CleanUpBench: Embodied Sweeping and Grasping Benchmark

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Wenbo, Chen, Guanting, Zhao, Tao, Wang, Jiyao, Hu, Tianxin, Liao, Yuwen, Guo, Weixiang, Yuan, Shenghai
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913979249459200
author Li, Wenbo
Chen, Guanting
Zhao, Tao
Wang, Jiyao
Hu, Tianxin
Liao, Yuwen
Guo, Weixiang
Yuan, Shenghai
author_facet Li, Wenbo
Chen, Guanting
Zhao, Tao
Wang, Jiyao
Hu, Tianxin
Liao, Yuwen
Guo, Weixiang
Yuan, Shenghai
contents Embodied AI benchmarks have advanced navigation, manipulation, and reasoning, but most target complex humanoid agents or large-scale simulations that are far from real-world deployment. In contrast, mobile cleaning robots with dual mode capabilities, such as sweeping and grasping, are rapidly emerging as realistic and commercially viable platforms. However, no benchmark currently exists that systematically evaluates these agents in structured, multi-target cleaning tasks, revealing a critical gap between academic research and real-world applications. We introduce CleanUpBench, a reproducible and extensible benchmark for evaluating embodied agents in realistic indoor cleaning scenarios. Built on NVIDIA Isaac Sim, CleanUpBench simulates a mobile service robot equipped with a sweeping mechanism and a six-degree-of-freedom robotic arm, enabling interaction with heterogeneous objects. The benchmark includes manually designed environments and one procedurally generated layout to assess generalization, along with a comprehensive evaluation suite covering task completion, spatial efficiency, motion quality, and control performance. To support comparative studies, we provide baseline agents based on heuristic strategies and map-based planning. CleanUpBench bridges the gap between low-level skill evaluation and full-scene testing, offering a scalable testbed for grounded, embodied intelligence in everyday settings.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05543
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CleanUpBench: Embodied Sweeping and Grasping Benchmark
Li, Wenbo
Chen, Guanting
Zhao, Tao
Wang, Jiyao
Hu, Tianxin
Liao, Yuwen
Guo, Weixiang
Yuan, Shenghai
Robotics
Embodied AI benchmarks have advanced navigation, manipulation, and reasoning, but most target complex humanoid agents or large-scale simulations that are far from real-world deployment. In contrast, mobile cleaning robots with dual mode capabilities, such as sweeping and grasping, are rapidly emerging as realistic and commercially viable platforms. However, no benchmark currently exists that systematically evaluates these agents in structured, multi-target cleaning tasks, revealing a critical gap between academic research and real-world applications. We introduce CleanUpBench, a reproducible and extensible benchmark for evaluating embodied agents in realistic indoor cleaning scenarios. Built on NVIDIA Isaac Sim, CleanUpBench simulates a mobile service robot equipped with a sweeping mechanism and a six-degree-of-freedom robotic arm, enabling interaction with heterogeneous objects. The benchmark includes manually designed environments and one procedurally generated layout to assess generalization, along with a comprehensive evaluation suite covering task completion, spatial efficiency, motion quality, and control performance. To support comparative studies, we provide baseline agents based on heuristic strategies and map-based planning. CleanUpBench bridges the gap between low-level skill evaluation and full-scene testing, offering a scalable testbed for grounded, embodied intelligence in everyday settings.
title CleanUpBench: Embodied Sweeping and Grasping Benchmark
topic Robotics
url https://arxiv.org/abs/2508.05543