Decentralized Uncertainty-Aware Active Search with a Team of Aerial Robots
The Robotics Institute, Carnegie Mellon University（机器人研究所、卡内基梅隆大学）
Wennie Tabib, John Stecklein, Caleb McDowell, Kshitij Goel, Felix Jonathan, Abhishek Rathod, Meghan Kokoski, Edsel Burkholder, Brian Wallace, Luis Ernesto Navar… 展开作者
Wennie Tabib, John Stecklein, Caleb McDowell, Kshitij Goel, Felix Jonathan, Abhishek Rathod, Meghan Kokoski, Edsel Burkholder, Brian Wallace, Luis Ernesto Navarro-Serment, Nikhil Angad Bakshi, Tejus Gupta, Norman Papernick, David Guttendorf, Erik E. Kahn, Jessica Kasemer, Jesse Holdaway, Jeff Schneider
Rapid search and rescue is critical to maximizing survival rates following natural disasters. However, these efforts are challenged by the need to search large disaster zones, lack of reliability in the communications infrastructure, and a priori unknown numbers of objects of interest (OOIs), such as injured survivors. Aerial robots are increasingly being deployed for search and rescue due to their high mobility, but there remains a gap in deploying multi-robot autonomous aerial systems for methodical search of large environments. Prior works have relied on preprogrammed paths from human operators or are evaluated only in simulation. We bridge these gaps in the state of the art by developing and demonstrating a decentralized active search system, which biases its trajectories to take additional views of uncertain OOIs. The methodology leverages stochasticity for rapid coverage in communication denied scenarios. When communications are available, robots share poses, goals, and OOI information to accelerate the rate of search. Detections from multiple images and vehicles are fused to provide a mean and covariance for each OOI location. Extensive simulations and hardware experiments in Bloomingdale, OH, are conducted to validate the approach. The results demonstrate the active search approach outperforms greedy coverage-based planning in communication-denied scenarios while maintaining comparable performance in communication-enabled scenarios. The results also demonstrate the ability to detect and localize all a priori unknown OOIs with a mean error of approximately 3m at flight altitudes between 50m-60m.
We present a fully integrated autonomous multi- robot aerial system for finding and collecting moving and static objects with unknown locations. This task addresses multiple relevant problems in search and rescue (SAR) robotics such as multi-agent aerial exploration, object detection and tracking, and aerial gripping. Usually, the community tackles these problems individually but the integration into a working system generates extra complexity which is rarely addressed. We show that this task can be solved reliably using only simple components. Our decentralized system uses accurate global sta…
Service Robotics LaboratoryUniversidad Pablo de Olavide（塞维利亚大学服务机器人实验室）；Computer Vision and Aerial Robotics GroupCentre for Automation and Robotics (C.A.R.)Universidad Politécnica de Madrid (UPM-CSIC)（马德里理工大学（UPM-CSIC）自动化与机器人中心计算机视觉与空中机器人小组）；Universidad Pablo de Olavide（塞维利亚大学）；Universidad Politécnica de Madrid (UPM-CSIC)（马德里理工大学（UPM-CSIC））；Centre for Automation and Robotics (C.A.R.)（自动化与机器人中心（C.A.R.））；Computer Vision and Aerial Robotics Group（计算机视觉与空中机器人小组）；Service Robotics Laboratory（服务机器人实验室）
The paper presents a framework for fire extinguishing in an urban scenario by a team of aerial and ground robots. The system was developed to address Challenge 3 of the 2020Mohamed Bin Zayed International Robotics Challenge (MBZIRC). The challenge required to autonomously detect, locate and extinguish fires on different floors of a building, as well as in its surroundings. The multi-robot system developed consists of a heterogeneous robot team of up to three Unmanned Aerial Vehicles (UAV) and one Unmanned Ground Vehicle (UGV). We describe the main hardware and software components for UAV and U…
University of Nevada, Reno（内华达大学里诺分校）；NTNU（挪威科技大学）；ETH Zurich（苏黎世联邦理工学院）
This paper presents a novel strategy for autonomous teamed exploration of subterranean environments using legged and aerial robots. Tailored to the fact that subterranean settings, such as cave networks and underground mines, often involve complex, large-scale and multi-branched topologies, while wireless communication within them can be particularly challenging, this work is structured around the synergy of an onboard exploration path planner that allows for resilient long-term autonomy, and a multi-robot coordination framework. The onboard path planner is unified across legged and flying rob…
Learning to Navigate in Turbulent Flows with Aerial Robot Swarms: A Cooperative Deep Reinforcement Learning Approach
University of Pennsylvania（宾夕法尼亚大学）；Amazon Robotics（亚马逊机器人公司）；Universidad Santo Tomas（圣托马斯大学）；Bethune Cookman University（白求恩-库克曼大学）；Lehigh University（利哈伊大学）
We study the problem of reducing the amount of communication in decentralized target tracking. We focus on the scenario where a team of robots are allowed to move on the boundary of the environment. Their goal is to seek a formation so as to best track a target moving in the interior of the environment. The robots are capable of measuring distances to the target. Decentralized control strategies have been proposed in the past that guarantee that the robots asymptotically converge to the optimal formation. However, existing methods require that the robots exchange information with their neighbo…
In this paper, we present a decentralized and communication-free collision avoidance approach for multi-robot systems that accounts for both robot localization and sensing uncertainties. The approach relies on the computation of an uncertainty-aware safe region for each robot to navigate among other robots and static obstacles in the environment, under the assumption of Gaussian-distributed uncertainty. In particular, at each time step, we construct a chance-constrained buffered uncertainty-aware Voronoi cell (B-UAVC) for each robot given a specified collision probability threshold. Probabilis…
School of Electrical Engineering and Telecommunications, The University of New South Wales（新南威尔士大学电气工程与电信学院）
This research investigates decentralized control of mobile robots specifically for coverage problems. There are different approaches associated with decentralized control strategy for coverage control problems. We perform a comparative review of these approaches and use the approach based on simple local coordination rules. We investigate this extensively used nearest neighbour rule based approach for developing coverage control algorithms. In this approach, a mobile robot gives an equal importance to every neighbour robot coming under its communication range. We develop our control approach b…
Polytechnique Montréal（蒙特利尔综合理工大学）；European Space Agency（欧洲空间局）；Università degli Studi di Modena e Reggio Emilia（摩德纳-雷焦艾米利亚大学）
Redundancy and parallelism make decentralized multi-robot systems appealing solutions for the exploration of extreme environments. However, effective cooperation often requires team-wide connectivity and a carefully designed communication strategy. Several recently proposed decentralized connectivity maintenance approaches exploit elegant algebraic results drawn from spectral graph theory. Yet, these proposals are rarely taken beyond simulations or laboratory implementations. In this work, we present two major contributions: (i) we describe the full-stack implementation---from hardware to soft…
Singapore University of Technology and Design（新加坡科技设计大学）
In this paper, we consider the problem of collectively exploring unknown and dynamic environments with a decentralized heterogeneous multi-robot system consisting of multiple units of two variants of a miniature robot. The first variant-a wheeled ground unit-is at the core of a swarm of floor-mapping robots exhibiting scalability, robustness and flexibility. These properties are systematically tested and quantitatively evaluated in unstructured and dynamic environments, in the absence of any supporting infrastructure. The results of repeated sets of experiments show a consistent performance fo…
We consider a multi-robot system with a team of collaborative robots and multiple tasks that emerges over time. We propose a fully decentralized task and path planning (DTPP) framework consisting of a task allocation module and a localized path planning module. Each task is modeled as a Markov Decision Process (MDP) or a Mixed Observed Markov Decision Process (MOMDP) depending on whether full states or partial states are observable. The task allocation module then aims at maximizing the expected pure reward (reward minus cost) of the robotic team. We fuse the Markov model into a factor graph f…
In densely-packed robot swarms operating in confined regions, spatial interference -- which manifests itself as a competition for physical space -- forces robots to spend more time navigating around each other rather than performing the primary task. This paper develops a decentralized algorithm that enables individual robots to decide whether to stay in the region and contribute to the overall mission, or vacate the region so as to reduce the negative effects that interference has on the overall efficiency of the swarm. We develop this algorithm in the context of a distributed collection task…
University of Edinburgh（爱丁堡大学）；Shenzhen Institute for Artificial Intelligence and Robotics for Society（深圳人工智能与机器人研究院）
Multi-robot teams can achieve more dexterous, complex and heavier payload tasks than a single robot, yet effective collaboration is required. Multi-robot collaboration is extremely challenging due to the different kinematic and dynamics capabilities of the robots, the limited communication between them, and the uncertainty of the system parameters. In this paper, a Decentralized Ability-Aware Adaptive Control is proposed to address these challenges based on two key features. Firstly, the common manipulation task is represented by the proposed nominal task ellipsoid, which is used to maximize e…
Swarms are highly robust systems that offer unique benefits compared to their alternatives. In this work, we propose a bio-inspired and artificial potential field-driven robot swarm control method, where the swarm formation dynamics are modeled on the basis of Markov Random Field (MRF) optimization. We integrate the internal agent-wise local interactions and external environmental influences into the MRF. The optimized formation configurations at different stages of the trajectory can be viewed as formation "shapes" which further allows us to integrate dynamics-constrained motion control of th…
LITIS, University of Le Havre（勒阿弗尔大学LITIS）；GREAH, University of Le Havre（勒阿弗尔大学GREAH）；IUT GEII, University of Le Havre（勒阿弗尔大学IUT GEII）
This paper presents a novel decentralized interactive architecture for aerial and ground mobile robots cooperation. The aerial mobile robot is used to provide a global coverage during an area inspection, while the ground mobile robot is used to provide a local coverage of ground features. We include a human-in-the-loop to provide waypoints for the ground mobile robot to progress safely in the inspected area. The aerial mobile robot follows continuously the ground mobile robot in order to always keep it in its coverage view.
Purpose of review: Recent advances in sensing, actuation, and computation have opened the door to multi-robot systems consisting of hundreds/thousands of robots, with promising applications to automated manufacturing, disaster relief, harvesting, last-mile delivery, port/airport operations, or search and rescue. The community has leveraged model-free multi-agent reinforcement learning (MARL) to devise efficient, scalable controllers for multi-robot systems (MRS). This review aims to provide an analysis of the state-of-the-art in distributed MARL for multi-robot cooperation. Recent findings: De…
This technical report addresses the problem of optimal surveillance of the route followed by a dynamic parade using a team of aerial robots. The dynamic parade is considered to take place within an urban environment, it is discretized and at every iteration, the algorithm computes the best possible placing of the aerial robotic team members, subject to their camera model and the occlusions arising from the environment. As the parade route is only as well covered as its least-covered point, the optimization objective is to place the aerial robots such that they maximize the minimum coverage ove…
Khoury College of Computer Sciences, Northeastern University（东北大学库里计算机科学学院）
In many real-world multi-robot tasks, high-quality solutions often require a team of robots to perform asynchronous actions under decentralized control. Decentralized multi-agent reinforcement learning methods have difficulty learning decentralized policies because of the environment appearing to be non-stationary due to other agents also learning at the same time. In this paper, we address this challenge by proposing a macro-action-based decentralized multi-agent double deep recurrent Q-net (MacDec-MADDRQN) which trains each decentralized Q-net using a centralized Q-net for action selection. …
MIT（麻省理工学院）；Northeastern University（东北大学）；Thomas J. Watson Research Center（托马斯·J·沃森研究中心）；Boeing Research & Technology（波音研究与技术有限公司）
Robust environment perception is essential for decision-making on robots operating in complex domains. Intelligent task execution requires principled treatment of uncertainty sources in a robot's observation model. This is important not only for low-level observations (e.g., accelerometer data), but also for high-level observations such as semantic object labels. This paper formalizes the concept of macro-observations in Decentralized Partially Observable Semi-Markov Decision Processes (Dec-POSMDPs), allowing scalable semantic-level multi-robot decision making. A hierarchical Bayesian approach…
Academy for Engineering and Technology, Fudan University（复旦大学工程与技术研究院）；Huzhou Institute of Zhejiang University（浙江大学湖州研究院）；Zhejiang University（浙江大学）
Designing autonomous aerial robot team systems remains a grand challenge in robotics. Existing works in this field can be categorized as centralized and decentralized. Centralized methods suffer from scale dilemmas, while decentralized ones often lead to poor planning quality. In this paper, we propose an enhanced decentralized autonomous aerial robot team system with group planning. According to the spatial distribution of agents, the system dynamically divides the team into several groups and isolated agents. For conflicts within each group, we propose a novel coordination mechanism named gr…
Hong Kong University of Science and Technology（香港科技大学）
Decentralized state estimation is one of the most fundamental components of autonomous aerial swarm systems in GPS-denied areas yet it still remains a highly challenging research topic. Omni-swarm, a decentralized omnidirectional visual-inertial-UWB state estimation system for aerial swarms, is proposed in this paper to address this research niche. To solve the issues of observability, complicated initialization, insufficient accuracy, and lack of global consistency, we introduce an omnidirectional perception front-end in Omni-swarm. It consists of stereo wide-FoV cameras and ultra-wideband se…
University of Nevada（内华达大学）；NASA Ames Research Center（NASA艾姆斯研究中心）
Wildland fire fighting is a very dangerous job, and the lack of information of the fire front is one of main reasons that causes many accidents. Using unmanned aerial vehicle (UAV) to cover wildfire is promising because it can replace human in hazardous fire tracking and save operation costs significantly. In this paper we propose a distributed control framework designed for a team of UAVs that can closely monitor a wildfire in open space, and precisely track its development. The UAV team, designed for flexible deployment, can effectively avoid in-flight collision as well as cooperate well wit…
Hong Kong University of Science and Technology（香港科技大学）
The collaboration of unmanned aerial vehicles (UAVs) has become a popular research topic for its practicability in multiple scenarios. The collaboration of multiple UAVs, which is also known as aerial swarm is a highly complex system, which still lacks a state-of-art decentralized relative state estimation method. In this paper, we present a novel fully decentralized visual-inertial-UWB fusion framework for relative state estimation and demonstrate the practicability by performing extensive aerial swarm flight experiments. The comparison result with ground truth data from the motion capture sy…
Czech Technical University in Prague（布拉格捷克理工大学）；University of Seville（塞维利亚大学）
This letter describes a method for autonomous aerial cinematography with distributed lighting by a team of unmanned aerial vehicles (UAVs). Although camera-carrying multi-rotor helicopters have become commonplace in cinematography, their usage is limited to scenarios with sufficient natural light or of lighting provided by static artificial lights. We propose to use a formation of unmanned aerial vehicles as a tool for filming a target under illumination from various directions, which is one of the fundamental techniques of traditional cinematography. We decompose the multi-UAV trajectory opti…
University of Cambridge（剑桥大学）；University of Pennsylvania（宾夕法尼亚大学）
Effective communication is key to successful, decentralized, multi-robot path planning. Yet, it is far from obvious what information is crucial to the task at hand, and how and when it must be shared among robots. To side-step these issues and move beyond hand-crafted heuristics, we propose a combined model that automatically synthesizes local communication and decision-making policies for robots navigating in constrained workspaces. Our architecture is composed of a convolutional neural network (CNN) that extracts adequate features from local observations, and a graph neural network (GNN) tha…
University of Seville（塞维利亚大学）；Czech Technical University in Prague（捷克技术大学布拉格分校）
A software architecture aimed at coordinating a team of heterogeneous aerial vehicles for inspection and maintenance operations in high-voltage power line scenarios is presented in this paper. A hierarchical approach deals with high-level tasks by planning and executing complex missions requiring vehicles to support human operators. A resource-constrained problem allows distributing tasks among the team taking into account vehicles' capabilities and battery constraints. Besides, Behavior Trees (BTs) are in charge of mission execution, triggering replanning operations in case of unforeseen even…
During floods, reaching survivors in the shortest possible time is a priority for rescue teams. Given their ability to explore difficult terrain in short spans of time, Unmanned Aerial Vehicles (UAVs) have become an increasingly valuable aid to search and rescue operations. Traditionally, UAVs utilize exhaustive lawnmower exploration patterns to locate stranded survivors, without any information regarding the survivor's whereabouts. In real life disaster scenarios however, on-ground observers provide valuable information to the rescue effort, such as the survivor's last known location and head…
University of Seville（塞维利亚大学）；University of Denver（丹佛大学）；University of Texas at Dallas（德克萨斯大学达拉斯分校）
This paper addresses a synchronization problem that arises when a team of aerial robots (ARs) need to communicate while performing assigned tasks in a cooperative scenario. Each robot has a limited communication range and flies within a previously assigned closed trajectory. When two robots are close enough, a communication link may be established, allowing the robots to exchange information. The goal is to schedule the flights such that the entire system can be synchronized for maximum information exchange, that is, every pair of neighbors always visit the feasible communication link at the s…
A Reflectance Transformation Imaging technique (RTI) realized by multi-rotor Unmanned Aerial Vehicles (UAVs) with a focus on deployment in difficult to access buildings is presented in this letter. RTI is a computational photographic method that captures a surface shape and color of a subject and enables its interactive re-lighting from any direction in a software viewer, revealing details that are not visible with the naked eye. The input of RTI is a set of images captured by a static camera, each one under illumination from a different known direction. We present an innovative approach apply…
New York University, Tandon School of Engineering（纽约大学坦登工程学院）；Technology Innovation Institute（技术创新研究院）
In this paper, we address the vision-based detection and tracking problems of multiple aerial vehicles using a single camera and Inertial Measurement Unit (IMU) as well as the corresponding perception consensus problem (i.e., uniqueness and identical IDs across all observing agents). We design several vision-based decentralized Bayesian multi-tracking filtering strategies to resolve the association between the incoming unsorted measurements obtained by a visual detector algorithm and the tracked agents. We compare their accuracy in different operating conditions as well as their scalability ac…
This paper addresses the motion planning problem for a team of aerial agents under high level goals. We propose a hybrid control strategy that guarantees the accomplishment of each agent's local goal specification, which is given as a temporal logic formula, while guaranteeing inter-agent collision avoidance. In particular, by defining 3-D spheres that bound the agents' volume, we extend previous work on decentralized navigation functions and propose control laws that navigate the agents among predefined regions of interest of the workspace while avoiding collision with each other. This allows…
This work presents an efficient and implementable solution to the problem of joint task allocation and path planning in a multi-UAV platform deployed for biometric data collection in-the-wild. The sensing requirement associated with the task gives rise to an uncanny variant of the traditional vehicle routing problem with coverage/sensing constraints. As is the case in several multi-robot path-planning problems, our problem reduces to an $m$TSP problem. In order to tame the computational challenges associated with the problem, we propose a hierarchical solution that decouples the vehicle routin…
University of the Western Cape（西开普大学）；Cartage University（迦太基大学）
The use of Unmanned Aerial Vehicles (UAVs) in Data transport has attracted a lot of attention and applications, as a modern traffic engineering technique used in data sensing, transport, and delivery to where infrastructure is available for its interpretation. Due to UAVs constraints such as limited power lifetime, it has been necessary to assist them with ground sensors to gather local data which has to be transferred to UAVs upon visiting the sensors. The management of such ground sensor communication together with a team of flying UAVs constitutes an interesting data muling problem which st…
Faculty of Electrical Engineering, Czech Technical University in Prague（布拉格捷克理工大学电气工程学院）
This paper presents a system for autonomous cooperative wall building with a team of Unmanned Aerial Vehicles (UAVs). The system was developed for Challenge 2 of the Mohamed Bin Zayed International Robotics Challenge (MBZIRC) 2020. The wall-building scenario of Challenge 2 featured an initial stack of bricks and wall structure where the individual bricks had to be placed by a team of three UAVs. The objective of the task was to maximize collected points for placing the bricks within the restricted construction time while following the prescribed wall pattern. The proposed approach uses initial…
Visibility-Aware Cooperative Tracking with Decentralized LiDAR-Based Aerial Swarms
Department of Mechanical Engineering, The University of Hong Kong（香港大学机械工程系）；School of Intelligent System Engineering, Sun Yat-sen University（中山大学智能系统工程学院）
University of Nevada, Reno（内华达大学里诺分校）；NASA Ames Research Center（美国国家航空航天局艾姆斯研究中心）
Wild-land fire fighting is a hazardous job. A key task for firefighters is to observe the "fire front" to chart the progress of the fire and areas that will likely spread next. Lack of information of the fire front causes many accidents. Using Unmanned Aerial Vehicles (UAVs) to cover wildfire is promising because it can replace humans in hazardous fire tracking and significantly reduce operation costs. In this paper we propose a distributed control framework designed for a team of UAVs that can closely monitor a wildfire in open space, and precisely track its development. The UAV team, designe…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Maryland（马里兰大学）
In this paper, we study the problem of exploring an unknown Region Of Interest (ROI) with a team of aerial robots. The size and shape of the ROI are unknown to the robots. The objective is to find a tour for each robot such that each point in the ROI must be visible from the field-of-view of some robot along its tour. In conventional exploration using ground robots, the ROI boundary is typically also as an obstacle and robots are naturally constrained to the interior of this ROI. Instead, we study the case where aerial robots are not restricted to flying inside the ROI (and can fly over the bo…
Decentralized and Fully Onboard: Range-Aided Cooperative Localization and Navigation on Micro Aerial Vehicles
Learning Systems and Robotics Lab（学习系统与机器人实验室）；Technical University of Munich（慕尼黑技术大学）；University of Toronto Institute for Aerospace Studies（多伦多大学航空航天研究所）；University of Toronto Robotics Institute（多伦多大学机器人研究所）；Munich Institute of Robotics and Machine Intelligence（慕尼黑机器人与机器智能研究所）；Vector Institute for Artificial Intelligence（人工智能向量研究所）
A mixed aerial and ground robot team, which includes both unmanned ground vehicles (UGVs) and unmanned aerial vehicles (UAVs), is widely used for disaster rescue, social security, precision agriculture, and military missions. However, team capability and corresponding configuration vary since robots have different motion speeds, perceiving ranges, reaching areas, and resilient capabilities to the dynamic environment. Due to heterogeneous robots inside a team and the resilient capabilities of robots, it is challenging to perform a task with an optimal balance between reasonable task allocations…
