Towards Embodied Air-Ground Cooperative Object Search: Benchmark, Dataset and Agentic Method
AGOS-Bench is introduced, the first dedicated benchmark for evaluating whether general-purpose Vision-Language Models (VLMs) can integrate aerial discoveries and ground-level verification through UAV-UGV cooperation, and AGOS-Agent is proposed, a training-free and tool-augmented approach to address the AGOS task.
Bokyung Yu, Zi-Mo Chen, Jun-Reng Rao et al.
· 3 citations
· ⚡1