Agile Interception of a Flying Target using Competitive Reinforcement Learning

Timothée Gavin; Simon Lacroix; Murat Bronz

cs.ROMar 17, 2026

Agile Interception of a Flying Target using Competitive Reinforcement Learning

Authors: Timothée Gavin, Simon Lacroix, Murat Bronz

Organizations: ENAC-LAB, LAAS-RIS · IAS, Thales LAS, Rungis, France · LAAS-RIS · RIS, LAAS CNRS, Toulouse, France ·

Abstract

This article presents a solution to intercept an agile drone by another agile drone carrying a catching net. We formulate the interception as a Competitive Reinforcement Learning problem, where the interceptor and the target drone are controlled by separate policies trained with Proximal Policy Optimization (PPO). We introduce a high-fidelity simulation environment that integrates a realistic quadrotor dynamics model and a low-level control architecture implemented in JAX, which allows for fast parallelized execution on GPUs. We train the agents using low-level control, collective thrust and body rates, to achieve agile flights both for the interceptor and the target. We compare the performance of the trained policies in terms of catch rate, time to catch, and crash rate, against common heuristic baselines and show that our solution outperforms these baselines for interception of agile targets. Finally, we demonstrate the performance of the trained policies in a scaled real-world scenario using agile drones inside an indoor flight arena.

Figures & tables

Fig. 1 : A competitive reinforcement learning approach to train both a pursuer and an evader drone for agile interception tasks. Both agents learn low-level control policies that enable them to perform dynamic maneuvers in a high-fidelity simulation environment.

Panel of Figure 2 — Fig. 2 : Control architecture used for the quadrotor dynamics simulation.

Fig. 3 : Schematic of the interception problem. Capture happens when the distance $d$ between the evader’s centre comes within a capture distance of the pursuer’s net.

Coefficient	Value	Coefficient	Value
$\lambda_{\rm catch}$	10.0	$\lambda_{\rm coll}$	0.1
$\lambda_{\rm dist}$	0.001	$\lambda_{\rm fail}$	30.0
$\lambda_{\rm cmd}$	2e-04	$\lambda_{\rm bnd}$	1.0

TABLE I : Reward coefficients.

Hyperparameter	Value
Number of parallel environments (per agent)	1024
Rollout length	128
Learning rate	$5\times 10^{-4}$
Discount factor	0.99
Number of PPO epochs per training data batch	15
Number of minibatches per PPO epoch	1

TABLE II : Training hyperparameters.

Panel of Figure 6 — Fig. 4 : Comparison of learning curves and average episode length.

Pursuer mode	Evader Mode
Pursuer mode	Small arena			Large arena
PP	Hov.	APF	DRL	Hov.	APF	DRL
Catch Rate (%)	96.4	19.5	58.3	100	15.9	24.6
Evade Rate (%)	0.0	47.9	40.0	0.0	66.6	74.6
of which timeout	0.0	0.0	0.8	0.0	0.0	1.1
Crash rates (%)

TABLE III : Performances of the pursuer and the evader in a 40x40x14m (Large) and a 8x8x5m (Small) arena.

Fig. 7 : Simulation results: A full pursuit-evasion episode using the trained policies. The trajectory on the right is a shortened version of the full episode for more visibility. We can see the pursuer first missing the evader in a first attempt, then successfully catching it after a second attempt.

Fig. 8 : A portion of the real-world flight trajectory. The pursuer (blue) successfully caught the evader (green).

Robotic RL

Robotic reinforcement learning uses trial-and-error learning to help robots control, navigate, and manipulate objects.

See all 299 papers

Intercepting an Agile Target with Net-Carrying Drones using Competitive Multi-Agent Reinforcement Learning
Jul 7, 2026Timothée Gavin, Murat BronzRobotic RL Cooperative MARL
ENAC-LAB, LAAS-RIS · *IAS, Thales LAS, Rungis, France · †Dynamic Systems, OPTIM, Fédération ENAC ISAE-SUPAERO ONERA, Université de Toulouse, Toulouse, France +2
Learning Agile Intruder Interception using Differentiable Quadrotor Dynamics
Jul 2, 2026Michael Anoruo, Xiaoyu Tian, Abhishek Rathod +5RL Control Robot Policy Learning
Carnegie Mellon University · Artificial Intelligence Integration Center
Autonomous fixed-wing interception using reinforcement learning
Oct 27, 2026Daan van Hamersveld, Ewoud Smeur, Iurii KriachkoAerial Robotics RL Control

Jul 7, 2026J/K move · Enter open · S save

Intercepting an Agile Target with Net-Carrying Drones using Competitive Multi-Agent Reinforcement Learning

Timothée Gavin, Murat Bronz

ENAC-LAB, LAAS-RIS · *IAS, Thales LAS, Rungis, France · †Dynamic Systems, OPTIM, Fédération ENAC ISAE-SUPAERO ONERA, Université de Toulouse, Toulouse, France+2

Robotic RL Cooperative MARL Multi-Agent Reinforcement Learning

Open paper AskPDF arXiv

This article presents a solution to intercept an agile drone by a team of agile drone carrying catching nets. We formulate the problem as a competitive Multi-Agent Reinforcement Learning (MARL) task. To address the problem of nonstationarity and catastrophic forgetting of agents overfitting to the current opponent strategy, we train the pursuers and the evader using Multi-Agent Proximal Policy Optimization (MAPPO) with Prioritized Fictitious Self Play (PFSP). We train the agents in a high-fidelity simulator using low-level control commands, collective thrust and body rates (CTBR), to achieve agile flights for both the pursuers and the evader. We compare the performance of the trained policies in terms of catch rate, time to catch and crash rates, against heuristic baselines and show that our solution outperforms them. Ablation studies show that PFSP lead to more robust policies that can adapt to different opponent strategies, and that a low-level control commands are crucial for learning performing strategies in the pursuit-evasion task. Finally, a qualitative analysis of the learned behaviours highlights the emergence of cooperative tactics among the pursuers.

Abstract

Robotic RL

Explore similar work

Intercepting an Agile Target with Net-Carrying Drones using Competitive Multi-Agent Reinforcement Learning

Learning Agile Intruder Interception using Differentiable Quadrotor Dynamics

Autonomous fixed-wing interception using reinforcement learning