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

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.

arXiv commentFor team website, see https://costar.jpl.nasa.gov/. Accepted for publication in the Journal of Field Robotics, 2021

References in corpus (12)

• YOLOv4: Optimal Speed and Accuracy of Object Detection
• YOLOv3: An Incremental Improvement
• A Survey of Autonomous Driving: Common Practices and Emerging Technologies
• Tightly Coupled 3D Lidar Inertial Odometry and Mapping
• Heterogeneous Ground and Air Platforms, Homogeneous Sensing: Team CSIRO Data61's Approach to the DARPA Subterranean Challenge
• Bayesian Learning-Based Adaptive Control for Safety Critical Systems
• Where to Map? Iterative Rover-Copter Path Planning for Mars Exploration
• MobileDets: Searching for Object Detection Architectures for Mobile Accelerators
• Bi-directional Value Learning for Risk-aware Planning Under Uncertainty: Extended Version
• STEP: Stochastic Traversability Evaluation and Planning for Risk-Aware Off-road Navigation
• PLGRIM: Hierarchical Value Learning for Large-scale Exploration in Unknown Environments
• The Kinematics of Tracked Vehicles via the Power Dissipation Method

Cited by in corpus (7)

• Towards Collaborative Simultaneous Localization and Mapping: a Survey of the Current Research Landscape
• UAVs Beneath the Surface: Cooperative Autonomy for Subterranean Search and Rescue in DARPA SubT
• Flexible Supervised Autonomy for Exploration in Subterranean Environments
• STEP: Stochastic Traversability Evaluation and Planning for Risk-Aware Off-road Navigation
• Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems
• Learning Risk-aware Costmaps for Traversability in Challenging Environments
• Cooperative Indoor Exploration Leveraging a Mixed-Size UAV Team with Heterogeneous Sensors