Benchmarking Interaction-Oriented Aerial Mobility across Heterogeneous Environments
Overview
CrossFly introduces a benchmark for aerial mobility in diverse environments, with 15K trajectories and the IRR metric. VLA agents show 9.7% success in unseen scenes, highlighting cross-environment challenges in aerial interaction tasks.
Generated from attributed reports · Updated 1 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Environment: simulation
“ntal transitions. When interaction is evaluated, agents are often initialized near the target, leaving the transition from navigation to interaction largely unassessed. This work introduces CrossFly, a benchmark for long-horizon interaction-oriented aerial mobility across heterogeneous environments. CrossFly contains 15K trajectories across more than 20 reconstructed scenes under a unified simulation and evaluation f”
Exact source · revision 1Source owner not reported
Reported quantity · Robot trajectories: 15000 trajectories · trajectory count
“ntal transitions. When interaction is evaluated, agents are often initialized near the target, leaving the transition from navigation to interaction largely unassessed. This work introduces CrossFly, a benchmark for long-horizon interaction-oriented aerial mobility across heterogeneous environments. CrossFly contains 15K trajectories across more than 20 reconstructed scenes under a unified simulation and evaluation f”
Exact source · revision 1Source owner not reported
Reported quantity · scenes: 20 other · Basis not reported
“ntal transitions. When interaction is evaluated, agents are often initialized near the target, leaving the transition from navigation to interaction largely unassessed. This work introduces CrossFly, a benchmark for long-horizon interaction-oriented aerial mobility across heterogeneous environments. CrossFly contains 15K trajectories across more than 20 reconstructed scenes under a unified simulation and evaluation f”
Exact source · revision 1Source owner not reported
Reported quantity · Reported success rate: 9.7 percent · Basis not reported
“eftrightarrow$Outdoor settings are more challenging than single-environment settings, with the highest success rate reaching 9.7% on unseen scenes. A downstream manipulation case study further validates the relevance of interaction-oriented arrival to subsequent physical interaction. We hope CrossFly helps advance aerial embodied intelligence toward unified mobility and physical interaction in heterogeneous environme”
Exact source · revision 1Source owner not reported
Reported quantity · agents: 5 other · Basis not reported
“ramework, covering Indoor, Outdoor, and Indoor$\leftrightarrow$Outdoor trajectories. It further introduces Interaction Readiness Rate (IRR) to assess whether terminal navigation states provide suitable conditions for downstream interaction without assuming a specific manipulation policy. Experiments with five representative aerial vision-language-action (VLA) agents and the proposed CrossFly-Agent show that Indoor$\l”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsBenchmarking Interaction-Oriented Aerial Mobility across Heterogeneous Environments
This research introduces CrossFly, a benchmark for long-horizon interaction-oriented aerial mobility across heterogeneous environments. It includes 15K trajectories across more than 20 reconstructed scenes and introduces the Interaction Readiness Rate (IRR) metric. Experiments with five aerial vision-language-action (VLA) agents show that cross-environment settings are more challenging, achieving a success rate of 9.7% on unseen scenes.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).