Vision-language-action (VLA) models open a new path toward intuitive robot control by directly linking perception, language, and action in a single end-to-end framework. Yet for UAVs, practical adoption remains difficult because existing solutions are either computationally heavy or insufficiently capable in complex environments. In this work, we propose a practical expert-distillation pipeline (Exp2VLA) for language-conditioned drone navigation. The core idea is to distill expert behavior, obtained from reinforcement learning, teleoperation, or other controllers, into training data that can be used to fine-tune compact VLA models. This allows existing control strategies to be transferred into a unified language-guided navigation model, reducing manual system integration and lowering the barrier for deploying new robot behaviors. Experiments in both sim-to-sim and simulation-in-the-loop settings across multi-object scenes show that the fine-tuned models can handle varied semantic commands and generalize to unseen target compositions. The proposed framework demonstrates how expert-policy distillation can help mechatronic systems move from specialized control modules toward more flexible and reusable robot intelligence.
Team Xiaomi EV-AD VLA: Caption-Guided Retrieval System for Cross-Modal Drone Navigation -- Technical Report for IROS 2025 RoboSense Challenge Track 4
Tsinghua University（清华大学）；Xiaomi EV（小米电动车）；Georgia Institute of Technology（佐治亚理工学院）；National University of Singapore（新加坡国立大学）；The Chinese University of Hong Kong（香港中文大学）；Renmin University of China（中国人民大学）
Indian Institute of Technology, Gandhinagar（印度理工学院甘地纳格尔分校）
This paper proposes a novel framework for autonomous drone navigation through a cluttered environment. Control policies are learnt in a low-level environment during training and are applied to a complex environment during inference. The controller learnt in the training environment is tricked into believing that the robot is still in the training environment when it is actually navigating in a more complex environment. The framework presented in this paper can be adapted to reuse simple policies in more complex tasks. We also show that the framework can be used as an interpretation tool for re…
Delft University of Technology（代尔夫特理工大学）；Micro Air Vehicle lab, Control and Simulation, Delft University of Technology（代尔夫特理工大学控制与仿真系微型飞行器实验室）
Drone racing is becoming a popular sport where human pilots have to control their drones to fly at high speed through complex environments and pass a number of gates in a pre-defined sequence. In this paper, we develop an autonomous system for drones to race fully autonomously using only onboard resources. Instead of commonly used visual navigation methods, such as simultaneous localization and mapping and visual inertial odometry, which are computationally expensive for micro aerial vehicles (MAVs), we developed the highly efficient snake gate detection algorithm for visual navigation, which …
Event-based vision has already revolutionized the perception task for robots by promising faster response, lower energy consumption, and lower bandwidth without introducing motion blur. In this work, a novel deep learning method based on gated recurrent units utilizing sparse convolutions for detecting gates in a race track is proposed using event-based vision for the autonomous drone racing problem. We demonstrate the efficiency and efficacy of the perception pipeline on a real robot platform that can safely navigate a typical autonomous drone racing track in real-time. Throughout the experim…
Drones Guiding Drones: Cooperative Navigation of a Less-Equipped Micro Aerial Vehicle in Cluttered Environments
Multi-robot Systems Group, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague（多机器人系统组，控制系，电气工程系，捷克技术大学）
Drones are not fully trusted yet. Their reliance on radios and cameras for navigation raises safety and privacy concerns. These systems can fail, causing accidents, or be misused for unauthorized recordings. Considering recent regulations allowing commercial drones to operate only at night, we propose a radically new approach where drones obtain navigation information from artificial lighting. In our system, standard light bulbs modulate their intensity to send beacons and drones decode this information with a simple photodiode. This optical information is combined with the inertial and altitu…
This paper presents Navion, an energy-efficient accelerator for visual-inertial odometry (VIO) that enables autonomous navigation of miniaturized robots (e.g., nano drones), and virtual/augmented reality on portable devices. The chip uses inertial measurements and mono/stereo images to estimate the drone's trajectory and a 3D map of the environment. This estimate is obtained by running a state-of-the-art VIO algorithm based on non-linear factor graph optimization, which requires large irregularly structured memories and heterogeneous computation flow. To reduce the energy consumption and footp…
One of the biggest challenges is to determine the deployment and navigation of the drones to benefit the most for different applications. Many research questions have been raised about this topic. For example, drone-enabled wildlife monitoring has received much attention in recent years. Unfortunately, this approach results in significant disturbance to different species of wild animals. Moreover, with the capability of rapidly moving communication supply towards demand when required, the drone equipped with a base station, i.e., drone-cell, is becoming a promising solution for providing cellu…
In this work we showcase the design and assessment of the performance of a multi-camera UAV, when coupled with state-of-the-art planning and mapping algorithms for autonomous navigation. The system leverages state-of-the-art receding horizon exploration techniques for Next-Best-View (NBV) planning with 3D and semantic information, provided by a reconfigurable multi stereo camera system. We employ our approaches in an autonomous drone-based inspection task and evaluate them in an autonomous exploration and mapping scenario. We discuss the advantages and limitations of using multi stereo camera …
Exploring Unstructured Environments using Minimal Sensing on Cooperative Nano-Drones
Computer Vision and Aerial Robotics Group at Universidad Politécnica de Madrid（马德里理工大学计算机视觉与空中机器人小组）；Centre for Automation and Robotics C.A.R. (UPM-CSIC)（自动化与机器人中心（UPM-CSIC））；Department of Mechanical Engineering, Texas A&M University（机械工程系，德克萨斯A&M大学）
The Perspective-n-Point problem aims to estimate the relative pose between a calibrated monocular camera and a known 3D model, by aligning pairs of 2D captured image points to their corresponding 3D points in the model. We suggest an algorithm that runs on weak IoT devices in real-time but still provides provable theoretical guarantees for both running time and correctness. Existing solvers provide only one of these requirements. Our main motivation was to turn the popular DJI's Tello Drone (<90gr, <\$100) into an autonomous drone that navigates in an indoor environment with no external human/…
Korea Advanced Institute of Science and Technology（韩国科学技术院）
This paper presents a vision-based modularized drone racing navigation system that uses a customized convolutional neural network (CNN) for the perception module to produce high-level navigation commands and then leverages a state-of-the-art planner and controller to generate low-level control commands, thus exploiting the advantages of both data-based and model-based approaches. Unlike the state-of-the-art method which only takes the current camera image as the CNN input, we further add the latest three drone states as part of the inputs. Our method outperforms the state-of-the-art method in …
Universidade Federal de Minas Gerais（米纳斯吉拉斯联邦大学）；Instituto Tecnológico Vale (ITV)（淡水河谷技术研究所）
The use of delivery services is an increasing trend worldwide, further enhanced by the COVID pandemic. In this context, drone delivery systems are of great interest as they may allow for faster and cheaper deliveries. This paper presents a navigation system that makes feasible the delivery of parcels with autonomous drones. The system generates a path between a start and a final point and controls the drone to follow this path based on its localization obtained through GPS, 9DoF IMU, and barometer. In the landing phase, information of poses estimated by a marker (ArUco) detection technique usi…
Enabling the capability of assessing risk and making risk-aware decisions is essential to applying reinforcement learning to safety-critical robots like drones. In this paper, we investigate a specific case where a nano quadcopter robot learns to navigate an apriori-unknown cluttered environment under partial observability. We present a distributional reinforcement learning framework to generate adaptive risk-tendency policies. Specifically, we propose to use lower tail conditional variance of the learnt return distribution as intrinsic uncertainty estimation, and use exponentially weighted av…
AirDreamer: Generalist Drone Navigation with World Models
Institute for AI Industry Research, Tsinghua University, Beijing, China（人工智能产业研究院，清华大学，北京，中国）；Department of Electronic Engineering, Tsinghua University, Beijing, China（电子工程系，清华大学，北京，中国）；School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China（遥感与信息工程学院，武汉大学，武汉，中国）
NASA-Jet Propulsion Laboratory, California Institute of Technology（美国国家航空航天局喷气推进实验室，加州理工学院）
Robots and particularly drones are especially useful in exploring extreme environments that pose hazards to humans. To ensure safe operations in these situations, usually perceptually degraded and without good GNSS, it is critical to have a reliable and robust state estimation solution. The main body of literature in robot state estimation focuses on developing complex algorithms favoring accuracy. Typically, these approaches rely on a strong underlying assumption: the main estimation engine will not fail during operation. In contrast, we propose an architecture that pursues robustness in stat…
In this paper, we present a control system that allows a drone to fly autonomously through a series of gates marked with ArUco tags. A simple and low-cost DJI Tello EDU quad-rotor platform was used. Based on the API provided by the manufacturer, we have created a Python application that enables the communication with the drone over WiFi, realises drone positioning based on visual feedback, and generates control. Two control strategies were proposed, compared, and critically analysed. In addition, the accuracy of the positioning method used was measured. The application was evaluated on a lapto…
ETH Zürich（苏黎世联邦理工学院）；University of Zürich（苏黎世大学）；University of Bologna（博洛尼亚大学）；GreenWaves Technologies
Fully-autonomous miniaturized robots (e.g., drones), with artificial intelligence (AI) based visual navigation capabilities are extremely challenging drivers of Internet-of-Things edge intelligence capabilities. Visual navigation based on AI approaches, such as deep neural networks (DNNs) are becoming pervasive for standard-size drones, but are considered out of reach for nanodrones with size of a few cm${}^\mathrm{2}$. In this work, we present the first (to the best of our knowledge) demonstration of a navigation engine for autonomous nano-drones capable of closed-loop end-to-end DNN-based vi…
ETH Zurich（苏黎世联邦理工学院）；Max Planck ETH Center for Learning Systems（马克斯·普朗克-苏黎世联邦理工学习系统中心）
This work presents a case study of a learning-based approach for target driven map-less navigation. The underlying navigation model is an end-to-end neural network which is trained using a combination of expert demonstrations, imitation learning (IL) and reinforcement learning (RL). While RL and IL suffer from a large sample complexity and the distribution mismatch problem, respectively, we show that leveraging prior expert demonstrations for pre-training can reduce the training time to reach at least the same level of performance compared to plain RL by a factor of 5. We present a thorough ev…
Indian Institute of Technology (IIT) Kharagpur（印度理工学院卡拉格普尔分校）
SLAM based techniques are often adopted for solving the navigation problem for the drones in GPS denied environment. Despite the widespread success of these approaches, they have not yet been fully exploited for automation in a warehouse system due to expensive sensors and setup requirements. This paper focuses on the use of low-cost monocular camera-equipped drones for performing warehouse management tasks like inventory scanning and position update. The methods introduced are at par with the existing state of warehouse environment present today, that is, the existence of a grid network for t…
Building upon the theory of Kalman Filtering on Lie Groups, this paper describes an Extended Kalman Filter and Smoother for Loosely Coupled Integration of GNSS/INS tailored for post-processing applications. The approach employs a dynamic model on a matrix Lie Group that aggregates position, velocity, attitude, and the IMU biases as a single element of a Lie group. The development was motivated by a drone-borne Differential Interferometric SAR (DinSAR) application, which requires high-precision navigation information for short-flight missions using low-cost MEMS sensors. The filter and the Rauc…
CeDR-Nav: Cross-Embodiment Mapless Navigation via Offline Demonstration Recasting
The Hong Kong Polytechnic University（香港理工大学）；Eastern Institute of Technology（宁波工程学院）；University of Science and Technology of China（中国科学技术大学）；National University of Singapore（新加坡国立大学）
Technische Universität München（慕尼黑工业大学）；Oculus Research（奥库鲁斯研究院）；RWTH Aachen University（亚琛工业大学）
Micro aerial vehicles (MAVs) are strongly limited in their payload and power capacity. In order to implement autonomous navigation, algorithms are therefore desirable that use sensory equipment that is as small, low-weight, and low-power consuming as possible. In this paper, we propose a method for autonomous MAV navigation and exploration using a low-cost consumer-grade quadrocopter equipped with a monocular camera. Our vision-based navigation system builds on LSD-SLAM which estimates the MAV trajectory and a semi-dense reconstruction of the environment in real-time. Since LSD-SLAM only deter…
DRAL: Deep Reinforcement Adaptive Learning for Multi-UAVs Navigation in Unknown Indoor Environment
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of California, Irvine（加利福尼亚大学欧文分校）；George Washington University（乔治·华盛顿大学）；Beijing Sineva Robot Technology Co., Ltd（北京思知机器人科技有限公司）；University of Southern California（南加利福尼亚大学）；Santa Clara University（圣克拉拉大学）；Mangosuthu University of Technology（曼戈苏图科技大学）
Aerial navigation in GPS-denied, indoor environments, is still an open challenge. Drones can perceive the environment from a richer set of viewpoints, while having more stringent compute and energy constraints than other autonomous platforms. To tackle that problem, this research displays a biologically inspired deep-learning algorithm for simultaneous localization and mapping (SLAM) and its application in a drone navigation system. We propose an unsupervised representation learning method that yields low-dimensional latent state descriptors, that mitigates the sensitivity to perceptual aliasi…
Enhanced Robotic Navigation in Deformable Environments using Learning from Demonstration and Dynamic Modulation
Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich (TUM), Germany（慕尼黑机器人与机器智能研究所（MIRMI），慕尼黑技术大学（TUM））；Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE（穆罕默德·本·扎耶德人工智能大学）
University of Massachusetts Dartmouth（马萨诸塞大学达特茅斯分校）；United States Army Research Laboratory（美国陆军研究实验室）
Traditional imitation learning provides a set of methods and algorithms to learn a reward function or policy from expert demonstrations. Learning from demonstration has been shown to be advantageous for navigation tasks as it allows for machine learning non-experts to quickly provide information needed to learn complex traversal behaviors. However, a minimal set of demonstrations is unlikely to capture all relevant information needed to achieve the desired behavior in every possible future operational environment. Due to distributional shift among environments, a robot may encounter features t…
