Exploring the Most Sectors at the DARPA Subterranean Challenge Finals

摘要

Autonomous robot navigation in austere environments is critical to missions like “search and rescue”, yet it remains difficult to achieve. The recent DARPA Subterranean Challenge (SubT) highlights prominent challenges including GPS-denied navigation through rough terrains, rapid exploration in large-scale three-dimensional (3D) space, and interrobot coordination over unreliable communication. Solving these challenges requires both mechanical resilience and algorithmic intelligence. Here, we present our approach that leverages a fleet of custom-built heterogeneous robots and an autonomy stack for robust navigation in challenging environments. Our approach has demonstrated superior navigation performance in the SubT Final Event, resulting in the fastest traversal and most thorough exploration of the environment, which won the “Most Sectors Explored Award.” This paper details our approach from two aspects: mechanical designs of a marsupial ground-and-aerial system to overcome mobility challenges and autonomy algorithms enabling collective rapid exploration. We also provide lessons learned in the design, development and deployment of complex but resilient robotic systems to overcome real-world navigation challenges.