A5001914278- Planetary Science and Exploration
- Space Exploration and Technology
- Astro and Planetary Science
- Space Satellite Systems and Control
- Robotics and Automated Systems
- Human-Automation Interaction and Safety
- Spaceflight effects on biology
- Robotics and Sensor-Based Localization
- Spacecraft Design and Technology
- Spacecraft and Cryogenic Technologies
- Advanced Image and Video Retrieval Techniques
- Robotic Path Planning Algorithms
- Distributed systems and fault tolerance
- Infrared Target Detection Methodologies
- 3D Surveying and Cultural Heritage
- AI-based Problem Solving and Planning
- Social Robot Interaction and HRI
- Teleoperation and Haptic Systems
- Space exploration and regulation
- Space Science and Extraterrestrial Life
- Underwater Vehicles and Communication Systems
- Image Enhancement Techniques
- Methane Hydrates and Related Phenomena
- Satellite Image Processing and Photogrammetry
- Robot Manipulation and Learning
Ames Research Center
2015-2024
National Aeronautics and Space Administration
2019-2022
National Institute of Standards and Technology
2021
Honeybee Robotics (United States)
2021
Stanford University
2016
Search for Extraterrestrial Intelligence
2010
Los Alamos National Laboratory
2008
Carnegie Mellon University
2001
Small flying robots represent a rapidly emerging family of robotic technologies with aerial capabilities that enable unique forms assistance in variety collaborative tasks. Such tasks will necessitate interaction humans close proximity, requiring designers consider human perceptions regarding and acting within environments. We explore the design space explicit robot communication flight intentions to nearby viewers. apply constraints behaviors, using biological airplane as inspiration,...
Vehicle detection from aerial images is becoming an increasingly important research topic in surveillance, traffic monitoring and military applications. The system described this paper focuses on vehicle rural environments its applications to oil gas pipeline threat detection. Automatic by unmanned vehicles (UAV) will replace current patrol services that rely pilot visual inspection of the low altitude high risk flights are often restricted weather conditions. Our compares a set feature...
When planning planetary rover missions it is useful to develop intuition and skills driving in, quite literally, alien environments before incurring the cost of reaching said locales. Simulators make possible operate in that have physical characteristics target locations without expense overhead extensive tests. To end, NASA Ames Open Robotics collaborated on a Lunar simulator based open source Gazebo simulation platform leveraging ROS (Robotic Operating System)components. The was integrated...
Smart SPHERES is a prototype free-flying space robot based on the platform. can be remotely operated by astronauts inside spacecraft, or mission controllers ground. We developed to perform variety of intravehicular activities (IVA), such as operations International Space Station (ISS). These IVA tasks include environmental monitoring surveys (radiation, sound levels, etc.), inventory, and mobile camera work. In this paper, we first discuss motivation for robots. then describe development...
Horizon line is a promising visual cue which can be exploited for robot localization or geo-localization. Prominent approaches to horizon detection rely on edge as pre-processing step inherently non-stable approach due parameter choices and underlying assumptions. We present novel uses machine learning Dynamic Programming (DP) extract the from classification map instead of an map. The key idea assigning score each pixel, interpreted likelihood pixel belonging line, representing multi-stage...
Craters are among the most abundant features on surface of many planets with great importance for planetary scientists. They reveal chronology information about and may be used autonomous spacecraft navigation landing. Although numerous research efforts have been carried out in field crater detection, existing detection algorithms (CDAs) only helpful a limited number applications. A promising approach involves two main steps: 1) hypothesis generation (HG) 2) verification (HV). During HG,...
Simulated operations during a recent NASA robotic field test demonstrated realtime computation of performance metrics for human-robot interaction that includes adjustable autonomy.
In planning for future exploration missions, architecture and study teams have made numerous assumptions about how crew can be telepresent on a planetary surface by remotely operating robots from space (i.e. flight vehicle or deep habitat). These include estimates of technology maturity, existing gaps, operational risks. assumptions, however, not been grounded experimental data. Moreover, to date, no crew-controlled telerobot has fully tested in high-fidelity manner. To address these issues,...
With the infusion of computation into workplaces and homes, various service settings, everyday objects, scholars in human–computer interaction (HCI) related domains have begun to consider research design implications not only smart "things," but <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">smart environments</i> . Much work on environments date has focused homes; HCI explores user values for means interacting with homes (e.g., interfaces...
Rover-mounted geotechnical systems are of paramount importance to lunar trafficability assessment, construction, and excavation/mining toward establishing permanent human presence on the Moon. These tools can also be used determine density, when regolith is as radiation shield, for example. Two popular in-situ devices properties soil Static Cone Penetrometer (SCP) Dynamic (DCP). However, both have shortcomings that may prevent them from being robotically-deployed in a low gravity...
This paper introduces an advanced rover localization system suitable for autonomous planetary exploration in the absence of Global Positioning System (GPS) infrastructure. Given existing terrain map (image and elevation) obtained from satellite imagery images provided by stereo camera system, proposed method determines best location through visual odometry, 3D horizon matching. The is tested on data retrieved a 3 km traverse Basalt Hills quarry California where GPS track used as ground...
Horizon line detection requires finding a boundary which segments an image into sky and non-sky regions. It has many applications including visual geo-localization geo-tagging, robot navigation/localization, ship port security. Recently, two machine learning based approaches have been proposed for horizon detection: one relying on edge classification the other pixel classification. In edge-based approach, classifier is used to refine map by removing non-horizon edges. The refined then form...
In this paper, we consider the problem of segmenting an image into sky and non-sky regions, typically referred to as horizon line detection or skyline extraction. Specifically, present a new approach by coupling machine learning with dynamic programming. Given image, Canny edge detector is applied first keeping only those edges which survive over wide range thresholds. We refer surviving Maximally Stable Extremal Edges (MSEEs). The number further reduced classifying MSEEs non-horizon using...
This letter assesses an adaptive approach to fault recovery in autonomous robotic space operations, which uses indicators of opportunity, such as physiological state measurements and observations past human assistant performance, inform future selections. We validated our reinforcement learning using data we collected from humans executing simulated mission scenarios. present a method structuring human-factors experiments that permits collection relevant indicator opportunity assigned...