A VLM+LLM pipeline on an AMR classifies anomalies as Hazardous or Conflict and triggers mitigation actions, reporting 91.2% accuracy and a 6-second average latency in small indoor trials.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Embodied Hazard Mitigation using Vision-Language Models for Autonomous Mobile Robots
A VLM+LLM pipeline on an AMR classifies anomalies as Hazardous or Conflict and triggers mitigation actions, reporting 91.2% accuracy and a 6-second average latency in small indoor trials.