EPISODE · May 15, 2025 · 16 MIN
UAV Visual Object Search in City Space
from Neural intel Pod · host Neuralintel.org
This document introduces CityAVOS, a new benchmark dataset designed for Aerial Visual Object Search (AVOS)tasks using Unmanned Aerial Vehicles (UAVs) in realistic urban environments. The text describes the unique challenges of urban AVOS, such as complex semantics and difficult identification of similar objects, which differentiate it from previous navigation and object search tasks. It also presents PRPSearcher, a novel Multi-modal Large Language Model (MLLM)-powered agentic method that employs spatial perception, target reasoning, and action planningusing semantic, cognitive, and uncertainty maps to improve UAV search capabilities. Experimental results demonstrate that PRPSearcher outperforms existing baseline methods, though human performance remains the ultimate benchmark, highlighting areas for future research in autonomous urban search.
What this episode covers
This document introduces CityAVOS, a new benchmark dataset designed for Aerial Visual Object Search (AVOS)tasks using Unmanned Aerial Vehicles (UAVs) in realistic urban environments. The text describes the unique challenges of urban AVOS, such as complex semantics and difficult identification of similar objects, which differentiate it from previous navigation and object search tasks. It also presents PRPSearcher, a novel Multi-modal Large Language Model (MLLM)-powered agentic method that employs spatial perception, target reasoning, and action planningusing semantic, cognitive, and uncertainty maps to improve UAV search capabilities. Experimental results demonstrate that PRPSearcher outperforms existing baseline methods, though human performance remains the ultimate benchmark, highlighting areas for future research in autonomous urban search.
NOW PLAYING
UAV Visual Object Search in City Space
No transcript for this episode yet
Similar Episodes
Mar 14, 2026 ·23m
Mar 11, 2026 ·16m
Feb 28, 2026 ·14m