SenseSwarm: Swarm Exploration via Neural Structure Estimation with Shared World-
Overview
SenseSwarm is a research paper proposing a decentralized swarm exploration method that uses a lightweight learned map predictor to enhance mapping efficiency. The approach integrates neural structure estimation with shared world-anticipation, allowing a swarm of robots to rapidly map unknown environments. The method is evaluated on a benchmark of real building floors and simulations, showing improved performance in map reconstruction compared to non-predictive baselines.
From arXiv Robotics — research abstracts
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · square meters: 24000 other · Basis not reported · Differing source assertions
“ucture back into a stigmergic guidance field. Its 709K-parameter predictor is fine-tuned on the swarm's own multi-front observations, which we show is necessary: a single-robot predictor collapses on such views. We build a benchmark of twelve real building floors from HouseExpo, HKUST, and KTH, up to 24,000 square meters, and run 1,620 simulations across nine coordination methods, swarm sizes 32 to 512, and three see”
Exact source · revision 1Source owner not reported
Reported quantity · square meters: 670 other · Basis not reported · Differing source assertions
“ds. On physical coverage the swarm is near parity with a greedy frontier planner, as expected. On map reconstruction, every non-predictive baseline needs 1.3 to 1.9 times longer to reach an 80 percent known map, and SenseSwarm holds an equal-time area lead of about 670 square meters, up to 1,359. Folding the prediction into the shared field matters: the same predictor applied per robot matches our speed but suffers a”
Exact source · revision 1Source owner not reported
Reported quantity · square meters: 1359 other · Basis not reported · Differing source assertions
“ds. On physical coverage the swarm is near parity with a greedy frontier planner, as expected. On map reconstruction, every non-predictive baseline needs 1.3 to 1.9 times longer to reach an 80 percent known map, and SenseSwarm holds an equal-time area lead of about 670 square meters, up to 1,359. Folding the prediction into the shared field matters: the same predictor applied per robot matches our speed but suffers a”
Exact source · revision 1Source owner not reported
Reported quantity · Robot count: 512 robots · Basis not reported · Differing source assertions
“6.9 times higher inter-robot contact rate at 512 robots. The prediction is computed once per shared map, so its cost stayed flat from 32 to 512 robots.”
Exact source · revision 1Source owner not reported
Reported quantity · Robot count: 32 robots · Basis not reported · Differing source assertions
“6.9 times higher inter-robot contact rate at 512 robots. The prediction is computed once per shared map, so its cost stayed flat from 32 to 512 robots.”
Exact source · revision 1Source owner not reported
Evidence dependency changes (3)
- 2026-10-30T22:34:26.583Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-30T22:34:09.820Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-19T22:42:15.675Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalSenseSwarm: Swarm Exploration via Neural Structure Estimation with Shared World-Anticipation for Rapid Mapping
SenseSwarm is a research paper proposing a decentralized swarm exploration method that uses a lightweight learned map predictor to enhance mapping efficiency. The approach integrates neural structure estimation with shared world-anticipation, allowing a swarm of robots to rapidly map unknown environments. The method is evaluated on a benchmark of real building floors and simulations, showing improved performance in map reconstruction compared to non-predictive baselines.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).