ICRA 2025 highlights key research using Clearpath robots, covering advancements in autonomous navigation with asymmetric cost-aware planning, vision-language models for outdoor navigation, and anomaly detection in home environments. The dangers of jailbreaking LLM-controlled robots and UAV-UGV cooperative routing for mission
Table of contents
QuasiNav: Asymmetric Cost-Aware Navigation Planning with Constrained Quasimetric Reinforcement LearningVLM-GroNav: Robot Navigation Using Physically Grounded Vision-Language Models in Outdoor Environments“Don’t Forget to Put the Milk Back!” Dataset for Enabling Embodied Agents to Detect Anomalous SituationsJailbreaking LLM-Controlled RobotsRisk-Aware Energy-Constrained UAV-UGV Cooperative Routing Using Attention-Guided Reinforcement LearningSort: