PLGRIM: Hierarchical Value Learning for Large-scale Exploration in Unknown Environments

Kim, Sung-Kyun; Bouman, Amanda; Salhotra, Gautam; Fan, David D.; Otsu, Kyohei; Burdick, Joel W.; Agha–mohammadi, Ali–akbar

doi:10.1609/icaps.v31i1.16014

Cited by 33 publications

(12 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Team CoSTAR's winning solution from the Urban Circuit is described in Bouman et al (2020), focusing on the Spot platform, supplementing Spot's inbuilt sensing with a sensor package that incorporates lidar, RealSense cameras, an IMU, gas and WiFi detectors, and a thermal camera. The architecture utilizes NeBula (networked belief aware perceptual autonomy); key aspects of this work are risk and uncertainty-aware local planning (Kim et al, 2021), yielding a highly capable platform that is able to conduct long-duration missions beyond communications range. Comparably, our focus has been on establishing a common understanding on all agents, enabling them to coordinate autonomously, out of range of the operator base station.…”

Section: Other Subt Teamsmentioning

confidence: 99%

Heterogeneous Ground and Air Platforms, Homogeneous Sensing: Team CSIRO Data61’s Approach to the DARPA Subterranean Challenge

Hudson¹,

Talbot²,

Cox³

et al. 2022

View full text Add to dashboard Cite

Heterogeneous teams of robots, leveraging a balance between autonomy and human interaction, bring powerful capabilities to the problem of exploring dangerous, unstructured subterranean environments. Here we describe the solution developed by Team CSIRO Data61, consisting of CSIRO, Emesent, and Georgia Tech, during the DARPA Subterranean Challenge. These presented systems were fielded in the Tunnel Circuit in August 2019, the Urban Circuit in February 2020, and in our own Cave event, conducted in September 2020. A unique capability of the fielded team is the homogeneous sensing of the platforms utilized, which is used to obtain a decentralized multi-agent SLAM solution on each platform (both ground agents and UAVs) using peer-to-peer communications. This approach enabled a shift in focus from constructing a pervasive communications network to relying on multi-agent autonomy, motivated by experiences in early circuit events. These experiences also showed the surprising capability of rugged tracked platforms for challenging terrain, which in turn led to the heterogeneous team structure based on a BIA5 OzBot Titan ground robot and an Emesent Hovermap UAV, supplemented by smaller tracked or legged ground robots. The ground agents use a common CatPack perception module, which allowed reuse of the perception and autonomy stack across all ground agents with minimal adaptation.

show abstract

Section: Other Subt Teamsmentioning

confidence: 99%

Heterogeneous Ground and Air Platforms, Homogeneous Sensing: Team CSIRO Data61’s Approach to the DARPA Subterranean Challenge

Hudson¹,

Talbot²,

Cox³

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Overall, successful exploration in a three‐dimensional landscape will require the tight integration and co‐design of mobility systems, traversability assessment instruments, and innovative automation/AI algorithms (Agha‐Mohammadi et al., 2018 , 2021 ; Ahmed et al., 2019 ; Sauder et al., 2017 ). Robots will need to traverse terrain that is at best partially characterized or at worst completely unknown using onboard autonomy (Otsu et al., 2020 ) and perception capabilities (Ebadi et al., 2020 ; Santamaria‐Navarro et al., 2019 ), as well as respond to off‐nominal and unexpected events during operations (Agha‐Mohammadi et al., 2018 ; Kim et al., 2021 ) (Q41).…”

Section: Resultsmentioning

confidence: 99%

Fundamental Science and Engineering Questions in Planetary Cave Exploration

et al. 2022

View full text Add to dashboard Cite

Nearly half a century ago, two papers postulated the likelihood of lunar lava tube caves using mathematical models. Today, armed with an array of orbiting and fly-by satellites and survey instrumentation, we have now acquired cave data across our solar system-including the identification of potential cave entrances on the Moon, Mars, and at least nine other planetary bodies. These discoveries gave rise to the study of planetary caves. To help advance this field, we leveraged the expertise of an interdisciplinary group to identify a strategy to explore caves beyond Earth. Focusing primarily on astrobiology, the cave environment, geology, robotics, instrumentation, and human exploration, our goal was to produce a framework to guide this subdiscipline through at least the next decade. To do this, we first assembled a list of 198 science and engineering questions. Then, through a series of social surveys, 114 scientists and engineers winnowed down the list to the top 53 highest priority questions. This exercise resulted in identifying emerging and crucial research areas that require robust development to ultimately support a robotic mission to a planetary caveprincipally the Moon and/or Mars. With the necessary financial investment and institutional support, the research and technological development required to achieve these necessary advancements over the next decade WYNNE ET AL.

show abstract

“…The DARPA Subterranean Exploration Challenge is an interesting example of large-scale real-world application of autonomous localization, mapping and navigation in an unknown environment [31], where POMDP modeling is a natural choice. The PLGRIM [75] framework follows the hierarchical approach to make planning over long time horizons feasible in this context. Locally, PLGRIM uses POMCP to cover the environment search space efficiently.…”

Section: Pomdps In Roboticsmentioning

confidence: 99%

Partially Observable Markov Decision Processes in Robotics: A Survey

Lauri¹,

Hsu

Pajarinen

2023

IEEE Trans. Robot.

View full text Add to dashboard Cite

Noisy sensing, imperfect control, and environment changes are defining characteristics of many real-world robot tasks. The partially observable Markov decision process (POMDP) provides a principled mathematical framework for modeling and solving robot decision and control tasks under uncertainty. Over the last decade, it has seen many successful applications, spanning localization and navigation, search and tracking, autonomous driving, multi-robot systems, manipulation, and human-robot interaction. This survey aims to bridge the gap between the development of POMDP models and algorithms at one end and application to diverse robot decision tasks at the other. It analyzes the characteristics of these tasks and connects them with the mathematical and algorithmic properties of the POMDP framework for effective modeling and solution. For practitioners, the survey provides some of the key task characteristics in deciding when and how to apply POMDPs to robot tasks successfully. For POMDP algorithm designers, the survey provides new insights into the unique challenges of applying POMDPs to robot systems and points to promising new directions for further research.

show abstract

PLGRIM: Hierarchical Value Learning for Large-scale Exploration in Unknown Environments

Cited by 33 publications

References 27 publications

Heterogeneous Ground and Air Platforms, Homogeneous Sensing: Team CSIRO Data61’s Approach to the DARPA Subterranean Challenge

Heterogeneous Ground and Air Platforms, Homogeneous Sensing: Team CSIRO Data61’s Approach to the DARPA Subterranean Challenge

Fundamental Science and Engineering Questions in Planetary Cave Exploration

Partially Observable Markov Decision Processes in Robotics: A Survey

Contact Info

Product

Resources

About