Coordinated Aerial-Ground Robot Exploration via Monte-Carlo View Quality Rendering
This work addresses exploration challenges in robotics for applications like search and rescue, but it appears incremental as it builds on existing heuristics with specific enhancements.
The paper tackled the problem of exploring large, unstructured environments using a team of aerial and ground robots, and the result was a framework that improved exploration efficiency by guiding agents to informative viewpoints and reducing planning time.
We present a framework for a ground-aerial robotic team to explore large, unstructured, and unknown environments. In such exploration problems, the effectiveness of existing exploration-boosting heuristics often scales poorly with the environments' size and complexity. This work proposes a novel framework combining incremental frontier distribution, goal selection with Monte-Carlo view quality rendering, and an automatic-differentiable information gain measure to improve exploration efficiency. Simulated with multiple complex environments, we demonstrate that the proposed method effectively utilizes collaborative aerial and ground robots, consistently guides agents to informative viewpoints, improves exploration paths' information gain, and reduces planning time.