Libor Přeučil

A Practical Multirobot Localization System

We present a fast and precise vision-based software intended for multiple robot localization. The core component of the software is a novel and efficient algorithm for black and white pattern detection. The method is robust to variable lighting conditions, achieves sub-pixel precision and its computational complexity is independent of the processed image size. With off-the-shelf computational equipment and low-cost cameras, the core algorithm is able to process hundreds of images per second while tracking hundreds of objects with millimeter precision. In addition, we present the method’s mathematical model, which allows to estimate the expected localization precision, area of coverage, and processing speed from the camera’s intrinsic parameters and hardware’s processing capacity. The correctness of the presented model and performance of the algorithm in real-world conditions is verified in several experiments. Apart from the method description, we also make its source code public at http://purl.org/robotics/whycon; so, it can be used as an enabling technology for various mobile robotic problems.

Coordination and navigation of heterogeneous MAV-UGV formations localized by a 'hawk-eye'-like approach under a model predictive control scheme

An approach for coordination and control of 3D heterogeneous formations of unmanned aerial and ground vehicles under hawk-eye-like relative localization is presented in this paper. The core of the method lies in the use of visual top-view feedback from flying robots for the stabilization of the entire group in a leader–follower formation. We formulate a novel model predictive control-based methodology for guiding the formation. The method is employed to solve the trajectory planning and control of a virtual leader into a desired target region. In addition, the method is used for keeping the following vehicles in the desired shape of the group. The approach is designed to ensure direct visibility between aerial and ground vehicles, which is crucial for the formation stabilization using the hawk-eye-like approach. The presented system is verified in numerous experiments inspired by search-and-rescue applications, where the formation acts as a searching phalanx. In addition, stability and convergence analyses are provided to explicitly determine the limitations of the method in real-world applications.

An application of the self-organizing map in the non-Euclidean Traveling Salesman Problem

An application of the self-organizing map (SOM) to the Traveling Salesman Problem (TSP) has been reported by many researchers, however these approaches are mainly focused on the Euclidean TSP variant. We consider the TSP as a problem formulation for the multi-goal path planning problem in which paths among obstacles have to be found. We apply a simple approximation of the shortest path that seems to be suitable for the SOM adaptation procedure. The approximation is based on a geometrical interpretation of SOM, where weights of neurons represent nodes that are placed in the polygonal domain. The approximation is verified in a set of real problems and experimental results show feasibility of the proposed approach for the SOM based solution of the non-Euclidean TSP.

Fault-Tolerant Formation Driving Mechanism Designed for Heterogeneous MAVs-UGVs Groups

A fault-tolerant method for stabilization and navigation of 3D heterogeneous formations is proposed in this paper. The presented Model Predictive Control (MPC) based approach enables to deploy compact formations of closely cooperating autonomous aerial and ground robots in surveillance scenarios without the necessity of a precise external localization. Instead, the proposed method relies on a top-view visual relative localization provided by the micro aerial vehicles flying above the ground robots and on a simple yet stable visual based navigation using images from an onboard monocular camera. The MPC based schema together with a fault detection and recovery mechanism provide a robust solution applicable in complex environments with static and dynamic obstacles. The core of the proposed leader-follower based formation driving method consists in a representation of the entire 3D formation as a convex hull projected along a desired path that has to be followed by the group. Such an approach provides non-collision solution and respects requirements of the direct visibility between the team members. The uninterrupted visibility is crucial for the employed top-view localization and therefore for the stabilization of the group. The proposed formation driving method and the fault recovery mechanisms are verified by simulations and hardware experiments presented in the paper.

A Sensor Placement Algorithm for a Mobile Robot Inspection Planning

In this paper, we address the inspection planning problem to “see” the whole area of the given workspace by a mobile robot. The problem is decoupled into the sensor placement problem and the multi-goal path planning problem to visit found sensing locations. However the decoupled approach provides a feasible solution, its overall quality can be poor, because the sub-problems are solved independently. We propose a new randomized approach that considers the path planning problem during solution process of the sensor placement problem. The proposed algorithm is based on a guiding of the randomization process according to prior knowledge about the environment. The algorithm is compared with two algorithms already used in the inspection planning. Performance of the algorithms is evaluated in several real environments and for a set of visibility ranges. The proposed algorithm provides better solutions in both evaluated criterions: a number of sensing locations and a length of the inspection path.

High-level motion planning for CPG-driven modular robots

Modular robots may become candidates for search and rescue operations or even for future space missions, as they can change their structure to adapt to terrain conditions and to better fulfill a given task. A core problem in such missions is the ability to visit distant places in rough terrain. Traditionally, the motion of modular robots is modeled using locomotion generators that can provide various gaits, e.g. crawling or walking. However, pure locomotion generation cannot ensure that desired places in a complex environment with obstacles will in fact be reached. These cases require several locomotion generators providing motion primitives that are switched using a planning process that takes the obstacles into account. In this paper, we present a novel motion planning method for modular robots equipped with elementary motion primitives. The utilization of primitives significantly reduces the complexity of the motion planning which enables plans to be created for robots of arbitrary shapes. The primitives used here do not need to cope with environmental changes, which can therefore be realized using simple locomotion generators that are scalable, i.e., the primitives can provide motion for robots with many modules. As the motion primitives are realized using locomotion generators, no reconfiguration is required and the proposed approach can thus be used even for modular robots without self-reconfiguration capabilities. The performance of the proposed algorithm has been experimentally verified in various environments, in physical simulations and also in hardware experiments. A novel method for motion planning of modular robots is presented.The robots are equipped with a vocabulary of motion primitives.The primitives are realized using Central Pattern Generators.The motion planner combines the primitives to achieve a goal.The system is experimentally verified in simulated and real environments.

RRT-path - A Guided Rapidly Exploring Random Tree

Motion planning is one of the most studied problems in robotics. Various methods for solving this problem have been introduced in the last two decades. Applications beyond robotics including 3D object manipulation, computational biology, computational graphics, or drug folding are presented in [10].

FPGA-based module for SURF extraction

We present a complete hardware and software solution of an FPGA-based computer vision embedded module capable of carrying out SURF image features extraction algorithm. Aside from image analysis, the module embeds a Linux distribution that allows to run programs specifically tailored for particular applications. The module is based on a Virtex-5 FXT FPGA which features powerful configurable logic and an embedded PowerPC processor. We describe the module hardware as well as the custom FPGA image processing cores that implement the algorithm’s most computationally expensive process, the interest point detection. The module’s overall performance is evaluated and compared to CPU and GPU-based solutions. Results show that the embedded module achieves comparable distinctiveness to the SURF software implementation running in a standard CPU while being faster and consuming significantly less power and space. Thus, it allows to use the SURF algorithm in applications with power and spatial constraints, such as autonomous navigation of small mobile robots.

Motion planning and control of formations of micro aerial vehicles

Abstract A model predictive control based algorithm for maintenance of leader-follower formations of micro-scale aerial vehicles is proposed in this paper. The approach is designed for stabilization of teams of unmanned quadrotor helicopters and for their motion planning into a distant target region. The presented method of the model predictive control with a planning horizon enables integration of an obstacle avoidance function into the local control of the formation as well as into the global plan of formation movement. Deployment of the method in real-world scenarios, with particular interest in failure recovery and inter-vehicle avoidance, is verified in various simulations.

Visual Topological Mapping

We present an outdoor topological exploration system based on visual recognition. Robot moves through a graph-like environment and creates a topological map, where edges represent paths and vertices their intersections. The algorithm can handle indistinguishable crossings and close loops in the environment with the help of one marked place. The visual navigation system supplies path traversing and crossing detection abilities. Path traversing is purely reactive and relies on color segmentation of an image taken by on-board camera. The crossing passage algorithm reports azimuths of paths leading out of a crossing to the topological subsystem, which decides what path to traverse next. Compass and odometry is then utilized to move the robot to the beginning of picked path. The proposed system performance is tested in simulated and real outdoor environment using a P3AT robotic platform.