Meet the AI-powered robotic dog ready to help with emergency response - Robohub

Texas A&M University engineering students have developed an AI-powered robotic dog designed to enhance emergency response efforts such as search-and-rescue missions and disaster operations. The robot integrates a multimodal large language model (MLLM) with a visual memory-based navigation system, enabling it to interpret camera inputs, process voice commands, and perform advanced path planning. This hybrid control architecture allows the robot to make strategic decisions and real-time adjustments, improving its ability to navigate complex, unpredictable environments like disaster zones or unmapped areas where GPS is unavailable. The robotic dog’s memory-driven system allows it to recall and reuse previously traveled paths, increasing navigation efficiency by minimizing redundant exploration. This capability is particularly valuable in emergency scenarios, but the technology’s applications could extend to hospitals, warehouses, assistance for visually impaired individuals, minefield exploration, and hazardous reconnaissance. The project, supported by the National Science Foundation, also involved international collaboration on ROS2 infrastructure and map design. The developers believe this approach to combining vision, language, and memory