cs.RONov 9, 2026

GeoMind: A Benchmark for Spatial Understanding in Robotic Manipulation

Authors: Jinghe Wang, Xinrui Cao, Duo Wu, Chenghao Gu, Yong Zhong, Linjia Kang, Tianyi Xiong, Zhi Wang

Organizations: Tsinghua Shenzhen International Graduate School, Tsinghua University · Southern University of Science and Technology

Abstract

Robotic manipulation has advanced rapidly in mapping visual observations and language instructions to actions. However, reliable manipulation in open-world environments requires robust spatial understanding: the ability to identify targets in complex layouts (spatial reasoning) and adapt to scenes that continuously evolve through interaction (spatial memory). Yet existing embodied benchmarks fall short in evaluating spatial understanding: they often introduce strong visual cues that bypass spatial reasoning, and focus on static scenes that offer little insight into an agent's capacity for spatial memory. To address this gap, we introduce GeoMind, a systematic benchmark for structured spatial understanding through tabletop manipulation. GeoMind comprises 54 evaluated task variants organized around spatial reasoning and spatial memory. It also incorporates a scalable pipeline that automates the generation and annotation of task instances with verified targets and executable interactions. Extensive evaluations across diverse embodied agents reveal their consistent weaknesses in spatial understanding. Our findings highlight that these agents struggle to track identities after spatial changes and convert relational or geometric constraints into executable actions. We release the GeoMind benchmark at https://github.com/Notfound-JH/GEOMIND-benchmark.git.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks

    Jun 8, 2026Hongcheng Gao, Hailong Qu, Jingyi Tang +18Spatial Reasoning BenchmarksVisual Spatial Reasoning

  2. BEHAVIOR-Spatial Benchmark: Evaluating Spatial Understanding for Robotics

    Oct 25, 2026Sirui Chen, Huang Huang, Qineng Wang +5Spatial Reasoning BenchmarksSpatial Grounding for VLA Models

  3. Seeing What Execution Needs: Benchmarking Task-Conditioned Actionable Spatial Belief for Manipulation

    Nov 6, 2026Yina Jian, Mingkun XuRobot Manipulation BenchmarksActive Vision for Robot Manipulation