AerialClaw: An Open-Source Framework for LLM-Driven Autonomous Aerial Agents

The paper frames the work as planningControl & PlanningPlanningFiguring out what the robot should do before or during movement.. Start here because it defines what success means and which assumptions the rest of the method inherits.

AerialClaw lets you build UAV systems where an LLM understands natural-language missions and autonomously decides which aerial skills to invoke, observes results, and adapts in a closed loop—replacing manual task-specific pipelines with flexible, reproducible agent behavior. The framework abstracts perceptionPerception & SensingPerceptionThe process of turning raw sensor data into useful understanding of the world., planningControl & PlanningPlanningFiguring out what the robot should do before or during movement., and controlControl & PlanningControlThe method used to make the robot move the way you want. into modular components so developers can focus on mission logic rather than integration plumbing. This means a UAV can interpret "search for survivors in that forest" without pre-coded waypoints, using memory and reflection to improve decisions in real time. When reading the method section, identify the inputs, the learned or engineered representation, and the actionCore ConceptsActionA command the robot sends to its motors, controller, or low-level system. or prediction produced by the system.

For robotics work, the data story is part of the method: check whether the system depends on teleoperationImitation & Reinforcement LearningTeleoperation (teleop)A human remotely controlling the robot, often to collect demonstrations., simulationSimulation & Sim-to-RealSimulationA virtual environment where robots can be trained or tested., internet video, human labels, or robotCore ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. rollouts.

The paper should be judged through its evaluationSimulation & Sim-to-RealEvaluationMeasuring how well a robot system performs. protocol: what data is used, what robotCore ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. or simulator is tested, and which baselineEvaluation & ResearchBaselineA reference method used for comparison. comparisons support the claim. Look for the gap between the headline result and the deploymentSimulation & Sim-to-RealDeploymentPutting the trained system on a real robot. setting you would actually care about.