Swooper: Learning High-Speed Aerial Grasping With a Simple Gripper

2026-02-01

IEEE Robotics and Automation Letters

AI Summary

This work proposes a unified control framework based on deep reinforcement learning to address the challenges of precise control and coordinated grasping during high-speed flight. By employing a two-stage training strategy—first pretraining for agile flight control and then fine-tuning for grasping capability—the approach integrates high-speed navigation and active grasping into a single lightweight neural network for the first time. The resulting policy enables zero-shot transfer to real-world platforms without requiring online adaptation. Experimental results demonstrate that, on a lightweight quadrotor equipped with a commercial off-the-shelf gripper, the system achieves an 84% success rate in physical grasping trials (25 attempts) at speeds up to 1.5 m/s, with inference latency of approximately 1.0 ms—performance comparable to classical methods that rely on more complex gripper mechanisms.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Search and Optimization: Learning to Search
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

High-speed aerial grasping presents significant challenges due to the high demands on precise, responsive flight control and coordinated gripper manipulation. In this work, we propose Swooper, a deep reinforcement learning (DRL) based approach that achieves both precise flight control and active gripper control using a single lightweight neural network policy. Training such a policy directly via DRL is nontrivial due to the complexity of coordinating flight and grasping. To address this, we adopt a two-stage learning strategy: we first pre-train a flight control policy, and then fine-tune it to acquire grasping skills. With the carefully designed reward functions and training framework, the entire training process completes in under 60 minutes on a standard desktop with an Nvidia RTX 3060 GPU. To validate the trained policy in the real world, we develop a lightweight quadrotor grasping platform equipped with a simple off-the-shelf gripper, and deploy the policy in a zero-shot manner on the onboard Raspberry Pi 4B computer, where each inference takes only about 1.0 ms. In 25 real-world trials, our policy achieves an 84% grasp success rate and grasping speeds of up to 1.5 m/s without any fine-tuning. This matches the robustness and agility of state-of-the-art classical systems with sophisticated grippers, highlighting the capability of DRL for learning a robust control policy that seamlessly integrates high-speed flight and grasping.

Problem

• high-speed aerial grasping
• flight control
• gripper manipulation
• quadrotor
• aerial robotics

Innovation

• deep reinforcement learning
• aerial grasping
• two-stage learning
• zero-shot deployment
• lightweight policy