NeBula: TEAM CoSTAR’s Robotic Autonomy Solution that Won Phase II of DARPA Subterranean Challenge
Author:
Agha AliORCID, Otsu KyoheiORCID, Morrell BenjaminORCID, Fan David, Thakker RohanORCID, Santamaria-Navarro AngelORCID, Kim Sung-KyunORCID, Bouman AmandaORCID, Lei XianmeiORCID, Edlund JeffreyORCID, Ginting MuhammadORCID, Ebadi KamakORCID, Anderson MatthewORCID, Pailevanian Torkom, Terry EdwardORCID, Wolf MichaelORCID, Tagliabue AndreaORCID, Vaquero TiagoORCID, Palieri MatteoORCID, Tepsuporn ScottORCID, Chang YunORCID, Kalantari ArashORCID, Chavez Fernando, Lopez BrettORCID, Funabiki NobuhiroORCID, Miles Gregory, Touma ThomasORCID, Buscicchio Alessandro, Tordesillas JesusORCID, Alatur NikhileshORCID, Nash JeremyORCID, Walsh William, Jung SunggooORCID, Lee HanseobORCID, Kanellakis ChristoforosORCID, Mayo JohnORCID, Harper ScottORCID, Kaufmann MarcelORCID, Dixit AnushriORCID, Correa GustavoORCID, Lee CarlynORCID, Gao JayORCID, Merewether GeneORCID, Maldonado-Contreras Jairo, Salhotra GautamORCID, Saboia Da Silva MairaORCID, Ramtoula BenjaminORCID, Fakoorian Seyed, Hatteland Alexander, Kim TaeyeonORCID, Bartlett TaraORCID, Stephens AlexORCID, Kim Leon, Bergh Chuck, Heiden EricORCID, Lew ThomasORCID, Cauligi AbhishekORCID, Heywood TristanORCID, Kramer Andrew, Leopold HenryORCID, Melikyan Hov, Choi HyunghoORCID, Daftry ShreyanshORCID, Toupet OlivierORCID, Wee InhwanORCID, Thakur AbhishekORCID, Feras MicahORCID, Beltrame GiovanniORCID, Nikolakopoulos GeorgeORCID, Shim David, Carlone LucaORCID, Burdick JoelORCID
Abstract
This paper presents and discusses algorithms, hardware, and software architecture developed by the TEAM CoSTAR (Collaborative SubTerranean Autonomous Robots), competing in the DARPA Subterranean Challenge. Specifically, it presents the techniques utilized within the Tunnel (2019) and Urban (2020) competitions, where CoSTAR achieved second and first place, respectively. We also discuss CoSTAR’s demonstrations in Martian-analog surface and subsurface (lava tubes) exploration. The paper introduces our autonomy solution, referred to as NeBula (Networked Belief-aware Perceptual Autonomy). NeBula is an uncertainty-aware framework that aims at enabling resilient and modular autonomy solutions by performing reasoning and decision making in the belief space (space of probability distributions over the robot and world states). We discuss various components of the NeBula framework, including (i) geometric and semantic environment mapping, (ii) a multi-modal positioning system, (iii) traversability analysis and local planning, (iv) global motion planning and exploration behavior, (v) risk-aware mission planning, (vi) networking and decentralized reasoning, and (vii) learning-enabled adaptation. We discuss the performance of NeBula on several robot types (e.g., wheeled, legged, flying), in various environments. We discuss the specific results and lessons learned from fielding this solution in the challenging courses of the DARPA Subterranean Challenge competition.
Publisher
Field Robotics Publication Society
Cited by
13 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|