Constrained Imitation Learning for a Flapping Wing Unmanned Aerial Vehicle
On the map: Offline RL and imitation learning from data → Imitation learning methods
Abstract (arXiv)
This paper presents a data-driven optimal control policy for a micro flapping wing unmanned aerial vehicle. First, a set of optimal trajectories are computed off-line based on a geometric formulation of dynamics that captures the nonlinear coupling between the large angle flapping motion and the quasi-steady aerodynamics. Then, it is transformed into a feedback control system according to the framework of imitation learning. In particular, an additional constraint is incorporated through the learning process to enhance the stability properties of the resulting controlled dynamics. Compared with conventional methods, the proposed constrained imitation learning eliminates the need to generate additional optimal trajectories on-line, without sacrificing stability. As such, the computational efficiency is substantially improved. Furthermore, this establishes the first nonlinear control system that stabilizes the coupled longitudinal and lateral dynamics of flapping wing aerial vehicle without relying on averaging or linearization. These are illustrated by numerical examples for a simulated model inspired by Monarch butterflies.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 15 of its 34 references that are in the map. First posted on arXiv 8 Jun 2022.
Builds on
15 of 34 references.
References · 15
- 2015Trust Region Policy Optimizationcited by 2,580
- 2017DART: Noise Injection for Robust Imitation Learningcited by 191
- 2013Revisiting Natural Gradient for Deep Networkscited by 159
- 2021End-to-End Constrained Optimization Learning: A Surveycited by 157
- 2021Learning High-Speed Flight in the Wildcited by 128
- 2016Query-Efficient Imitation Learning for End-to-End Autonomous Drivingcited by 84
- 2020Deep Drone Acrobaticscited by 75
- 2015Learning Deep Control Policies for Autonomous Aerial Vehicles with MPC-Guided Policy Searchcited by 42
- 2016PLATO: Policy Learning using Adaptive Trajectory Optimizationcited by 24
- 2020Teaching the Old Dog New Tricks: Supervised Learning with Constraintscited by 16
- 2020Improving Deep Learning Models via Constraint-Based Domain Knowledge: a Brief Surveycited by 16
- 2019Aggressive Online Control of a Quadrotor via Deep Network Representations of Optimality Principlescited by 10
Built on by
Citing papers per year: 2024: 1; 2025: 1; 2026: 1.
3 papers.
- 2025UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobilitycited by 49
- 2024CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Communitycited by 0
- 2026Neural-Primitive: An Efficient End-to-end Local Planner with Primitive-based Imitation Learning for Autonomous Flightcited by 0
- 2026Neural-Primitive: An Efficient End-to-end Local Planner with Primitive-based Imitation Learning for Autonomous Flight21 Aug 2026
- 2025UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility4 Jan 2025
- 2024CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community9 Jul 2024
Similar, not cited
Close in wording, no citation either way
- 2024Learning-based Trajectory Tracking for Bird-inspired Flapping-Wing Robots
- 2025Aerobatic maneuvers in insect-scale flapping-wing aerial robots via deep-learned robust tube model predictive control
- 2025Reinforcement Twinning for Hybrid Control of Flapping-Wing Drones
- 2026Spiking Neural Network Control of a Flapping-Wing Robot on Resource-Constrained Hardware ↗
- 2025Hovering Flight of Soft-Actuated Insect-Scale Micro Aerial Vehicles using Deep Reinforcement Learning
- 2026Multi-Task Reinforcement Learning of Drone Aerobatics by Exploiting Geometric Symmetries
- 2026Learning-based control of a single-DOF Aero system
- 2024Imitation Learning-Based Online Time-Optimal Control with Multiple-Waypoint Constraints for Quadrotors