Research

Paper

TESTING March 09, 2026

Less is More: Robust Zero-Communication 3D Pursuit-Evasion via Representational Parsimony

Authors

Jialin Ying, Zhihao Li, Zicheng Dong, Guohua Wu, Yihuan Liao

Abstract

Asymmetric 3D pursuit-evasion in cluttered voxel environments is difficult under communication latency, partial observability, and nonholonomic maneuver limits. While many MARL methods rely on richer inter-agent coupling or centralized signals, these dependencies can become fragility sources when communication is delayed or noisy. Building on an inherited path-guided decentralized pursuit scaffold, we study a robustness-oriented question: can representational parsimony improve communication-free coordination? We instantiate this principle with (i) a parsimonious actor observation interface that removes team-coupled channels (83-D to 50-D), and (ii) Contribution-Gated Credit Assignment (CGCA), a locality-aware credit structure for communication-denied cooperation. In Stage-5 evaluation (4 pursuers vs. 1 evader), our configuration reaches 0.753 +/- 0.091 success and 0.223 +/- 0.066 collision, outperforming the 83-D FULL OBS counterpart (0.721 +/- 0.071, 0.253 +/- 0.089). It further shows graceful degradation under speed/yaw/noise/delay stress tests and resilient zero-shot transfer on urban-canyon maps (about 61% success at density 0.24). These results support a practical paradigm shift: explicitly severing redundant cross-agent channels can suppress compounding error cascades and improve robustness in latency-prone deployment.

Metadata

arXiv ID: 2603.08273
Provider: ARXIV
Primary Category: cs.RO
Published: 2026-03-09
Fetched: 2026-03-10 05:43

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.08273v1</id>\n    <title>Less is More: Robust Zero-Communication 3D Pursuit-Evasion via Representational Parsimony</title>\n    <updated>2026-03-09T11:44:04Z</updated>\n    <link href='https://arxiv.org/abs/2603.08273v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.08273v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Asymmetric 3D pursuit-evasion in cluttered voxel environments is difficult under communication latency, partial observability, and nonholonomic maneuver limits. While many MARL methods rely on richer inter-agent coupling or centralized signals, these dependencies can become fragility sources when communication is delayed or noisy. Building on an inherited path-guided decentralized pursuit scaffold, we study a robustness-oriented question: can representational parsimony improve communication-free coordination? We instantiate this principle with (i) a parsimonious actor observation interface that removes team-coupled channels (83-D to 50-D), and (ii) Contribution-Gated Credit Assignment (CGCA), a locality-aware credit structure for communication-denied cooperation. In Stage-5 evaluation (4 pursuers vs. 1 evader), our configuration reaches 0.753 +/- 0.091 success and 0.223 +/- 0.066 collision, outperforming the 83-D FULL OBS counterpart (0.721 +/- 0.071, 0.253 +/- 0.089). It further shows graceful degradation under speed/yaw/noise/delay stress tests and resilient zero-shot transfer on urban-canyon maps (about 61% success at density 0.24). These results support a practical paradigm shift: explicitly severing redundant cross-agent channels can suppress compounding error cascades and improve robustness in latency-prone deployment.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.RO'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.MA'/>\n    <published>2026-03-09T11:44:04Z</published>\n    <arxiv:comment>7 pages, 10 figures. This work has been submitted to the IEEE for possible publication</arxiv:comment>\n    <arxiv:primary_category term='cs.RO'/>\n    <author>\n      <name>Jialin Ying</name>\n    </author>\n    <author>\n      <name>Zhihao Li</name>\n    </author>\n    <author>\n      <name>Zicheng Dong</name>\n    </author>\n    <author>\n      <name>Guohua Wu</name>\n    </author>\n    <author>\n      <name>Yihuan Liao</name>\n    </author>\n  </entry>"
}