Safe autonomous navigation requires reliable estimation of environmental traversability. Traditional methods have relied on semantic or geometry-based approaches with human-defined thresholds, but these methods often yield unreliable predictions due to the inherent subjectivity of human supervision. While self-supervised approaches enable robots to learn from their own experience, they still face a fundamental challenge: the positive-only learning problem. To address these limitations, recent studies have employed Positive-Unlabeled (PU) learning, where the core challenge is identifying positive samples without explicit negative supervision. In this work, we propose GSAT, which addresses these limitations by constructing a positive hypersphere in latent space to classify traversable regions through anomaly detection without requiring additional prototypes (e.g., unlabeled or negative). Furthermore, our approach employs joint learning of anomaly classification and traversability prediction to more efficiently utilize robot experience. We comprehensively evaluate the proposed framework through ablation studies, validation on heterogeneous real-world robotic platforms, and autonomous navigation demonstrations in simulation environments.
NavMoE: Hybrid Model- and Learning-based Traversability Estimation for Local Navigation via Mixture of Experts
Department of Computer Science, University of Maryland（大学计算机科学系）；Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）；Georgia Institute of Technology（佐治亚理工学院）
Learning Traversability for Long Horizon Off-Road Navigation
J. Mike Walker ’66 Department of Mechanical Engineering, Texas A&M University（德克萨斯农工大学J. Mike Walker '66机械工程系）；DEVCOM Army Research laboratory（陆军研究实验室）
STONE Dataset: A Scalable Multi-Modal Surround-View 3D Traversability Dataset for Off-Road Robot Navigation
Interdisciplinary Program in Artificial Intelligence, Seoul National University（人工智能交叉学科项目，首尔国立大学）；Department of Electrical and Computer Engineering, Seoul National University（电气与计算机工程系，首尔国立大学）
Learning to Drive on Mars: Visual Multimodal Traversability Estimation for Off-World Navigation
University of Southern California（南加州大学）；Jet Propulsion Laboratory, California Institute of Technology（加州理工学院喷气推进实验室）；Washington State University（华盛顿州立大学）
Continual Learning for Traversability Prediction with Uncertainty-Aware Adaptation
Ulsan National Institute of Science and Technology（蔚山国立科学技术院）；Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich (TUM)（慕尼黑机器人与机器智能研究所（MIRMI），慕尼黑工业大学（TUM））
Trinity: Unifying Class-Agnostic Terrain and Semantic Segmentation for Unstructured Outdoor Environments by Leveraging Synthetic Data
Institute of Robotics and Mechatronics, German Aerospace Center (DLR)（机器人与机电系统研究所，德国航空航天中心（DLR））；Federal Institute of Technology Zurich (ETH Zurich)（苏黎世联邦理工学院（ETH Zurich））；Robotics and AI Institute (RAI)（机器人与人工智能研究所（RAI））
RoadRunner -- Learning Traversability Estimation for Autonomous Off-road Driving
Jet Propulsion Laboratory (JPL)（喷气推进实验室）；California Institute of Technology (Caltech)（加州理工学院）；Swiss Federal Institute of Technology (ETH Zürich)（苏黎世联邦理工学院）
Institute of Human and Machine Cognition（人类与机器认知研究所）；University of West Florida（西佛罗里达大学）；Pusan National University（釜山国立大学）；Boardwalk Robotics, Inc.（Boardwalk机器人公司）
We present a planning framework designed for humanoid navigation over challenging terrain. This framework is designed to plan a traversable, smooth, and collision-free path using a 2.5D height map. The planner is comprised of two stages. The first stage consists of an A* planner which reasons about traversability using terrain features. A novel cost function is presented which encodes the bipedal gait directly into the graph structure, enabling natural paths that are robust to small gaps in traversability. The second stage is an optimization framework which smooths the path while further impro…
Under shared autonomy, wheelchair users expect vehicles to provide safe and comfortable rides while following users high-level navigation plans. To find such a path, vehicles negotiate with different terrains and assess their traversal difficulty. Most prior works model surroundings either through geometric representations or semantic classifications, which do not reflect perceived motion intensity and ride comfort in downstream navigation tasks. We propose to model ride comfort explicitly in traversability analysis using proprioceptive sensing. We develop a self-supervised learning framework …
Baidu Research（百度研究院）；University of Maryland, College Park（马里兰大学帕克分校）
We present a terrain traversability mapping and navigation system (TNS) for autonomous excavator applications in an unstructured environment. We use an efficient approach to extract terrain features from RGB images and 3D point clouds and incorporate them into a global map for planning and navigation. Our system can adapt to changing environments and update the terrain information in real-time. Moreover, we present a novel dataset, the Complex Worksite Terrain (CWT) dataset, which consists of RGB images from construction sites with seven categories based on navigability. Our novel algorithms i…
Topological mapping for traversability-aware long-range navigation in off-road terrain
Center for Intelligent Machines, McGill University（麦吉尔大学智能机器中心）；Gault Nature Reserve（戈尔特自然保护区）；CMLabs（CMLabs公司）；National Canadian Robotics Network（加拿大国家机器人网络）
Johns Hopkins University Applied Physics Laboratory（约翰斯·霍普金斯大学应用物理实验室）
Robot navigation traditionally relies on building an explicit map that is used to plan collision-free trajectories to a desired target. In deformable, complex terrain, using geometric-based approaches can fail to find a path due to mischaracterizing deformable objects as rigid and impassable. Instead, we learn to predict an estimate of traversability of terrain regions and to prefer regions that are easier to navigate (e.g., short grass over small shrubs). Rather than predicting collisions, we instead regress on realized error compared to a canonical dynamics model. We train with an on-policy …
This work reports on developing a deep inverse reinforcement learning method for legged robots terrain traversability modeling that incorporates both exteroceptive and proprioceptive sensory data. Existing works use robot-agnostic exteroceptive environmental features or handcrafted kinematic features; instead, we propose to also learn robot-specific inertial features from proprioceptive sensory data for reward approximation in a single deep neural network. Incorporating the inertial features can improve the model fidelity and provide a reward that depends on the robot's state during deployment…
ZeST: A VLM-based Zero-Shot Traversability Navigation for Unknown Environments
Field Robotics Engineering and Science Hub (FRESH), Illinois Autonomous Farm, University of Illinois at Urbana-Champaign (UIUC), IL（伊利诺伊大学厄巴纳-香槟分校）；Mobile Robotics Group, São Carlos School of Engineering, University of São Paulo (EESC-USP), São Carlos, SP, Brazil（圣保罗大学）
PRISM: Multimodal Terrain Mapping for Rover Navigation in Unstructured Environments
SnT, University of Luxembourg（卢森堡大学安全、可靠性和信任跨学科中心）；Department of Automation and Systems Engineering, Universidad de Málaga, Andalucía Tech（马拉加大学自动化与系统工程系，安达卢西亚技术大学）
RAEM: Robust Autonomous Exploration for Multi-Floor Environments with a Quadruped Robot
AI Chip Center for Emerging Smart Systems（新兴智能系统AI芯片中心）；InnoHK Centers（创新香港中心）；HongKong University of Science and Technology（香港科技大学）；Southeast University（东南大学）；City University of Hong Kong（香港城市大学）；Huazhong University of Science and Technology（华中科技大学）；University of Hong Kong（香港大学）；Wuhan University（武汉大学）
In this paper, an stereo-based traversability analysis approach for all terrains in off-road mobile robotics, e.g. Unmanned Ground Vehicles (UGVs) is proposed. This approach reformulates the problem of terrain traversability analysis into two main problems: (1) 3D terrain reconstruction and (2) terrain all surfaces detection and analysis. The proposed approach is using stereo camera for perception and 3D reconstruction of the terrain. In order to detect all the existing surfaces in the 3D reconstructed terrain as superpixel surfaces (i.e. segments), an image segmentation technique is applied u…
Umeå University（于默奥大学）；Swedish University of Agricultural Sciences（瑞典农业科学大学）
We present a method that uses high-resolution topography data of rough terrain, and ground vehicle simulation, to predict traversability. Traversability is expressed as three independent measures: the ability to traverse the terrain at a target speed, energy consumption, and acceleration. The measures are continuous and reflect different objectives for planning that go beyond binary classification. A deep neural network is trained to predict the traversability measures from the local heightmap and target speed. To produce training data, we use an articulated vehicle with wheeled bogie suspensi…
Despite the progress in legged robotic locomotion, autonomous navigation in unknown environments remains an open problem. Ideally, the navigation system utilizes the full potential of the robots' locomotion capabilities while operating within safety limits under uncertainty. The robot must sense and analyze the traversability of the surrounding terrain, which depends on the hardware, locomotion control, and terrain properties. It may contain information about the risk, energy, or time consumption needed to traverse the terrain. To avoid hand-crafted traversability cost functions we propose to …
