Abstract
Active perception and manipulation are crucial for robots to interact with complex scenes. Existing benchmarks struggle to evaluate how robots effectively acquire and maintain information in memory in an active manner. To this end, we introduce ActiveArena-Sim, an active-perception simulator with controllable viewpoints and large-scale workspaces as the foundation. Built on this, we propose ActiveArena-Bench, which comprises 35 tasks across 5 fine-grained categories, covering visual exploration and interactive information acquisition. Each task is difficult to solve from passive observations alone, requiring multi-round evidence acquisition and memory-based reasoning. The benchmark provides rich memory annotations, standardized training data, and ID/OOD protocols featuring disjoint scenes, unseen distractor configurations, and novel backgrounds. Moreover, we present ActiveArena-VLA, a modular suite of 13 vision-language-action configurations for controlled studies of memory writing, memory capacity, proprioceptive state, subtask supervision, and high-level planning in active perception. Benchmark results reveal a substantial ID-OOD gap: uniform memory sampling, increased memory capacity under reliable write policies, proprioceptive inputs, and subtask supervision improve OOD generalization, while planner-guided memory management and decision-making achieve performance close to the best-performing configuration using only sparse memory. ActiveArena thus provides a unified testbed to develop and diagnose models for active perception and manipulation.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Li, Y., Zhou, E., Chen, R., Ding, Y., Liu, M., Han, Y., Zhan, J., Wang, L., Zhang, S., & Sheng, L. (2026). ActiveArena: Benchmarking and Understanding Active Perception in Robotic Manipulation. https://omanscience.com/en/articles/activearena-benchmarking-and-understanding-active-perception-in-robotic-manipulation
MLA 9
Li, Yibo, et al. "ActiveArena: Benchmarking and Understanding Active Perception in Robotic Manipulation." https://omanscience.com/en/articles/activearena-benchmarking-and-understanding-active-perception-in-robotic-manipulation.
Chicago (author–date)
Li, Yibo, Enshen Zhou, Rui Chen, Yanjun Ding, Mengzhen Liu, Yi Han, Jiabo Zhan, Lipeng Wang, Shanghang Zhang, and Lu Sheng. 2026. "ActiveArena: Benchmarking and Understanding Active Perception in Robotic Manipulation." https://omanscience.com/en/articles/activearena-benchmarking-and-understanding-active-perception-in-robotic-manipulation.
Harvard
Li, Y., Zhou, E., Chen, R., Ding, Y., Liu, M., Han, Y., Zhan, J., Wang, L., Zhang, S. and Sheng, L. (2026) 'ActiveArena: Benchmarking and Understanding Active Perception in Robotic Manipulation', Available at: https://omanscience.com/en/articles/activearena-benchmarking-and-understanding-active-perception-in-robotic-manipulation.
Vancouver
Li Y, Zhou E, Chen R, Ding Y, Liu M, Han Y, et al. ActiveArena: Benchmarking and Understanding Active Perception in Robotic Manipulation. https://omanscience.com/en/articles/activearena-benchmarking-and-understanding-active-perception-in-robotic-manipulation
IEEE
Y. Li, E. Zhou, R. Chen, Y. Ding, M. Liu, Y. Han, J. Zhan, L. Wang, S. Zhang, and L. Sheng, "ActiveArena: Benchmarking and Understanding Active Perception in Robotic Manipulation," https://omanscience.com/en/articles/activearena-benchmarking-and-understanding-active-perception-in-robotic-manipulation.