RayFronts: Open-Set Semantic Ray Frontiers for Online Scene Understanding and Exploration
This addresses the challenge of efficient and fine-grained semantic mapping for open-world robots, though it appears incremental as it builds on existing mapping approaches.
The paper tackles the problem of open-set semantic mapping for robots by introducing RayFronts, a unified representation that combines within-range and beyond-range observations, achieving 8.84 Hz runtime and improving 3D semantic segmentation performance by 1.34x while increasing throughput by 16.5x.
Open-set semantic mapping is crucial for open-world robots. Current mapping approaches either are limited by the depth range or only map beyond-range entities in constrained settings, where overall they fail to combine within-range and beyond-range observations. Furthermore, these methods make a trade-off between fine-grained semantics and efficiency. We introduce RayFronts, a unified representation that enables both dense and beyond-range efficient semantic mapping. RayFronts encodes task-agnostic open-set semantics to both in-range voxels and beyond-range rays encoded at map boundaries, empowering the robot to reduce search volumes significantly and make informed decisions both within & beyond sensory range, while running at 8.84 Hz on an Orin AGX. Benchmarking the within-range semantics shows that RayFronts's fine-grained image encoding provides 1.34x zero-shot 3D semantic segmentation performance while improving throughput by 16.5x. Traditionally, online mapping performance is entangled with other system components, complicating evaluation. We propose a planner-agnostic evaluation framework that captures the utility for online beyond-range search and exploration, and show RayFronts reduces search volume 2.2x more efficiently than the closest online baselines.