Reinforcement Learning with Formal Performance Metrics for Quadcopter Attitude Control under Non-nominal Contexts
Not on the map. Why?
Abstract (arXiv)
We explore the reinforcement learning approach to designing controllers by extensively discussing the case of a quadcopter attitude controller. We provide all details allowing to reproduce our approach, starting with a model of the dynamics of a crazyflie 2.0 under various nominal and non-nominal conditions, including partial motor failures and wind gusts. We develop a robust form of a signal temporal logic to quantitatively evaluate the vehicle's behavior and measure the performance of controllers. The paper thoroughly describes the choices in training algorithms, neural net architecture, hyperparameters, observation space in view of the different performance metrics we have introduced. We discuss the robustness of the obtained controllers, both to partial loss of power for one rotor and to wind gusts and finish by drawing conclusions on practical controller design by reinforcement learning.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 28 of its 76 references that are in the map. First posted on arXiv 27 Jul 2021.
Builds on
28 of 76 references.
References · 28
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2015Continuous control with deep reinforcement learningcited by 3,279
- 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
- 2018Soft Actor-Critic Algorithms and Applicationscited by 1,179
- 2017Safe Reinforcement Learning via Shieldingcited by 427
- 2016Understanding Deep Neural Networks with Rectified Linear Unitscited by 253
- 2019Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guaranteescited by 77
- 2020Deep Drone Acrobaticscited by 66
- 2016Q-Learning for Robust Satisfaction of Signal Temporal Logic Specificationscited by 65
- 2019Reinforcement Learning with Non-Markovian Rewardscited by 45
- 2018Reinforcement Learning for UAV Attitude Controlcited by 40
- 2019Low Level Control of a Quadrotor with Deep Model-Based Reinforcement Learningcited by 40
16 more
- 2020D2RL: Deep Dense Architectures in Reinforcement Learningcited by 40
- 2019Sim-to-(Multi)-Real: Transfer of Low-Level Robust Control Policies to Multiple Quadrotorscited by 36
- 2020Learning to Locomote: Understanding How Environment Design Matters for Deep Reinforcement Learningcited by 27
- 2020A Smooth Robustness Measure of Signal Temporal Logic for Symbolic Controlcited by 21
- 2019Temporal Logic Guided Safe Reinforcement Learning Using Control Barrier Functionscited by 20
- 2019Arithmetic-Geometric Mean Robustness for Control from Signal Temporal Logic Specificationscited by 19
- 2019MAMPS: Safe Multi-Agent Reinforcement Learning via Model Predictive Shieldingcited by 17
- 2019Control from Signal Temporal Logic Specifications with Smooth Cumulative Quantitative Semanticscited by 16
- 2015Correct-by-synthesis reinforcement learning with temporal logic constraintscited by 10
- 2019AReN: Assured ReLU NN Architecture for Model Predictive Control of LTI Systemscited by 9
- 2015Time Robustness in MTL and Expressivity in Hybrid System Falsification (Extended Version)cited by 8
- 2020How to Make Deep RL Work in Practicecited by 8
- 2016Design of a Trajectory Tracking Controller for a Nanoquadcoptercited by 4
- 2020Two-Level Lattice Neural Network Architectures for Control of Nonlinear Systemscited by 4
- 2019Multi-Armed Bandits for Boolean Connectives in Hybrid System Falsification (Extended Version)cited by 2
- 2019Safe Reinforcement Learning with Nonlinear Dynamics via Model Predictive Shieldingcited by 2
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 1.
2 papers.