Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2103.11470

NeBula: Quest for Robotic Autonomy in Challenging Environments; TEAM CoSTAR at the DARPA Subterranean Challenge

Ali Agha·Kyohei Otsu·Benjamin Morrell·David D. Fan·Rohan Thakker·Angel Santamaria-Navarro·Sung-Kyun Kim·Amanda Bouman·Xianmei Lei·Jeffrey Edlund·Muhammad Fadhil Ginting·Kamak Ebadi·Matthew Anderson·Torkom Pailevanian·Edward Terry·Michael Wolf·Andrea Tagliabue·Tiago Stegun Vaquero·Matteo Palieri·Scott Tepsuporn·Yun Chang·Arash Kalantari·Fernando Chavez·Brett Lopez·Nobuhiro Funabiki·Gregory Miles·Thomas Touma·Alessandro Buscicchio·Jesus Tordesillas·Nikhilesh Alatur·Jeremy Nash·William Walsh·Sunggoo Jung·Hanseob Lee·Christoforos Kanellakis·John Mayo·Scott Harper·Marcel Kaufmann·Anushri Dixit·Gustavo Correa·Carlyn Lee·Jay Gao·Gene Merewether·Jairo Maldonado-Contreras·Gautam Salhotra·Maira Saboia Da Silva·Benjamin Ramtoula·Yuki Kubo·Seyed Fakoorian·Alexander Hatteland·Taeyeon Kim·Tara Bartlett·Alex Stephens·Leon Kim·Chuck Bergh·Eric Heiden·Thomas Lew·Abhishek Cauligi·Tristan Heywood·Andrew Kramer·Henry A. Leopold·Chris Choi·Shreyansh Daftry·Olivier Toupet·Inhwan Wee·Abhishek Thakur·Micah Feras·Giovanni Beltrame·George Nikolakopoulos·David Shim·Luca Carlone·Joel Burdick
View original source ↗Read source document ↗Export metadata ↓

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 2nd and 1st 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; (i) 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.

Explore related subjects

cs.ROcs.AI

Keep this discovery

BibTeXRIS

Ali Agha, Kyohei Otsu, Benjamin Morrell, David D. Fan, Rohan Thakker, Angel Santamaria-Navarro, Sung-Kyun Kim, Amanda Bouman, Xianmei Lei, Jeffrey Edlund, Muhammad Fadhil Ginting, Kamak Ebadi, Matthew Anderson, Torkom Pailevanian, Edward Terry, Michael Wolf, Andrea Tagliabue, Tiago Stegun Vaquero, Matteo Palieri, Scott Tepsuporn, Yun Chang, Arash Kalantari, Fernando Chavez, Brett Lopez, Nobuhiro Funabiki, Gregory Miles, Thomas Touma, Alessandro Buscicchio, Jesus Tordesillas, Nikhilesh Alatur, Jeremy Nash, William Walsh, Sunggoo Jung, Hanseob Lee, Christoforos Kanellakis, John Mayo, Scott Harper, Marcel Kaufmann, Anushri Dixit, Gustavo Correa, Carlyn Lee, Jay Gao, Gene Merewether, Jairo Maldonado-Contreras, Gautam Salhotra, Maira Saboia Da Silva, Benjamin Ramtoula, Yuki Kubo, Seyed Fakoorian, Alexander Hatteland, Taeyeon Kim, Tara Bartlett, Alex Stephens, Leon Kim, Chuck Bergh, Eric Heiden, Thomas Lew, Abhishek Cauligi, Tristan Heywood, Andrew Kramer, Henry A. Leopold, Chris Choi, Shreyansh Daftry, Olivier Toupet, Inhwan Wee, Abhishek Thakur, Micah Feras, Giovanni Beltrame, George Nikolakopoulos, David Shim, Luca Carlone, Joel Burdick. 2021-03-21. NeBula: Quest for Robotic Autonomy in Challenging Environments; TEAM CoSTAR at the DARPA Subterranean Challenge. https://arxiv.org/abs/2103.11470

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

IMLE-VLA: Fast Single-Step Action Generation for Vision-Language-Action Policies

Vision-language-action (VLA) policies leverage pretrained vision-language backbones to achieve strong cross-task generalization. A leading design couples this backbone with a dedicated continuous action head trained via diffusion or flow matching. However, such heads rely on iterative multi-step sampling, for example 10 Euler steps in $\pi_{0.5}$. This creates an inference bottleneck that produces stop-and-go movement in the robot and slower task completion. We introduce IMLE-VLA, which replaces the iterative action head with a single-step conditional generator trained via conditional Implicit Maximum Likelihood Estimation (cIMLE). The cIMLE objective promotes multimodal action coverage, avoiding the mode collapse of naive regression heads while eliminating multi-step sampling entirely. When IMLE-VLA is applied to $\pi_{0.5}$, it increases inference frequency 3.67x (55 Hz vs. 15 Hz), enabling up to 11x higher action throughput. On the 40-task LIBERO benchmark, IMLE-VLA achieves the highest average success rate (98.0%) among all baselines while leading in inference frequency. Under the test-time perturbations of LIBERO-plus, IMLE-VLA retains $\pi_{0.5}$'s robustness while other baselines degrade sharply, confirming that the cIMLE head preserves generalization. Real-world experiments on a Franka Emika Panda across four tasks demonstrate smoother motion (2.2x to 3.0x lower jerk) and faster task completion, with IMLE-VLA outperforming $\pi_{0.5}$ on every task and reducing average VLA inference time per episode by 3.9x to 6.6x. Videos and code are available at https://kianhk6.github.io/IMLE-VLA/

cs.RO↗
arXiv2026

ObstaDiff: Generalizable Diffusion Policy Learning via Obstacle-aware Representations

Imitation learning has achieved impressive results in robotic manipulation, yet most existing approaches assume clean backgrounds and lack explicit mechanisms for obstacle-aware motion generation. Extending such policies to cluttered, real-world scenes with unstructured obstacles remains a key generalization challenge. We present ObstaDiff, a decomposed diffusion-policy framework with a lightweight obstacle-aware visual encoder. ObstaDiff extracts a structured target-obstacle-background representation, enabling the downstream alignment policy to generate end-effector trajectories toward a target-centered bottleneck pose while reasoning about surrounding obstacles. We evaluate ObstaDiff on 61 real-robot greenhouse trials per method (366 executions in total). ObstaDiff achieves 75.41% average task success and 8.20% average obstacle collision rate, outperforming representative imitation-learning baselines and improving generalization in cluttered agricultural scenes.

cs.RO↗
arXiv2026

Testing Between the Test Cases: Proving End-to-End Steering in Conditions You Never Drove

AI-based automated vehicle testing is challenging because a model that passes every test condition can still fail in the real world. Formal verification offers a way to directly address this gap. On a simulated highway and an arterial road we trained two small end-to-end steering networks each in CARLA, one on clear conditions alone and one on clear, fog, night and low sun. All four models were driven against a 2.19 ft lane-departure budget. Without driving again, we used bound propagation, a formal method that reads the trained weights, to compute how far steering can drift at every disturbance strength between two captured images. One calculation covers more than a campaign could drive: on the arterial it spans 133 poses, where ten intensities each would be 10^133 combinations, in minutes on one GPU. Not only did formal verification find conditions that broke the clear-trained policy without simulation testing, it provided some preliminary evidence for potential failures between the test cases. Our overall conclusion is that formal verification is a viable complement to simulation, and could be adopted as a part of verification and validation for automated driving.

cs.RO↗