A5045281591- Robotic Path Planning Algorithms
- Robotics and Sensor-Based Localization
- UAV Applications and Optimization
- Vehicle Routing Optimization Methods
- Adaptive Control of Nonlinear Systems
- Distributed Control Multi-Agent Systems
- Modular Robots and Swarm Intelligence
- Computational Geometry and Mesh Generation
- Advanced Control Systems Optimization
- Robot Manipulation and Learning
- Transportation and Mobility Innovations
- Robotics and Automated Systems
- Autonomous Vehicle Technology and Safety
- Reinforcement Learning in Robotics
- Guidance and Control Systems
- Transport and Logistics Innovations
- Power Line Inspection Robots
- BIM and Construction Integration
- Teleoperation and Haptic Systems
- Advanced Manufacturing and Logistics Optimization
- Simulation Techniques and Applications
- Human Pose and Action Recognition
- Wildlife-Road Interactions and Conservation
- Control and Dynamics of Mobile Robots
- Aerospace and Aviation Technology
Czech Technical University in Prague
2016-2025
University of Zurich
2022-2023
ETH Zurich
2022
Autonomous, agile quadrotor flight raises fundamental challenges for robotics research in terms of perception, planning, learning, and control. A versatile standardized platform is needed to accelerate let practitioners focus on the core problems. To this end, we present Agilicious, a codesigned hardware software framework tailored autonomous, flight. It completely open source supports both model-based neural network–based controllers. Also, it provides high thrust-to-weight...
Over the last decade, use of autonomous drone systems for surveying, search and rescue, or last-mile delivery has increased exponentially. With rise these applications comes need highly robust, safety-critical algorithms that can operate drones in complex uncertain environments. Additionally, flying fast enables to cover more ground, increasing productivity further strengthening their case. One proxy developing used high-speed navigation is task racing, where researchers program fly through...
Abstract This paper addresses the perception, control, and trajectory planning for an aerial platform to identify land on a moving car at 15 km/hr. The hexacopter unmanned vehicle (UAV), equipped with onboard sensors computer, detects using monocular camera predicts future movement nonlinear motion model. While following car, UAV lands its roof, it attaches itself magnetic legs. proposed system is fully autonomous from takeoff landing. Numerous field tests were conducted throughout year‐long...
Abstract This paper addresses the problem of autonomous cooperative localization, grasping and delivering colored ferrous objects by a team unmanned aerial vehicles (UAVs). In proposed scenario, UAVs is required to maximize reward collecting them predefined location. task consists several subtasks such as coverage path planning, object detection state estimation, UAV self‐localization, precise motion control, trajectory tracking, dropping, decentralized coordination. The failure recovery...
Autonomous Micro Aerial Vehicles (MAVs) have the potential to assist in real-life tasks involving grasping and transportation, but not before solving several difficult research challenges. In this work, we address design, control, estimation, planning problems for cooperative localization, grasping, transportation of objects challenging outdoor scenarios. We demonstrate an autonomous team MAVs able plan safe trajectories manipulation ferrous objects, while guaranteeing interrobot collision...
In this paper, we tackle the problem of flying a quadrotor using time-optimal control policies that can be replanned online when environment changes or encountering unknown disturbances. This is challenging as trajectories consider full dynamics are computationally expensive to generate (order minutes even hours). We introduce sampling-based method for efficient generation paths point-mass model. These then tracked Model Predictive Contouring Control approach considers and single rotor...
We tackle the problem of planning a minimum-time trajectory for quadrotor over sequence specified waypoints in presence obstacles while exploiting full dynamics. This is crucial autonomous search and rescue drone racing scenarios but was, so far, unaddressed by robotics community <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">in its entirety</i> due to challenges minimizing time non-convex constraints posed collision avoidance. Early works...
In this letter, we address the orienteering problem (OP) for curvature constrained vehicle. For a given set of target locations, each with associated reward, OP stands to find tour from prescribed starting location ending such that it maximizes collected rewards while length is within travel budget constraint. The addressed generalization Euclidean called Dubins Orienteering Problem (DOP) in which reward collecting has satisfy limited turning radius DOP consists not only selecting most...
A framework for computing feasible and constrained trajectories a fleet of quad-rotors leveraging on Signal Temporal Logic (STL) specifications power line inspection tasks is proposed in this paper. The planner allows the formulation complex missions that avoid obstacles maintain safe distance between drones while performing planned mission. An optimization problem set to generate optimal strategies satisfy these also take vehicle constraints into account. Further, an event-triggered...
This paper tackles the problem of planning minimum-energy coverage paths for multiple UAVs. The addressed Multi-UAV Coverage Path Planning (mCPP) is a crucial many UAV applications such as inspection and aerial survey. However, typical path-length objective existing approaches does not directly minimize energy consumption, nor allows constraining individual by battery capacity. To this end, we propose novel mCPP method that uses optimal flight speed minimizing consumption per traveled...
This paper introduces a new concept for flexible motion planning and control of industrial robots. Instead closed monolithic architecture, an open service-based framework is proposed. The services can be run hardware-independent on decentralized IT infrastructure (Cloud) allowing fast reconfiguration modules their multiple usage in different tasks. dedicated PC or individual virtual machines inside single computing cluster. proposed was implemented tested the robotic manipulator. Effects...
We tackle the problem of minimum-time flight for a quadrotor through sequence waypoints in presence obstacles while exploiting full dynamics. Early works relied on simplified dynamics or polynomial trajectory representations that did not exploit actuator potential quadrotor, and, thus, resulted suboptimal solutions. Recent can plan trajectories; yet, trajectories are executed with control methods do account obstacles. Thus, successful execution such is prone to errors due model mismatch and...
Robotic simulators play a crucial role in the development and testing of autonomous systems, particularly realm Uncrewed Aerial Vehicles (UAV). However, existing often lack high-level autonomy, hindering their immediate applicability to complex tasks such as navigation unknown environments. This limitation stems from challenge integrating realistic physics, photorealistic rendering, diverse sensor modalities into single simulation environment. At same time, UAV use mostly hand-crafted...
This letter concerns a variant of the orienteering problem (OP) that arises from multi-goal data collection scenarios where robot with limited travel budget is requested to visit given target locations in an environment obstacles. We call introduced OP physical (POP). The POP sets out determine feasible, collision-free, path maximizes collected reward subset and does not exceed budget. combines motion planning combinatorial optimization multiple locations. proposed solution based on variable...
In this paper, we address the Orienteering problem (OP) by unsupervised learning of self-organizing map (SOM). We propose to solve OP with a new algorithm based on SOM for Traveling salesman (TSP). Both problems are similar in finding tour visiting given locations; however, stands determine most valuable that maximizes rewards collected subset locations while keeping length under specified travel budget. The proposed stochastic search is and it constructs feasible solution during each epoch....
Abstract The herein studied problem is motivated by practical needs of our participation in the Mohamed Bin Zayed International Robotics Challenge (MBZIRC) 2017 which a team unmanned aerial vehicles (UAVs) requested to collect objects given area as quickly possible and score according rewards associated with objects. mission time limited, most time‐consuming operation collection themselves. Therefore, we address identify valuable surveillance planning curvature‐constrained trajectories....
In this paper, we address the Dubins Orienteering Problem with Neighborhoods (DOPN) a novel problem derived from regular (OP). OP, one tries to find maximal reward collecting path through subset of given target locations, each associated reward, such that resulting length does not exceed specified travel budget. The (DOP) requires satisfy curvature-constrained model vehicle while reaching precise positions locations. newly introduced DOPN, also respects curvature constrained as in DOP;...
Recently, neural control policies have outperformed existing model-based planning-and-control methods for autonomously navigating quadrotors through cluttered environments in minimum time. However, they are not perception aware, a crucial requirement vision-based navigation due to the camera's limited field of view and underactuated nature quadrotor. We propose learning-based system that achieves perception-aware, agile flight environments. Our method combines imitation learning with...