mlsanityData to 14 Oct 2026

Learning Agile Intruder Interception using Differentiable Quadrotor Dynamics

arXiv 2607.02472 ↗First posted 2 Jul 2026cs.ROcited by 0

On the map: Deep reinforcement learning methods → RL for robot navigation and UAV control

Abstract (arXiv)

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%.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods. Builds on 16 of its 29 references that are in the map. First posted on arXiv 2 Jul 2026.

Builds on

16 of 29 references.

Closest ancestors · 4

Same direction, newest first

  1. 2026Agile Interception of a Flying Target using Competitive Reinforcement Learning17 Mar
  2. 2025Quadrotor Navigation using Reinforcement Learning with Privileged Information9 Sep
  3. 2025Learned Controllers for Agile Quadrotors in Pursuit-Evasion Games3 Jun
  4. 2025Non-Equilibrium MAV-Capture-MAV via Time-Optimal Planning and Reinforcement Learning9 Mar

Other references · 12

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  4. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  5. 2021Learning High-Speed Flight in the Wildcited by 128
  6. 2024Back to Newton's Laws: Learning Vision-based Agile Flight via Differentiable Physicscited by 45
  7. 2022Training Efficient Controllers via Analytic Policy Gradientcited by 22
  8. 2023On Onboard LiDAR-based Flying Object Detectioncited by 4
  9. 2024Towards Safe Mid-Air Drone Interception: Strategies for Tracking & Capturecited by 4
  10. 2026Simple but Stable, Fast and Safe: Achieve End-to-end Control by High-Fidelity Differentiable Simulationcited by 2
  11. 2024Precise Interception Flight Targets by Image-based Visual Servoing of Multicoptercited by 1
  12. 2025Autonomous 3D Moving Target Encirclement and Interception with Range measurementcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Learning Quadrotor Control From Visual Features Using Differentiable Simulation
  2. 2026VisFly-Lab: Unified Differentiable Framework for First-Order Reinforcement Learning of Quadrotor Control
  3. 2025Dynamics-Invariant Quadrotor Control using Scale-Aware Deep Reinforcement Learning
  4. 2025Leveling the Playing Field: Carefully Comparing Classical and Learned Controllers for Quadrotor Trajectory Tracking
  5. 2026MAVEN: A Meta-Reinforcement Learning Framework for Varying-Dynamics Expertise in Agile Quadrotor Maneuvers
  6. 2024RESC: A Reinforcement Learning Based Search-to-Control Framework for Quadrotor Local Planning in Dense Environments
  7. 2025Reactive Aerobatic Flight via Reinforcement Learning
  8. 2024Demonstrating Agile Flight from Pixels without State Estimation