urban terrains demonstrate that WildOS enables robust navigation, significantly outperforming purely geometric and purely vision-based baselines in both efficiency and autonomy. Our results highlight the potential of vision foundation models to drive open-world robotic behaviors that are both semantically informed and geometrically grounded. Project Page: https://leggedrobotics.github.io/wildos/

Autonomous robot navigation in off-road environments requires a comprehensive understanding of the terrain geometry and traversability. The degraded perceptual conditions and sparse geometric information at longer ranges make the problem challenging especially when driving at high speeds. Furthermore, the sensing-to-mapping latency and the look-ahead map range can limit the maximum speed of the vehicle. Building on top of the recent work RoadRunner, in this work, we address the challenge of long-range ( +/- 100m ) traversability estimation. Our RoadRunner (M&M) is an end-to-end learning-based framework that directly predicts the traversability and elevation maps at multiple ranges ( +/- 50m , +/- 100m ) and resolutions ( 0.2m , 0.8m ) taking as input multiple images and a LiDAR voxel map. Our method is trained in a self-supervised manner by leveraging the dense supervision signal generated by fusing predictions from an existing traversability estimation stack (X-Racer) in hindsight and satellite Digital Elevation Maps. RoadRunner M&M achieves a significant improvement of up to 50% for elevation mapping and 30% for traversability estimation over RoadRunner, and is able to predict in 30% more regions compared to X-Racer while achieving real-time performance. Experiments on various out-of-distribution datasets also demonstrate that our data-driven approach starts to generalize to novel unstructured environments. We integrate our proposed framework in closed-loop with the path planner to demonstrate autonomous high-speed off-road robotic navigation in challenging real-world environments.

Autonomous off-road navigation faces challenges due to diverse, unstructured environments, requiring robust perception with both geometric and semantic understanding. However, scarce densely labeled semantic data limits generalization across domains. Simulated data helps, but introduces domain adaptation issues. We propose COARSE, a semi-supervised domain adaptation framework for off-road semantic segmentation, leveraging sparse, coarse in-domain labels and densely labeled out-of-domain data. Using pretrained vision transformers, we bridge domain gaps with complementary pixel-level and patch-level decoders, enhanced by a collaborative pseudo-labeling strategy on unlabeled data. Evaluations on RUGD and Rellis-3D datasets show significant improvements of 9.7% and 8.4% respectively, versus only using coarse data. Tests on real-world off-road vehicle data in a multi-biome setting further demonstrate COARSE's applicability.

Autonomous navigation at high speeds in off-road environments necessitates robots to comprehensively understand their surroundings using onboard sensing only. The extreme conditions posed by the off-road setting can cause degraded camera image quality due to poor lighting and motion blur, as well as limited sparse geometric information available from LiDAR sensing when driving at high speeds. In this work, we present RoadRunner, a novel framework capable of predicting terrain traversability and an elevation map directly from camera and LiDAR sensor inputs. RoadRunner enables reliable autonomous navigation, by fusing sensory information, handling of uncertainty, and generation of contextually informed predictions about the geometry and traversability of the terrain while operating at low latency. In contrast to existing methods relying on classifying handcrafted semantic classes and using heuristics to predict traversability costs, our method is trained end-to-end in a self-supervised fashion. The RoadRunner network architecture builds upon popular sensor fusion network architectures from the autonomous driving domain, which embed LiDAR and camera information into a common Bird's Eye View perspective. Training is enabled by utilizing an existing traversability estimation stack to generate training data in hindsight in a scalable manner from real-world off-road driving datasets. Furthermore, RoadRunner improves the system latency by a factor of roughly 4, from 500 ms to 140 ms, while improving the accuracy for traversability costs and elevation map predictions. We demonstrate the effectiveness of RoadRunner in enabling safe and reliable off-road navigation at high speeds in multiple real-world driving scenarios through unstructured desert environments.

The ability to determine the pose of a rover in an inertial frame autonomously is a crucial capability necessary for the next generation of surface rover missions on other planetary bodies. Currently, most on-going rover missions utilize ground-in-the-loop interventions to manually correct for drift in the pose estimate and this human supervision bottlenecks the distance over which rovers can operate autonomously and carry out scientific measurements. In this paper, we present ShadowNav, an autonomous approach for global localization on the Moon with an emphasis on driving in darkness and at nighttime. Our approach uses the leading edge of Lunar craters as landmarks and a particle filtering approach is used to associate detected craters with known ones on an offboard map. We discuss the key design decisions in developing the ShadowNav framework for use with a Lunar rover concept equipped with a stereo camera and an external illumination source. Finally, we demonstrate the efficacy of our proposed approach in both a Lunar simulation environment and on data collected during a field test at Cinder Lakes, Arizona.

Off-road environments pose significant perception challenges for high-speed autonomous navigation due to unstructured terrain, degraded sensing conditions, and domain-shifts among biomes. Learning semantic information across these conditions and biomes can be challenging when a large amount of ground truth data is required. In this work, we propose an approach that leverages a pre-trained Vision Transformer (ViT) with fine-tuning on a small (<500 images), sparse and coarsely labeled (<30 semantic segmentation classes. These classes are fused over time via a novel range-based metric and aggregated into a 3D semantic voxel map. We demonstrate zero-shot out-of-biome 2D semantic segmentation on the Yamaha (52.9 mIoU) and Rellis (55.5 mIoU) datasets along with few-shot coarse sparse labeling with existing data for improved segmentation performance on Yamaha (66.6 mIoU) and Rellis (67.2 mIoU). We further illustrate the feasibility of using a voxel map with a range-based semantic fusion approach to handle common off-road hazards like pop-up hazards, overhangs, and water features.

There has been an increase in interest in missions that drive significantly longer distances per day than what has currently been performed. For example, Endurance-A proposes driving several kilometers a day in order to reach its target traverse of 2000 km in 4 years. Additionally, some of these proposed missions, including Endurance-A and rovers for Permanently Shadowed Regions (PSRs) of the moon, require autonomous driving and absolute localization in darkness. Endurance-A proposes to drive 1200 km of its total traverse at night. The lack of natural light available during these missions limits what can be used as visual landmarks and the range at which landmarks can be observed. In order for planetary rovers to traverse long-ranges, onboard absolute localization is critical to the rover's ability to maintain its planned trajectory and avoid known hazardous regions. Currently, the localization performed onboard rovers is relative to the rover's frame of reference and is performed through the integration of wheel and visual odometry and inertial measurements. To accomplish absolute localization, a "ground-in-the-loop" (GITL) operation is performed wherein a human operator matches local maps or images from onboard with orbital images and maps. This GITL operation places a limit on the distance that can be driven in a day to a few hundred meters, which is the distance that the rover can maintain acceptable localization error via relative methods. Previous work has shown that using craters as landmarks is a promising approach for performing absolute localization on the moon during the day. In this work we present a method of absolute localization that utilizes craters as landmarks and matches detected crater edges on the surface with known craters in orbital maps. We focus on a localization method based on a perception system which has an external illuminator and a stereo camera. While other methods based on lidar exist, lidar is not currently planned for deployment on the current proposed nighttime and PSR missions. In this paper, we evaluate (1) both monocular and stereo based surface crater edge detection techniques, (2) methods of scoring the crater edge matches for optimal localization, and (3) localization performance on simulated Lunar surface imagery at night. We demonstrate that this technique shows promise for maintaining absolute localization error of less than 10 m required for most planetary rover missions.

We previously presented Soil Property and Object Classification (SPOC), a machine learning-based terrain classi-fier for Mars rovers, for automatically segmenting rover images by its surface type such as sand and bedrock. This paper presents a number of practical improvements to pave the way for potential future onboard deployment. First, we achieved 97.0 % overall pixel accuracy, evaluated against the classification generated by human experts on images from Mars Science Lab-oratory (MSL) missions. The substantial increase in accuracy was primarily enabled by the sheer volume of data used for training; we created a new large-scale dataset of Martian terrain labels, namely AI4Mars, which contains more than 400k labels contributed by citizen scientists for ~50k images taken by the Mars Exploration Rovers (MER) and Mars Science Laboratory (MSL) rover. Second, we demonstrated that SPOC can quickly adapt to a new mission landed on a previously unseen site. Specifically, we pretrained a model with MER and MSL data from the AI4Mars dataset and then adapted to the Mars 2020 Rover (M2020) by feeding a small volume of data between Sol 0 and 157; the adapted model was tested on Sol 200–203 and resulted in 84.2 % overall pixel accuracy and 93.4 % reliability (recall) for detecting sand, the most concerning class for rover's traversability. Third, we found that pretraining can substan-tially mitigate the decline of accuracy over time. We showed that the performance of a SPOC model pretrained with the ImageNet dataset and then trained by MSL images only up to Sol 390 remains comparable to a model trained by images up to Sol 1689 on the test data after Sol 1689. Fourth, we reimplemented SPOC with a light-weight convolutional neural network (CNN), MobileNetV2, which typically runs within tens of milliseconds (ms) on mobile processors such as Qualcomm's Snapdragon. Finally, we released the AI4Mars dataset to the public to encourage open innovation.

Onboard localization capabilities for planetary rovers to date have used relative navigation, by integrating combinations of wheel odometry, visual odometry, and inertial measurements during each drive to track position relative to the start of each drive. At the end of each drive, a “ground-in-the-loop” (GITL) interaction is used to get a position update from human operators in a more global reference frame, by matching images or local maps from onboard the rover to orbital reconnaissance images or maps of a large region around the rover's current position. Autonomous rover drives are limited in distance so that accumulated relative navigation error does not risk the possibility of the rover driving into hazards known from orbital images. In practice, this limits drives to a few hundred meters between GITL cycles. Several rover mission concepts have recently been studied that require much longer drives between GITL cycles, particularly for the Moon. This includes lunar rover mission concepts that involve (1) driving mostly in sunlight at low latitudes, (2) driving in permanently shadowed regions near the south pole, and (3) a mixture of day and night driving in mid-latitudes. These concepts include total traverse distance requirements of up to 1,800 km in 4 Earth years, with individual drives of several kilometers between stops for downlink. These concepts require greater autonomy to minimize GITL cycles to enable such large range; onboard global localization is a key element of such autonomy. Multiple techniques have been studied in the past for onboard rover global localization, but a satisfactory solution has not yet emerged. For the Moon, the ubiquitous craters offer a new possibility, which involves mapping craters from orbit, then recognizing crater landmarks with cameras and/or a lidar onboard the rover. This approach is applicable everywhere on the Moon, does not require high resolution stereo imaging from orbit as some other approaches do, and has potential to enable position knowledge with order of 5 to 10 m accuracy at all times. This paper describes our technical approach to crater-based lunar rover localization and presents initial results on crater detection using 3-D point cloud data from onboard lidar or stereo cameras, as well as using shading cues in monocular onboard imagery.

Highly accurate localization of planetary robotic explorers is crucial for robust, efficient, and safe path planning in unknown and extreme planetary environments. In these environments, where satellite-based radio-navigation systems are unavailable, global localization can be achieved by relying on registration of ground imagery to an orbital map, X-band Doppler radio transmissions, or direct observation in satellite imagery. While these methods have proven to be effective, they rely heavily on a human-in-the-loop. This paper is concerned with autonomous global localization of planetary robotic explorers in extreme and GPS-denied environments by relying on semantic segmentation of ground imagery. Using a trained convolutional neural network (CNN), saliency maps are obtained from semantic segmentation of ground imagery. These maps are then registered to projected views of the terrain elevation maps in the rover's general region of operation to find the optimal match that places tight constraints on the pose of the robot in a Mars body-fixed coordinate system. We provide details on the use of the DeepLab V3+ framework for semantic image segmentation of Martian landscape imagery, including fine-tune training of existing models on domain specific data. Furthermore, we provide performance analysis of the proposed method on a Martian landscape dataset obtained by NASA's Perseverance rover, and discuss the limitations of the proposed method and future research directions.

Navigating off-road with a fast autonomous vehicle depends on a robust perception system that differentiates traversable from non-traversable terrain. Typically, this depends on a semantic understanding which is based on supervised learning from images annotated by a human expert. This requires a significant investment in human time, assumes correct expert classification, and small details can lead to misclassification. To address these challenges, we propose a method for predicting high- and low-risk terrains from only past vehicle experience in a self-supervised fashion. First, we develop a tool that projects the vehicle trajectory into the front camera image. Second, occlusions in the 3D representation of the terrain are filtered out. Third, an autoencoder trained on masked vehicle trajectory regions identifies low- and high-risk terrains based on the reconstruction error. We evaluated our approach with two models and different bottleneck sizes with two different training and testing sites with a four-wheeled off-road vehicle. Comparison with two independent test sets of semantic labels from similar terrain as training sites demonstrates the ability to separate the ground as low-risk and the vegetation as high-risk with 81.1% and 85.1% accuracy.

Deep learning has quickly become a necessity for self-driving vehicles on Earth. In contrast, the self-driving vehicles on Mars, including NASA’s latest rover, Perseverance, which is planned to land on Mars in February 2021, are still driven by classical machine vision systems. Deep learning capabilities, such as semantic segmentation and object recognition, would substantially benefit the safety and productivity of ongoing and future missions to the red planet. To this end, we created the first large-scale dataset, AI4Mars, for training and validating terrain classification models for Mars, consisting of ~326K semantic segmentation full image labels on 35K images from Curiosity, Opportunity, and Spirit rovers, collected through crowdsourcing. Each image was labeled by ~10 people to ensure greater quality and agreement of the crowdsourced labels. It also includes ~1.5K validation labels annotated by the rover planners and scientists from NASA’s MSL (Mars Science Laboratory) mission, which operates the Curiosity rover, and MER (Mars Exploration Rovers) mission, which operated the Spirit and Opportunity rovers. We trained a DeepLabv3 model on the AI4Mars training dataset and achieved over 96% overall classification accuracy on the test set. The dataset is made publicly available.1 2

Deegan Atha, a graduating senior in electrical engineering and a future engineer, is interested in human-centered design and developing technology that helps students engage and be successful in STEM.

Corrosion is a major defect in structural systems that has a significant economic impact and can pose safety risks if left untended. Currently, an inspector visually assesses the condition of a structure to identify corrosion. This approach is time-consuming, tedious, and subjective. Robotic systems, such as unmanned aerial vehicles, paired with computer vision algorithms have the potential to perform autonomous damage detection that can significantly decrease inspection time and lead to more frequent and objective inspections. This study evaluates the use of convolutional neural networks for corrosion detection. A convolutional neural network learns the appropriate classification features that in traditional algorithms were hand-engineered. Eliminating the need for dependence on prior knowledge and human effort in designing features is a major advantage of convolutional neural networks. This article presents different convolutional neural network–based approaches for corrosion assessment on metallic surfaces. The effect of different color spaces, sliding window sizes, and convolutional neural network architectures are discussed. To this end, the performance of two pretrained state-of-the-art convolutional neural network architectures as well as two proposed convolutional neural network architectures are evaluated, and it is shown that convolutional neural networks outperform state-of-the-art vision-based corrosion detection approaches that are developed based on texture and color analysis using a simple multilayered perceptron network. Furthermore, it is shown that one of the proposed convolutional neural networks significantly improves the computational time in contrast with state-of-the-art pretrained convolutional neural networks while maintaining comparable performance for corrosion detection.

Regular inspection of civil infrastructure and mechanical systems is crucial for safe operations. Corrosion is an important type of deterioration in structural systems that can lead to catastrophic effects if untended. Manual inspection is currently the predominant method of inspection that is time-consuming, costly, tedious, and subjective. A less time consuming and inexpensive alternative to current corrosion monitoring methods is the use of optical instrumentation (e.g. digital cameras). Due to the recent advances in using Convolutional Neural Networks (CNNs), the vision-based classification performance of computers has been improved significantly. This study evaluates the use of a CNN for corrosion detection. The effect of different sliding window sizes used for classification is evaluated. The experimental results show that the performance of the CNN outperforms state-of-the-art vision-based corrosion detection algorithms