AERIS: Aerial-Edge Role-Driven Intelligence at Runtime via Orchestrated Language-Model Swarm
For aerial robotics, AERIS addresses the bottleneck of deploying LLMs on resource-constrained edge devices with real-time constraints, enabling practical autonomous navigation.
AERIS is an edge deployment framework for aerial platforms that organizes small language models and lightweight modules into roles, dynamically rebinding them across executors to enable real-time closed-loop operation under heartbeat-constrained scheduling. It achieves long-horizon instruction decomposition via attention-subgoal alignment, and is validated on a UAV Vision-and-Language Navigation benchmark and two real-world experiments.
Integrating large language models into robotic systems holds promise for enhancing autonomy, yet practical deployment remains constrained by strict heartbeat-constrained scheduling and limited computational power. We propose AERIS: an edge deployment framework for aerial platforms. It organizes dedicated small language models combined with lightweight perception and control modules into roles that can be instantiated at runtime, and dynamically rebinds them across different executors as resources change, thereby pushing intelligent capabilities to the edge. AERIS achieves long-horizon instruction decomposition through an attention-subgoal alignment mechanism, which involves annotating the currently active instruction step in messages, thereby progressively approaching long-term objectives. We evaluate AERIS on a high-fidelity UAV Vision-and-Language Navigation benchmark. Under a heartbeat-timed execution mechanism, AERIS maintains a stable perception-decision-control loop between a low-frequency planner and a high-frequency controller, supporting real-time closed-loop operation. We further validate its deployability through two real-world experiments focused on planning and fast response. A demonstration video is provided in the supplementary materials.