ESARBench: A Benchmark for Agentic UAV Embodied Search and Rescue

• URL: http://arxiv.org/abs/2605.01371v1
• Date: Sat, 02 May 2026 10:30:42 GMT
• Title: ESARBench: A Benchmark for Agentic UAV Embodied Search and Rescue
• Abstract summary: Unmanned Aerial Vehicle (UAV) have exceptional capabilities in spatial reasoning, semantic understanding, and complex decision-making.<n>Existing UAV Search and Rescue research is dominated by traditional vision and path-planning methods.<n>We propose novel task of textbfEmbodied Search and Rescue (ESAR), which requires aerial agents to autonomously explore complex environments.<n>We present textbfESARBench, the first comprehensive benchmark designed to evaluate MLLM-driven UAV agents in highly realistic SAR scenarios.
• Score: 7.02322027654542
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid advancement of Multimodal Large Language Models (MLLMs) has empowered Unmanned Aerial Vehicle (UAV) with exceptional capabilities in spatial reasoning, semantic understanding, and complex decision-making, making them inherently suited for UAV Search and Rescue (SAR). However, existing UAV SAR research is dominated by traditional vision and path-planning methods and lacks a comprehensive and unified benchmark for embodied agents. To bridge this gap, we first propose the novel task of \textbf{Embodied Search and Rescue (ESAR)}, which requires aerial agents to autonomously explore complex environments, identify rescue clues, and reason about victim locations to execute informed decision-making. Additionally, we present \textbf{ESARBench}, the first comprehensive benchmark designed to evaluate MLLM-driven UAV agents in highly realistic SAR scenarios. Leveraging Unreal Engine 5 and AirSim, we construct four high-fidelity, large-scale open environments mapped directly from real-world Geographic Information System (GIS) data to ensure photorealistic landscapes. To rigorously simulate actual rescue operations, our benchmark incorporates dynamic variables including weather conditions, time of day, and stochastic clue placement. Furthermore, we create a dataset of 600 tasks modeled after real-world rescue cases and propose a robust set of evaluation metrics. We evaluate diverse baselines, ranging from traditional heuristics to advanced ground and aerial MLLM-based ObjectNav agents. Experimental results highlight the challenges in ESAR, revealing critical bottlenecks in spatial memory, aerial adaptation, and the trade-off between search efficiency and flight safety. We hope ESARBench serves as a valuable resource to advance research on Embodied Search and Rescue domain. Source code and project page: https://4amgodvzx.github.io/ESAR.github.io.

Related papers

• APEX: A Decoupled Memory-based Explorer for Asynchronous Aerial Object Goal Navigation [26.546610806602803]
  Aerial Object Goal Navigation, a challenging frontier in Embodied AI, requires an Unmanned Aerial Vehicle (UAV) agent to autonomously explore, reason, and identify a specific target using only visual perception and language description.<n>Existing methods struggle with the memorization of complex spatial representations in aerial environments, reliable and interpretable action decision-making, and inefficient exploration and information gathering.<n>We introduce textAPEX, a novel hierarchical agent designed for efficient exploration and target acquisition in complex aerial settings.
  arXiv  Detail & Related papers  (2026-01-31T06:27:57Z)
• AerialMind: Towards Referring Multi-Object Tracking in UAV Scenarios [64.51320327698231]
  We introduce AerialMind, the first large-scale RMOT benchmark in UAV scenarios.<n>We develop an innovative semi-automated collaborative agent-based labeling assistant framework.<n>We also propose HawkEyeTrack, a novel method that collaboratively enhances vision-language representation learning.
  arXiv  Detail & Related papers  (2025-11-26T04:44:27Z)
• ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks [64.86209459039313]
  ThinkGeo is an agentic benchmark designed to evaluate tool-augmented agents on remote sensing tasks via structured tool use and multi-step planning.<n>We implement a ReAct-style interaction loop and evaluate both open and closed-source LLMs on 486 structured agentic tasks with 1,773 expert-verified reasoning steps.<n>Our analysis reveals notable disparities in tool accuracy and planning consistency across models.
  arXiv  Detail & Related papers  (2025-05-29T17:59:38Z)
• Towards Autonomous UAV Visual Object Search in City Space: Benchmark and Agentic Methodology [26.90429412601702]
  We introduce CityAVOS, the first benchmark dataset for autonomous search of common urban objects.<n>This dataset comprises 2,420 tasks across six object categories with varying difficulty levels.<n>We also propose PRPSearcher, a novel agentic method powered by multi-modal large language models (MLLMs) that mimics human three-tier cognition.
  arXiv  Detail & Related papers  (2025-05-13T17:34:54Z)
• More Clear, More Flexible, More Precise: A Comprehensive Oriented Object Detection benchmark for UAV [58.89234732689013]
  CODrone is a comprehensive oriented object detection dataset for UAVs that accurately reflects real-world conditions.<n>It also serves as a new benchmark designed to align with downstream task requirements.<n>We conduct a series of experiments based on 22 classical or SOTA methods to rigorously evaluate CODrone.
  arXiv  Detail & Related papers  (2025-04-28T17:56:02Z)
• Exploring Spatial Representation to Enhance LLM Reasoning in Aerial Vision-Language Navigation [11.267956604072845]
  Aerial Vision-and-Language Navigation (VLN) is a novel task enabling Unmanned Aerial Vehicles (UAVs) to navigate in outdoor environments through natural language instructions and visual cues.<n>We propose a training-free, zero-shot framework for aerial VLN tasks, where the large language model (LLM) is leveraged as the agent for action prediction.
  arXiv  Detail & Related papers  (2024-10-11T03:54:48Z)
• Aerial View Goal Localization with Reinforcement Learning [6.165163123577484]
  We present a framework that emulates a search-and-rescue (SAR)-like setup without requiring access to actual UAVs. In this framework, an agent operates on top of an aerial image (proxy for a search area) and is tasked with localizing a goal that is described in terms of visual cues. We propose AiRLoc, a reinforcement learning (RL)-based model that decouples exploration (searching for distant goals) and exploitation (localizing nearby goals)
  arXiv  Detail & Related papers  (2022-09-08T10:27:53Z)
• Rethinking Drone-Based Search and Rescue with Aerial Person Detection [79.76669658740902]
  The visual inspection of aerial drone footage is an integral part of land search and rescue (SAR) operations today. We propose a novel deep learning algorithm to automate this aerial person detection (APD) task. We present the novel Aerial Inspection RetinaNet (AIR) algorithm as the combination of these contributions.
  arXiv  Detail & Related papers  (2021-11-17T21:48:31Z)
• A Multi-UAV System for Exploration and Target Finding in Cluttered and GPS-Denied Environments [68.31522961125589]
  We propose a framework for a team of UAVs to cooperatively explore and find a target in complex GPS-denied environments with obstacles. The team of UAVs autonomously navigates, explores, detects, and finds the target in a cluttered environment with a known map. Results indicate that the proposed multi-UAV system has improvements in terms of time-cost, the proportion of search area surveyed, as well as successful rates for search and rescue missions.
  arXiv  Detail & Related papers  (2021-07-19T12:54:04Z)
• Batch Exploration with Examples for Scalable Robotic Reinforcement Learning [63.552788688544254]
  Batch Exploration with Examples (BEE) explores relevant regions of the state-space guided by a modest number of human provided images of important states. BEE is able to tackle challenging vision-based manipulation tasks both in simulation and on a real Franka robot.
  arXiv  Detail & Related papers  (2020-10-22T17:49:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.