DATT: Deep Adaptive Trajectory Tracking for Quadrotor Control

2023/10/13 by Kevin Huang, Rwik Rana, Huang, Kevin +7 · 8 citations
Computer Science · Engineering · #Adaptive Control of Nonlinear Systems #Adaptive Dynamic Programming Control #Advanced Control Systems Optimization #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Electrical engineering #Robotics (cs.RO) #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2310.09053

openalex publication_date 2023/10/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Precise arbitrary trajectory tracking for quadrotors is challenging due to unknown nonlinear dynamics, trajectory infeasibility, and actuation limits. To tackle these challenges, we present Deep Adaptive Trajectory Tracking (DATT), a learning-based approach that can precisely track arbitrary, potentially infeasible trajectories in the presence of large disturbances in the real world. DATT builds on a novel feedforward-feedback-adaptive control structure trained in simulation using reinforcement learning. When deployed on real hardware, DATT is augmented with a disturbance estimator using L1 adaptive control in closed-loop, without any fine-tuning. DATT significantly outperforms competitive adaptive nonlinear and model predictive controllers for both feasible smooth and infeasible trajectories in unsteady wind fields, including challenging scenarios where baselines completely fail. Moreover, DATT can efficiently run online with an inference time less than 3.2 ms, less than 1/4 of the adaptive nonlinear model predictive control baseline

Cited by

• One Ring to Rule Them All: Constrained Distributional Control for Massive-Scale Heterogeneous Robotic Ensemble Systems
• TACO: Trajectory-Aware Controller Optimization for Quadrotors
• AD-NODE: Adaptive Dynamics Learning with Neural ODEs for Mobile Robots Control
• Contextual Neural Moving Horizon Estimation for Robust Quadrotor Control in Varying Conditions
• Rethinking Reference Trajectories in Agile Drone Racing: A Unified Reference-Free Model-Based Controller via MPPI
• RoVerFly: Robust and Versatile Implicit Hybrid Control of Quadrotor-Payload Systems
• Learning on the Fly: Rapid Policy Adaptation via Differentiable Simulation
• Leveling the Playing Field: Carefully Comparing Classical and Learned Controllers for Quadrotor Trajectory Tracking

Related

• Dynamics-Invariant Quadrotor Control using Scale-Aware Deep Reinforcement Learning
• Deep Nonlinear Adaptive Control for Unmanned Aerial Systems Operating under Dynamic Uncertainties
• TACO: Trajectory-Aware Controller Optimization for Quadrotors
• Time-attenuating Twin Delayed DDPG Reinforcement Learning for Trajectory Tracking Control of Quadrotors
• Deep Neural Networks for Improved, Impromptu Trajectory Tracking of Quadrotors