A5077137296- Robotics and Sensor-Based Localization
- Robotic Path Planning Algorithms
- Modular Robots and Swarm Intelligence
- Robotic Locomotion and Control
- 3D Surveying and Cultural Heritage
- Robotics and Automated Systems
- UAV Applications and Optimization
- Insect Pheromone Research and Control
- Radiation Detection and Scintillator Technologies
- Underwater Vehicles and Communication Systems
- Distributed Control Multi-Agent Systems
- Advanced Image and Video Retrieval Techniques
- Control and Dynamics of Mobile Robots
- Target Tracking and Data Fusion in Sensor Networks
- Indoor and Outdoor Localization Technologies
- Optimization and Search Problems
- Medical Image Segmentation Techniques
- Soft Robotics and Applications
- Adaptive Control of Nonlinear Systems
- Advanced MEMS and NEMS Technologies
- Advanced Optical Sensing Technologies
- Advanced Radiotherapy Techniques
- Planetary Science and Exploration
- Guidance and Control Systems
- Remote Sensing and LiDAR Applications
University of Nevada, Reno
2018-2022
Norwegian University of Science and Technology
2022
Abstract Autonomous exploration of subterranean environments remains a major challenge for robotic systems. In response, this paper contributes novel graph‐based path planning method that is attuned to key topological properties settings, such as large‐scale tunnel‐like networks and complex multibranched topologies. Designed both aerial legged robots, the proposed structured around bifurcated local‐ global‐planner architecture. The local planner utilizes rapidly exploring random graph...
Autonomous exploration of subterranean environments constitutes a major frontier for robotic systems, as underground settings present key challenges that can render robot autonomy hard to achieve. This problem has motivated the DARPA Subterranean Challenge, where teams robots search objects interest in various environments. In response, we CERBERUS system-of-systems, unified strategy using legged and flying robots. Our proposed approach relies on ANYmal quadraped primary robots, exploiting...
This paper presents a novel strategy for autonomous graph-based exploration path planning in subterranean environments. Attuned to the fact that settings, such as underground mines, are often large-scale networks of narrow tunnel-like and multi-branched topologies, proposed planner is structured around bifurcated local-and global-planner architecture. The local employs rapidly-exploring random graph reliably efficiently identify collision-free paths optimize an gain within subspace....
Resilient pose estimation for autonomous systems, and especially small unmanned aerial robots, is one of the core capabilities required these robots to perform their assigned tasks in a reliable efficient manner. Different sensing modalities have been utilized robot process, particularly GPS-denied environments. However, as are deployed more complex environments, such subterranean mines tunnels, different can become degraded parts environment due diversity sensor perception challenges...
In this work we present an integrated approach for autonomous navigation and mapping in underground mines using aerial robots. Underground a set of critical challenges as they are not only GPS-denied by nature, but their environmental circumstances also lead to severe sensor degradation (due combinations darkness, dust, smoke), localizability problems textureless surfaces locally self-similar structure), while presenting stringent conditions result certain very narrow geometries. To address...
The ability of autonomous exploration and mapping using aerial robots in GPS-denied dark visually-degraded environments is critical multiple applications including those inspection, exploration, search rescue tunnel environments, monitoring mines, underground voids. This paper presents the design a multi-modal unit tailored to such missions. When combined with our previous work receding horizon volumetric path planner, enables robotic autonomy without any prior knowledge environment....
In this paper we present a comprehensive solution for autonomous underground mine rescue using aerial robots. particular, new class of Micro Aerial Vehicles are equipped with the ability to localize and map in subterranean settings, explore unknown environments on their own, perform detection localization objects interest purposes (i.e., "human survivors" associated such as "backpacks", "smartphones" or "tools"). For GPS-denied mapping visually-degraded (e.g., smoke-filled during an...
In this paper the problem of autonomous navigation aerial robots through obscurants is considered. As visible spectrum cameras and most LiDAR technologies provide degraded data in such conditions, localization approached fusion thermal camera with inertial sensor cues. particular, a long-wave infrared employed combined an measurement unit. The intrinsic extrinsic parameters are appropriately calibrated, Extended Kalman Filter framework that uses direct photometric feedback order to achieve...
This paper presents a path planning strategy for the autonomous exploration of subterranean environments. Tailored to specific challenges and particularities underground settings, especially fact that they often are extremely large in scale, tunnel-like, narrow multibranched, proposed method employs bifurcated local- global-planning design enable efficiency solution resourcefulness. The local planner builds on top minimum-length random trees efficiently identifies collision-free paths...
This work presents the design, hardware realization, autonomous exploration and object detection capabilities of RMF-Owl, a new collision-tolerant aerial robot tailored for resilient subterranean exploration. The system is custom built underground with focus on collision tolerance, autonomy robust localization mapping, alongside high-performance path planning in confined, obstacle-filled topologically complex environments. Moreover, RMF-Owl offers ability to search, detect locate objects...
This paper details the system and methods developed to enable autonomous nuclear radiation source localization mapping using aerial robots in GPS-denied environments. A Thallium-doped Cesium Iodide (CsI(Tl)) scintillator a Silicon Photomultiplier are combined with custom-built electronics for counting spectroscopy, provided measurements pose-annotated visual-inertial enabling operation Provided this capability, strategy radioactive localization, as well active search path planning was...
GPS-denied localization of aerial robots in sensing-degraded environments and especially dark, textureless dustor smoked-filled settings is rendered particularly hard. An alternative to utilize Long Wave Infrared thermal vision which unaffected by darkness can penetrate most obscurants. However, utilization mostly considered combination with traditional visual-inertial odometry frameworks are made for grayscale visible-light camera images fail the full (e.g. 14-bit) radiometric information a...
In this work the challenge of autonomous navigation, exploration and mapping in underground mines using aerial robots is considered. Despite paramount importance mine accessing, relevant challenges sensor degradation (darkness, dust, smoke) broadly stringent navigation conditions due to particularly narrow geometries across very long drifts render typical planning methods insufficient. Towards a comprehensive solution, we present extensively field test variety robot realizations implementing...
This article presents the CERBERUS robotic system-of-systems, which won DARPA Subterranean Challenge Final Event in 2021. The was organized by with vision to facilitate novel technologies necessary reliably explore diverse underground environments despite grueling challenges they present for autonomy. Due their geometric complexity, degraded perceptual conditions combined lack of GNSS support, austere navigation conditions, and denied communications, subterranean settings render autonomous...
This article presents the CERBERUS robotic system-of-systems, which won DARPA Subterranean Challenge Final Event in 2021. The was organized by with vision to facilitate novel technologies necessary reliably explore diverse underground environments despite grueling challenges they present for autonomy. Due their geometric complexity, degraded perceptual conditions combined lack of GPS support, austere navigation conditions, and denied communications, subterranean settings render autonomous...
This paper details the system and methods designed to enable autonomous estimation of distributed nuclear radiation fields within complex possibly GPS-denied environments. A sensing apparatus consisting three radially placed Thallium-doped Cesium Iodide (CsI(Tl)) scintillators Silicon Photomultipliers (SiPm) combined with custom- built pulse counting circuitry is provided readings are pose-annotated using LiDAR-based localization. Given this capacity, a method that utilizes intensity first...
In this paper the problem of contact-based navigation path planning for aerial robots is considered with goal enabling autonomous in-contact operation on surfaces that can be highly anomalous. Such a capacity prove critical in inspection through contact missions, as well when flying robot tasked to operate very narrow environments rendering safe free-flight impossible. To achieve objective, beyond sliding contact, new locomotion primitive introduced, namely azimuth rotations perpendicular...
In this paper we present the complete system design for an aerial robot capable of autonomous exploration inside natural cave environments. Cave networks involve diverse and complicated topologies, complex geometries degraded conditions rendering process robotic mapping a particularly daunting adventure. response to these challenges, outline core algorithmic modules relating localization mapping, path planning control, alongside developed perception computing solutions onboard tailored...
This work presents the design, development and autonomous navigation of Resilient Micro Flyer, a new type collision-tolerant small aerial robot tailored to traversing searching within highly confined environments including manhole-sized tubes. The is particularly lightweight agile, while it implements design which renders resilient during forcible interaction with environment. overall rigid system enhanced through elastic passive flaps ensuring smoother more compliant collision was...