Search

Mapping and navigation have gone hand-in-hand since long before robots existed. Maps are a key form of communication, allowing someone who has never been somewhere to nonetheless navigate that area successfully. In the context of multi-robot systems, the maps and information that flow between robots are necessary for effective collaboration, whether those robots are operating concurrently, sequentially, or completely asynchronously. In this paper, we argue that maps must go beyond encoding purely geometric or visual information to enable increasingly complex autonomy, particularly between robots. We propose a framework for multi-robot autonomy, focusing in particular on air and ground robots operating in outdoor 2.5D environments. We show that semantic maps can enable the specification, planning, and execution of complex collaborative missions, including localization in GPS-denied settings. A distinguishing characteristic of this work is that we strongly emphasize field experiments and testing, and by doing so demonstrate that these ideas can work at scale in the real world. We also perform extensive simulation experiments to validate our ideas at even larger scales. We believe these experiments and the experimental results constitute a significant step forward toward advancing the state-of-the-art of large-scale, collaborative multi-robot systems operating with real communication, navigation, and perception constraints., Comment: Video: https://www.youtube.com/watch?v=ieNYH40buBo

This work presents an algorithm for scene change detection from point clouds to enable autonomous robotic caretaking in future space habitats. Autonomous robotic systems will help maintain future deep-space habitats, such as the Gateway space station, which will be uncrewed for extended periods. Existing scene analysis software used on the International Space Station (ISS) relies on manually-labeled images for detecting changes. In contrast, the algorithm presented in this work uses raw, unlabeled point clouds as inputs. The algorithm first applies modified Expectation-Maximization Gaussian Mixture Model (GMM) clustering to two input point clouds. It then performs change detection by comparing the GMMs using the Earth Mover's Distance. The algorithm is validated quantitatively and qualitatively using a test dataset collected by an Astrobee robot in the NASA Ames Granite Lab comprising single frame depth images taken directly by Astrobee and full-scene reconstructed maps built with RGB-D and pose data from Astrobee. The runtimes of the approach are also analyzed in depth. The source code is publicly released to promote further development., Comment: 15 pages, 7 figures, Manuscript was presented at the AIAA SciTech Forum in Orlando, FL, USA, 8 - 12 January 2024. Video presentation: [https://www.youtube.com/watch?v=7WHp0dQYG4Y]. Code: [https://github.com/nasa/isaac/tree/master/anomaly/gmm-change-detection]

Assistive free-flyer robots autonomously caring for future crewed outposts -- such as NASA's Astrobee robots on the International Space Station (ISS) -- must be able to detect day-to-day interior changes to track inventory, detect and diagnose faults, and monitor the outpost status. This work presents a framework for multi-agent cooperative mapping and change detection to enable robotic maintenance of space outposts. One agent is used to reconstruct a 3D model of the environment from sequences of images and corresponding depth information. Another agent is used to periodically scan the environment for inconsistencies against the 3D model. Change detection is validated after completing the surveys using real image and pose data collected by Astrobee robots in a ground testing environment and from microgravity aboard the ISS. This work outlines the objectives, requirements, and algorithmic modules for the multi-agent reconstruction system, including recommendations for its use by assistive free-flyers aboard future microgravity outposts., Comment: 11 pages, 8 figures, Manuscript presented at the 74th International Astronautical Congress, IAC 2023, Baku, Azerbaijan, 2 - 6 October 2023. Video presentation: [https://www.youtube.com/watch?v=VfjV-zwFEtU]. Code: [https://github.com/hollydinkel/astrobeecd]

In this work, we use MEMS microphones as vibration sensors to simultaneously classify texture and estimate contact position and velocity. Vibration sensors are an important facet of both human and robotic tactile sensing, providing fast detection of contact and onset of slip. Microphones are an attractive option for implementing vibration sensing as they offer a fast response and can be sampled quickly, are affordable, and occupy a very small footprint. Our prototype sensor uses only a sparse array (8-9 mm spacing) of distributed MEMS microphones (<$1, 3.76 x 2.95 x 1.10 mm) embedded under an elastomer. We use transformer-based architectures for data analysis, taking advantage of the microphones' high sampling rate to run our models on time-series data as opposed to individual snapshots. This approach allows us to obtain 77.3% average accuracy on 4-class texture classification (84.2% when excluding the slowest drag velocity), 1.8 mm mean error on contact localization, and 5.6 mm/s mean error on contact velocity. We show that the learned texture and localization models are robust to varying velocity and generalize to unseen velocities. We also report that our sensor provides fast contact detection, an important advantage of fast transducers. This investigation illustrates the capabilities one can achieve with a MEMS microphone array alone, leaving valuable sensor real estate available for integration with complementary tactile sensing modalities., Comment: 6 pages, 4 figures, accepted to 2024 IEEE International Conference on Robotics and Automation (ICRA)

In this work, we present an end-to-end heterogeneous multi-robot system framework where ground robots are able to localize, plan, and navigate in a semantic map created in real time by a high-altitude quadrotor. The ground robots choose and deconflict their targets independently, without any external intervention. Moreover, they perform cross-view localization by matching their local maps with the overhead map using semantics. The communication backbone is opportunistic and distributed, allowing the entire system to operate with no external infrastructure aside from GPS for the quadrotor. We extensively tested our system by performing different missions on top of our framework over multiple experiments in different environments. Our ground robots travelled over 6 km autonomously with minimal intervention in the real world and over 96 km in simulation without interventions., Comment: Sumbitted to RA-L and IROS

Currently, GPS is by far the most popular global localization method. However, it is not always reliable or accurate in all environments. SLAM methods enable local state estimation but provide no means of registering the local map to a global one, which can be important for inter-robot collaboration or human interaction. In this work, we present a real-time method for utilizing semantics to globally localize a robot using only egocentric 3D semantically labelled LiDAR and IMU as well as top-down RGB images obtained from satellites or aerial robots. Additionally, as it runs, our method builds a globally registered, semantic map of the environment. We validate our method on KITTI as well as our own challenging datasets, and show better than 10 meter accuracy, a high degree of robustness, and the ability to estimate the scale of a top-down map on the fly if it is initially unknown., Comment: Published in the IEEE Robotics and Automation Letters and presented at the IEEE 2021 International Conference on Robotics and Automation. See https://www.youtube.com/watch?v=_qwAoYK9iGU for accompanying video

We present a novel POMDP planning algorithm called heuristic search value iteration (HSVI).HSVI is an anytime algorithm that returns a policy and a provable bound on its regret with respect to the optimal policy. HSVI gets its power by combining two well-known techniques: attention-focusing search heuristics and piecewise linear convex representations of the value function. HSVI's soundness and convergence have been proven. On some benchmark problems from the literature, HSVI displays speedups of greater than 100 with respect to other state-of-the-art POMDP value iteration algorithms. We also apply HSVI to a new rover exploration problem 10 times larger than most POMDP problems in the literature., Comment: Appears in Proceedings of the Twentieth Conference on Uncertainty in Artificial Intelligence (UAI2004)

Existing complexity bounds for point-based POMDP value iteration algorithms focus either on the curse of dimensionality or the curse of history. We derive a new bound that relies on both and uses the concept of discounted reachability; our conclusions may help guide future algorithm design. We also discuss recent improvements to our (point-based) heuristic search value iteration algorithm. Our new implementation calculates tighter initial bounds, avoids solving linear programs, and makes more effective use of sparsity., Comment: Appears in Proceedings of the Twenty-First Conference on Uncertainty in Artificial Intelligence (UAI2005)

As of March 2019, four Astrobee free-flying robots have been integrated, tested and shipped to NASA’s Johnson Space Center, Texas, ready to be launched to space. Two of these Astrobee units (Honey and Bumble) will be launched to the International Space Station (ISS) on April 17, 2019, on the Cygnus NG-11 (Northrop Grumman) cargo resupply spacecraft from the Mid-Atlantic Regional Spaceport (MARS) launch facility, at NASA's Wallops Flight Facility, in Virginia, while the third unit (Queen) will be launched in mid-July 2019, with the cargo resupply mission Space-X 18, from Cape Canaveral, at NASA’s Kennedy Space Center. The primary purpose of the Astrobee system is to provide an autonomous and flexible platform for research on zero-g free-flying robotics, with the ability to accommodate guest researchers looking to utilize the unique capabilities of this platform in the microgravity of low earth orbit, and to advance the state of the art of guest science software and research payloads, which range from gecko-inspired adhesives for perching on smooth surfaces, to augmented reality interfaces to help astronauts and robots work together effectively, to RFID reader, performing inventory of RFID tagged items inside the ISS. Astrobee will also serve utility functions, such as free-flying cameras to record video and provide assistance during astronaut activities, and as mobile sensor platforms to conduct surveys of the ISS. In this paper we will give an overview of the status of the Astrobee system, which includes the docking station already launched and mounted in the JAXA JEM module of the ISS, the Astrobee robots, the Astrobee robotic arms, the ground data system (GDS) and the development of the several guest science payloads.

This presentation is an overview of the Integrated System for Autonomous and Adaptive Caretaking (ISAAC) project, funded by the STMD Game Changing Development program to develop autonomous caretaking capabilities for future human exploration spacecraft, especially during uncrewed phases.

This paper presents the thermal design of actuators in the perching arm of Astrobee robot that will operate inside the International Space Station (ISS) in starting 2019. Since the crew's safety is of the utmost importance on the ISS, all materials used in the Astrobee robot should meet the touch temperature requirements according to the ISS safety standards to protect crew from skin burns. The Astrobee perching arm consists of 2-DOF arm servo motors and 1-DOF gripper DC motor, which are capable of overheating when stalled, particularly given the lack of gravity-driven thermal convection in the ISS zero-gee environment. Thermal properties of two types of actuators are verified by monitoring the touch temperature in worst-case operations with no thermal protection. Then, the proper thermal protection designs have been conducted and installed to guarantee the safety in all conditions.

Astrobee is a new class of free-flying robots that operate in the interior of the International Space Station (ISS). In addition to providing a research platform for zero-g free-flying robotics (replacing the Synchronized Position Hold Engage and Reorient Experimental Satellites (SPHERES)), Astrobee improves the efficiency of ISS operations by providing flight and payload controllers with a mobile camera/sensor platform. The Astrobee system consists of three robots, a docking station, and a ground data system. Development began in late 2014, and Astrobee will launch to ISS in late 2018. This paper provides an overview of the capabilities of the Astrobee system, the concept of operations for ISS operations support, and the challenges of operating a free-flying robot within the constraints of the ISS environment.

Astrobee is a new class of free-flying robots that operate in the interior of the International Space Station (ISS). In addition to providing a research platform for zero-g free-flying robotics (replacing the Synchronized Position Hold Engage and Reorient Experimental Satellites (SPHERES)), Astrobee improves the efficiency of ISS operations by providing flight and payload controllers with a mobile camera/sensor platform. The Astrobee system consists of three robots, a docking station, and a ground data system. Development began in late 2014, and Astrobee will launch to ISS in late 2018. This paper provides an overview of the capabilities of the Astrobee system, the concept of operations for ISS operations support, and the challenges of operating a free-flying robot within the constraints of the ISS environment.

The Astrobees are next-generation free-flying robots that will operate in the interior of the International Space Station (ISS). Their primary purpose is to provide a flexible platform for research on zero-g freeflying robotics, with the ability to carry a wide variety of future research payloads and guest science software. They will also serve utility functions: as free-flying cameras to record video of astronaut activities, and as mobile sensor platforms to conduct surveys of the ISS. The Astrobee system includes two robots, a docking station, and a ground data system (GDS). It is developed by the Human Exploration Telerobotics 2 (HET-2) Project, which began in Oct. 2014, and will deliver the Astrobees for launch to ISS in 2017. This paper covers selected aspects of the Astrobee design, focusing on capabilities relevant to potential users of the platform.

Astronaut time will always be in short supply, consumables (e.g., oxygen) will always be limited, and some work will not be feasible, or productive, for astronauts to do manually. Free flyers offer significant potential to perform a great variety of tasks, include routine, repetitive or simple but long-duration work, such as conducting environment surveys, taking sensor readings or monitoring crew activities. The "Astrobee" project is developing a new free flying robot system suitable for performing Intravehicular Activity (IVA) work on the International Space Station (ISS). This paper will describe the Astrobee project objectives, initial design, concept of operations, and key challenges.

The Planetary Lake Lander Project is studying the impact of rapid deglaciation at a high altitude alpine lake in the Andes, where disrupted environmental, physical, chemical, and biological cycles result in newly emerging natural patterns. The solar powered Lake Lander robot is designed to monitor the lake system and characterize both baseline characteristics and impacts of disturbance events such as storms and landslides. Lake Lander must use an onboard adaptive science-on-the-fly approach to return relevant data about these events to mission control without exceeding limited energy and bandwidth resources. Lake Lander carries weather sensors, cameras and a sonde that is winched up and down the water column to monitor temperature, dissolved oxygen, turbidity and other water quality parameters. Data from Lake Lander is returned via satellite and distributed to an international team of scientists via web-based ground data systems. Here, we describe the Lake Lander Project scientific goals, hardware design, ground data systems, and preliminary data from 2011. The adaptive science-on-the-fly system will be described in future papers.

We are studying how "robotic follow-up" can improve future planetary exploration. Robotic follow-up, which we define as augmenting human field work with subsequent robot activity, is a field exploration technique designed to increase human productivity and science return. To better understand the benefits, requirements, limitations and risks associated with this technique, we are conducting analog field tests with human and robot teams at the Haughton Crater impact structure on Devon Island, Canada. In this paper, we discuss the motivation for robotic follow-up, describe the scientific context and system design for our work, and present results and lessons learned from field testing.

Since 2004, NASA has been working to return to the Moon. In contrast to the Apollo missions, two key objectives of the current exploration program is to establish significant infrastructure and an outpost. Achieving these objectives will enable long-duration stays and long-distance exploration of the Moon. To do this, robotic systems will be needed to perform tasks which cannot, or should not, be performed by crew alone. In this paper, we summarize our work to develop "utility robots" for lunar surface operations, present results and lessons learned from field testing, and discuss directions for future research.