MAD: Mapping-Aware World Models for Agile Quadrotor Flight
State Key Lab of Autonomous Intelligent Unmanned Systems, Beijing Institute of Technology, Beijing 100081, China（自主智能无人系统国家重点实验室，北京理工大学，北京100081，中国）；Zhongguancun Academy, Beijing 100094, China（中关村学院，北京100094，中国）；School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院）；Department of Mechanical and Energy Engineering, Southern University of Science and Technology（南方科技大学机械与能源工程系）；Harbin Institute of Technology（哈尔滨工业大学）
Xinhong Zhang, Runqing Wang, Yunfan Ren, Ding Yu, Boyu Zhou, Jian Sun, Fang Deng, Jie Chen, Gang Wang
Agile quadrotor flight in cluttered scenes requires more than a reactive mapping from a depth image to a control command: the vehicle must remember which regions have been observed, infer nearby occupied space, and act under partial visibility and tight latency. In this paper, we present Mapping-Aware Dreamer (MAD), a geometry-aware world model for vision-based quadrotor flight. Instead of using raw-image reconstruction as the main self-supervised objective, MAD learns recurrent latent dynamics that reconstruct robocentric occupancy and visibility grid maps together with proprioceptive states. This design forces the latent state to encode local geometry, visibility history, and ego-motion in a form that is directly relevant to collision avoidance. MAD is trained in DiffAero using a GPU-parallel map-construction module that provides high-throughput supervision for occupancy and visibility. The learned representation is used in three policy-learning modes: imagination-based MAD-Dreamer and feature-extractor variants based on PPO and SHAC. Across visual navigation and racing tasks, MAD-based agents achieve higher success rates, faster flight, and better cross-task transfer than corresponding vision-only baselines. The model also produces interpretable map predictions and accurate ego-motion estimates from depth observations. We further deploy the learned policy on a physical quadrotor with an Intel RealSense D435i and demonstrate safe indoor and outdoor flight under limited sensing, reaching 9.66 m/s in simulation and 5.05 m/s in real-world forest experiments. These results show that mapping-aware world models provide a practical middle ground between modular aerial navigation and end-to-end learning.
In this paper, we tackle the problem of flying a quadrotor using time-optimal control policies that can be replanned online when the environment changes or when encountering unknown disturbances. This problem is challenging as the time-optimal trajectories that consider the full quadrotor dynamics are computationally expensive to generate (order of minutes or even hours). We introduce a sampling-based method for efficient generation of time-optimal paths of a point-mass model. These paths are then tracked using a Model Predictive Contouring Control approach that considers the full quadrotor dy…
APACE: Agile and Perception-Aware Trajectory Generation for Quadrotor Flights
School of Artificial Intelligence, Sun Yat-Sen University（中山大学人工智能学院）；Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology（香港科技大学电子与计算机工程学系）
We present a perception constrained visual predictive control (PCVPC) algorithm for quadrotors to enable aggressive flights without using any position information. Our framework leverages nonlinear model predictive control (NMPC) to formulate a constrained image-based visual servoing (IBVS) problem. The quadrotor dynamics, image dynamics, actuation constraints, and visibility constraints are taken into account to handle quadrotor maneuvers with high agility. Two main challenges of applying IBVS to agile drones are considered: (i) high sensitivity of depths to intense orientation changes, and (…
Quadrotors are extremely agile, so much in fact, that classic first-principle-models come to their limits. Aerodynamic effects, while insignificant at low speeds, become the dominant model defect during high speeds or agile maneuvers. Accurate modeling is needed to design robust high-performance control systems and enable flying close to the platform's physical limits. We propose a hybrid approach fusing first principles and learning to model quadrotors and their aerodynamic effects with unprecedented accuracy. First principles fail to capture such aerodynamic effects, rendering traditional ap…
Learned Controllers for Agile Quadrotors in Pursuit-Evasion Games
Robotics, Perception and Learning Lab., School of Electrical Engineering and Computer Science, Royal Institute of Technology (KTH)（机器人感知与学习实验室，电气工程与计算机科学学院，皇家理工学院（KTH））
University of Zurich（苏黎世大学）；ETH Zurich（苏黎世联邦理工学院）；LAAS-CNRS（法国国家科学研究中心图卢兹自动化与系统分析实验室）；Université de Toulouse（图卢兹大学）；CNRS（法国国家科学研究中心）
In this paper, we prove that the dynamical model of a quadrotor subject to linear rotor drag effects is differentially flat in its position and heading. We use this property to compute feed-forward control terms directly from a reference trajectory to be tracked. The obtained feed-forward terms are then used in a cascaded, nonlinear feedback control law that enables accurate agile flight with quadrotors. Compared to state-of-the-art control methods, which treat the rotor drag as an unknown disturbance, our method reduces the trajectory tracking error significantly. Finally, we present a method…
We consider the problem of generating a time-optimal quadrotor trajectory that attains a set of prescribed waypoints. This problem is challenging since the optimal trajectory is located on the boundary of the set of dynamically feasible trajectories. This boundary is hard to model as it involves limitations of the entire system, including hardware and software, in agile high-speed flight. In this work, we propose a multi-fidelity Bayesian optimization framework that models the feasibility constraints based on analytical approximation, numerical simulation, and real-world flight experiments. By…
This paper proposes a systematic solution that uses an unmanned aerial vehicle (UAV) to aggressively and safely track an agile target. The solution properly handles the challenging situations where the intent of the target and the dense environments are unknown to the UAV. Our work is divided into two parts: target motion prediction and tracking trajectory planning. The target motion prediction method utilizes target observations to reliably predict the future motion of the target considering dynamic constraints. The tracking trajectory planner follows the traditional hierarchical workflow.A t…
University of Zurich（苏黎世大学）；ETH Zurich（苏黎世联邦理工学院）；Intel Labs（英特尔实验室）
Autonomous agile flight brings up fundamental challenges in robotics, such as coping with unreliable state estimation, reacting optimally to dynamically changing environments, and coupling perception and action in real time under severe resource constraints. In this paper, we consider these challenges in the context of autonomous, vision-based drone racing in dynamic environments. Our approach combines a convolutional neural network (CNN) with a state-of-the-art path-planning and control system. The CNN directly maps raw images into a robust representation in the form of a waypoint and desired…
Curriculum Reinforcement Learning for Quadrotor Racing with Random Obstacles
School of Automation and Perception, Shanghai Jiao Tong University（自动化与感知学院，上海交通大学）；Faculty of Aerospace Engineering, Delft University of Technology（航空航天工程学院，代尔夫特理工大学）
Conventional quadrotors received great attention in trajectory design and fault-tolerant control in these years. The direction of each thrust is perpendicular to the body because of the geometrics in mechanical design. Comparing with the conventional quadrotor, a novel quadrotor named quad-tilt-rotor brings better freedom in manipulating the thrust vector. Quad-tilt-rotor augments the additional degrees of freedom in the thrust, providing the possibility of violating the normal direction of the thrust in the conventional quadrotor. This provides the ability of greater agility in control. This …
Minimum-time navigation within constrained and dynamic environments is of special relevance in robotics. Seeking time-optimality, while guaranteeing the integrity of time-varying spatial bounds, is an appealing trade-off for agile vehicles, such as quadrotors. State of the art approaches, either assume bounds to be static and generate time-optimal trajectories offline, or compromise time-optimality for constraint satisfaction. Leveraging nonlinear model predictive control and a path parametric reformulation of the quadrotor model, we present a real-time control that approximates time-optimal b…
We present a novel, decentralized collision avoidance algorithm for navigating a swarm of quadrotors in dense environments populated with static and dynamic obstacles. Our algorithm relies on the concept of Optimal Reciprocal CollisionAvoidance (ORCA) and utilizes a flatness-based Model Predictive Control (MPC) to generate local collision-free trajectories for each quadrotor. We feedforward linearize the non-linear dynamics of the quadrotor and subsequently use this linearized model in our MPC framework. Our method is downwash conscious and computes safe trajectories that avoid quadrotors from…
Quadrotors are highly nonlinear dynamical systems that require carefully tuned controllers to be pushed to their physical limits. Recently, learning-based control policies have been proposed for quadrotors, as they would potentially allow learning direct mappings from high-dimensional raw sensory observations to actions. Due to sample inefficiency, training such learned controllers on the real platform is impractical or even impossible. Training in simulation is attractive but requires to transfer policies between domains, which demands trained policies to be robust to such domain gap. In this…
Transporting objects using aerial robots has been widely studied in the literature. Still, those approaches always assume that the connection between the quadrotor and the load is made in a previous stage. However, that previous stage usually requires human intervention, and autonomous procedures to locate and attach the object are not considered. Additionally, most of the approaches assume cables as rigid links, but manipulating cables requires considering the state when the cables are hanging. In this work, we design and control a catenary robot. Our robot is able to transport hook-shaped ob…
Agile quadrotor flight in challenging environments has the potential to revolutionize shipping, transportation, and search and rescue applications. Nonlinear model predictive control (NMPC) has recently shown promising results for agile quadrotor control, but relies on highly accurate models for maximum performance. Hence, model uncertainties in the form of unmodeled complex aerodynamic effects, varying payloads and parameter mismatch will degrade overall system performance. In this paper, we propose L1-NMPC, a novel hybrid adaptive NMPC to learn model uncertainties online and immediately comp…
Quadrotors are among the most agile flying robots. However, planning time-optimal trajectories at the actuation limit through multiple waypoints remains an open problem. This is crucial for applications such as inspection, delivery, search and rescue, and drone racing. Early works used polynomial trajectory formulations, which do not exploit the full actuator potential because of their inherent smoothness. Recent works resorted to numerical optimization but require waypoints to be allocated as costs or constraints at specific discrete times. However, this time allocation is a priori unknown an…
Accurately modeling quadrotor's system dynamics is critical for guaranteeing agile, safe, and stable navigation. The model needs to capture the system behavior in multiple flight regimes and operating conditions, including those producing highly nonlinear effects such as aerodynamic forces and torques, rotor interactions, or possible system configuration modifications. Classical approaches rely on handcrafted models and struggle to generalize and scale to capture these effects. In this paper, we present a novel Physics-Inspired Temporal Convolutional Network (PI-TCN) approach to learning quadr…
