Camera Feed
📷
Start Camera
DRONE-X1337
Nighthawk
AUTONOMOUS
5:36:44 PM
📶
95%
🔋
89%
SAR Vision
LLaVA is a multimodal large language model for vision-language tasks including VQA.
Inference on Scene of Interest
AI Agent Interface
Connected
Avg Response Time
6s
Model
LLaVA
Confidence
98%
Can you read any signs?
Any hazards in the area?
Any people in danger?
How is the terrain?
Enquire
Clear