Learning Agile Intruder Interception using Differentiable Quadrotor Dynamics

Published July 3, 2026 · Category: Robotics

Overview

arXiv:2607.02472v1 Announce Type: new Abstract: This paper presents a methodology for learning a control policy to intercept an intruder using the 3D direction unit vector to the intruder and the interceptor state. Prior deep reinforcement learning approaches assume either relative position or distance to the intruder is available, but this information is not readily accessible in real-world applications that employ passive, monocular camera sensors. Instead, we propose a solution that leverages an analytical policy gradient method using differentiable quadrotor dynamics to learn agile interception at speeds up to 10 m/s. The proposed approach outperforms baseline methods that utilize simplified point mass dynamics by an average of 30%.

Source

Originally published at arxiv.org.

Related Articles

• Exact equivariance, kept through training, buys zero-shot generalisation across the symmetry group
• One Demonstration Is Enough for Real-World Robotic Reinforcement Learning
• Human Supervisor Workload Prediction: Lag Horizon Selection