Learned Tree Search for Long-Horizon Social Robot Navigation in Shared Airspace
This work addresses the need for safe and trustworthy autonomous navigation in shared airspace, particularly for general aviation, but it is incremental as it augments existing methods with a planner.
The authors tackled the problem of autonomous aerial robot navigation in crowded, dynamic shared spaces by proposing the Social Robot Tree Search (SoRTS) algorithm, which combines socially-aware trajectory prediction with Monte Carlo Tree Search planning, and demonstrated through a user study with 26 FAA certified pilots that SoRTS performs comparably to a competent human pilot and significantly outperforms a baseline algorithm.
The fast-growing demand for fully autonomous aerial operations in shared spaces necessitates developing trustworthy agents that can safely and seamlessly navigate in crowded, dynamic spaces. In this work, we propose Social Robot Tree Search (SoRTS), an algorithm for the safe navigation of mobile robots in social domains. SoRTS aims to augment existing socially-aware trajectory prediction policies with a Monte Carlo Tree Search planner for improved downstream navigation of mobile robots. To evaluate the performance of our method, we choose the use case of social navigation for general aviation. To aid this evaluation, within this work, we also introduce X-PlaneROS, a high-fidelity aerial simulator, to enable more research in full-scale aerial autonomy. By conducting a user study based on the assessments of 26 FAA certified pilots, we show that SoRTS performs comparably to a competent human pilot, significantly outperforming our baseline algorithm. We further complement these results with self-play experiments in scenarios with increasing complexity.