Improving Drone Racing Performance Through Iterative Learning MPC
Autonomous drone racing presents a challenging control problem, requiring real-time decision-making and robust handling of nonlinear system dynamics. While iterative learning model predictive control (LMPC) offers a promising framework for iterative performance improvement, its direct application to drone racing faces challenges like real-time compatibility or the trade-off between time-optimal and safe traversal. In this paper, we enhance LMPC with three key innovations: (1) an adaptive cost function that dynamically weights time-optimal tracking against centerline adherence, (2) a shifted local safe set to prevent excessive shortcutting and enable more robust iterative updates, and (3) a Cartesian-based formulation that accommodates safety constraints without the singularities or integration errors associated with Frenet-frame transformations. Results from extensive simulation and real-world experiments demonstrate that our improved algorithm can optimize initial trajectories generated by a wide range of controllers with varying levels of tuning for a maximum improvement in lap time by 60.85%. Even applied to the most aggressively tuned state-of-the-art model-based controller, MPCC++, on a real drone, a 6.05% improvement is still achieved. Overall, the proposed method pushes the drone toward faster traversal and avoids collisions in simulation and real-world experiments, making it a practical solution to improve the peak performance of drone racing.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Curriculum-Based Iterative Self-Play for Scalable Multi-Drone Racing
The coordination of multiple autonomous agents in high-speed, competitive environments represents a significant engineering challenge. This paper presents CRUISE (Curriculum-Based Iterative Self-Play for Scalable Multi-D…
Reinforcement LearningSPIRAL: Self-Play Incremental Racing Algorithm for Learning in Multi-Drone Competitions
This paper introduces SPIRAL (Self-Play Incremental Racing Algorithm for Learning), a novel approach for training autonomous drones in multi-agent racing competitions. SPIRAL distinctively employs a self-play mechanism t…
Reinforcement LearningAlphaPilot: Autonomous Drone Racing
This paper presents a novel system for autonomous, vision-based drone racing combining learned data abstraction, nonlinear filtering, and time-optimal trajectory planning. The system has successfully been deployed at the…
NavigateTrajectory PlanningLearning Generalizable Policy for Obstacle-Aware Autonomous Drone Racing
Autonomous drone racing has gained attention for its potential to push the boundaries of drone navigation technologies. While much of the existing research focuses on racing in obstacle-free environments, few studies hav…
Deep Reinforcement LearningDrone navigationLong-Term Planning with Deep Reinforcement Learning on Autonomous Drones
In this paper, we study a long-term planning scenario that is based on drone racing competitions held in real life. We conducted this experiment on a framework created for "Game of Drones: Drone Racing Competition" at Ne…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)