Conference Paper

GPU accelerated coverage path planning optimized for accuracy in robotic inspection applications

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

In this paper, we introduce a coverage path planning algorithm for inspecting large structures optimized to generate highly accurate 3D models. Robotic inspection of structures such as aircrafts, bridges and buildings, is considered a critical task since missing any detail could affect the performance and integrity of the structures. Additionally, it is a time and resource intensive task that should be performed as efficiently and accurately as possible. The method we propose is a model based coverage path planning approach that generates an optimized path that passes through a set of admissible waypoints to cover a complex structure. The coverage path planning algorithm is developed with a heuristic reward function that exploits our knowledge of the structure mesh model, and the UAV's onboard sensors' models to generate optimal paths that maximizes coverage and accuracy, and minimizes distance travelled. Moreover, we accelerated critical components of the algorithm utilizing the Graphics Processing Unit (GPU) parallel architecture. A set of experiments were conducted in a simulated environment to test the validity of the proposed algorithm.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... The increasing autonomy of robots, as well as their ability to perform actions with a high degree of accuracy, makes them suitable for autonomous 3D reconstruction in order to generate high quality models. If an existing model is provided, then an exploration path could be computed offline, which is then executed by the robot during the reconstruction task [6][7][8][9]. However, these reference models are usually not available, not provided, or inaccurate. ...
... The viewpoint is validated by checking if it is in a free space, within workspace bounds, not colliding with octree map, and the centroid is inside its FOV. The visibility of each viewpoint is then obtained in the cylinder utilizing the concept of occlusion culling described in [7] to check the frontier cluster coverage. Occlusion culling process extracts visible points that exist in a viewpoint FOV. ...
Article
Full-text available
In this paper, a Next Best View (NBV) approach with a profiling stage and a novel utility function for 3D reconstruction using an Unmanned Aerial Vehicle (UAV) is proposed. The proposed approach performs an initial scan in order to build a rough model of the structure that is later used to improve coverage completeness and reduce flight time. Then, a more thorough NBV process is initiated, utilizing the rough model in order to create a dense 3D reconstruction of the structure of interest. The proposed approach exploits the reflectional symmetry feature if it exists in the initial scan of the structure. The proposed NBV approach is implemented with a novel utility function, which consists of four main components: information theory, model density, traveled distance, and predictive measures based on symmetries in the structure. This system outperforms classic information gain approaches with a higher density, entropy reduction and coverage completeness. Simulated and real experiments were conducted and the results show the effectiveness and applicability of the proposed approach.
... Plath planning implemented on GPU have been used for tasks such as inspecting large structures in 3D space [32]and for tackling efficiently multiple agents in large environments [33]. Moreover, the use of path planning algorithms on assistive tools in navigation for blind people is limited to few systems like [2]- [6], so we consider important the advances of path planning algorithms implemented on GPU, for these kinds of applications that require online processing on embedded computers. ...
Article
Full-text available
Blind people present difficulties for reaching objects of interest in the daily life. In this sense, the integration of a path planning module for assisting blind people in purposeful navigation is noteworthy. In this work, we present an algorithm that leverages the high capability of an embedded computer with graphics processing unit (GPU) NVIDIA Jetson TX2 for computing optimal paths to objects of interest. The algorithm computes the optimal path to the objective, considering changes in the environment and changes in the position of the user. The algorithm is efficient for computing new paths when the environment changes by reusing parts of previous computations. In order to compare the performance, the algorithms were implemented and evaluated in MATLAB, C++ and CUDA, for different size of the grid and percentage of unknown obstacles. We found that the implementation on GPU has a speed up of 20 times W.R.T the implementation in C++ and more than 400 times W.R.T the implementation in MATLAB. These results boost us to integrate this module to our main system based on a stereo camera and a haptic belt and so provide to the user assistance in purposeful navigation at real time. T
... We consider the problem of inspection planning where a robot needs to inspect a set of points of interest (POIs) in a given environment with its on-board sensor while optimizing plan cost. This problem has numerous applications such as product surface inspections for industrial quality control [1], structural inspections with unmanned aerial vehicles (UAVs) [2], [3], [4], [5], [6], ship-hull inspections [7], [8], [9], underwater inspections for scientific surveying [10], [11], [12], [13], and patient-anatomy inspections in medicalendoscopic procedures for disease diagnosis [14]. ...
Preprint
The inspection-planning problem calls for computing motions for a robot that allow it to inspect a set of points of interest (POIs) while considering plan quality (e.g., plan length). This problem has applications across many domains where robots can help with inspection, including infrastructure maintenance, construction, and surgery. Incremental Random Inspection-roadmap Search (IRIS) is an asymptotically-optimal inspection planner that was shown to compute higher-quality inspection plans orders of magnitudes faster than the prior state-of-the-art method. In this paper, we significantly accelerate the performance of IRIS to broaden its applicability to more challenging real-world applications. A key computational challenge that IRIS faces is effectively searching roadmaps for inspection plans -- a procedure that dominates its running time. In this work, we show how to incorporate lazy edge-evaluation techniques into \iris's search algorithm and how to reuse search efforts when a roadmap undergoes local changes. These enhancements, which do not compromise IRIS's asymptotic optimality, enable us to compute inspection plans much faster than the original IRIS. We apply IRIS with the enhancements to simulated bridge inspection and surgical inspection tasks and show that our new algorithm for some scenarios can compute similar-quality inspection plans 570x faster than prior work.
... In some cases, a model or blueprint of the structure is provided which can be used to pre-compute paths for the robot to follow as it reconstructs the structure [1,2]. However, these models are not available or provided in many cases. ...
Conference Paper
Full-text available
A modified Next Best View (NBV) approach is presented to improve the 3D reconstruction of complex symmetric structures. Two new stages are introduced to the NBV approach; A profiling stage quickly scans the structure of interest and builds a rough model called the "profile". The profile is relatively sparse but captures the major geometric features of the structure. A symmetry detection stage then determines major lines of symmetry in the profile and labels points of interest. If a point exists in known space but its mirror image lies in unknown space, the mirrored point becomes a point of interest. The reconstruction is performed by a sensor mounted on an Unmanned Aerial Vehicle by using a utility function that incorporates the detected symmetry points. We compare the proposed method with the classical information gain utility function in terms of coverage completeness , total iterations, and travel distance.
Chapter
The most critical process in the inspection is the structure coverage which is a time and resource intensive task. In this paper, Search Space Coverage Path Planning (SSCPP) algorithm for inspecting complex structure using a vehicular system consisting of Unmanned Aerial Vehicle (UAV) is proposed. The proposed algorithm exploits our knowledge of the structure model, and the UAV’s onboard sensors to generate coverage paths that maximizes coverage and accuracy. The algorithm supports the integration of multiple sensors to increase the coverage at each viewpoint and reduce the mission time. A weighted heuristic reward function is developed in the algorithm to target coverage, accuracy, travelled distance and turning angle at each viewpoint. The iterative processes of the proposed algorithm were accelerated exploiting the parallel architecture of the Graphics Processing Unit (GPU). A set of experiments using models of different shapes were conducted in simulated and real environments. The simulation and experimental results show the validity and effectiveness of the proposed algorithm.
Conference Paper
In this paper, we introduce a coverage path planning algorithm with adaptive viewpoint sampling to construct accurate 3D models of complex large structures using Unmanned Aerial Vehicle (UAV). The developed algorithm, Adaptive Search Space Coverage Path Planner (ASSCPP), utilizes an existing 3D reference model of the complex structure and the onboard sensors’ noise models to generate paths that are evaluated based on the traveling distance and the quality of the model. The algorithm generates a set of viewpoints by performing adaptive sampling that directs the search towards areas with low accuracy and low coverage. The algorithm predicts the coverage percentage obtained by following the generated coverage path using the reference model. A set of experiments were conducted in real and simulated environments with structures of different complexities to test the validity of the proposed algorithm.
Conference Paper
Full-text available
For large-scale and long-term simultaneous localization and mapping (SLAM), a robot has to deal with unknown initial positioning caused by either the kidnapped robot problem or multi-session mapping. This paper addresses these problems by tying the SLAM system with a global loop closure detection approach, which intrinsically handles these situations. However, online processing for global loop closure detection approaches is generally influenced by the size of the environment. The proposed graph-based SLAM system uses a memory management approach that only consider portions of the map to satisfy online processing requirements. The approach is tested and demonstrated using five indoor mapping sessions of a building using a robot equipped with a laser rangefinder and a Kinect.
Conference Paper
Full-text available
This paper proposes a path-planning approach to enable a team of unmanned aerial vehicles (UAVs) to efficiently conduct surveillance of sensitive areas. The proposed approach, termed PARCOV (Planner for Autonomous Risk-sensitive Coverage), seeks to maximize the area covered by the sensors mounted on each UAV while maintaining high sensor data quality and minimizing detection risk. PARCOV uses a dynamic grid to keep track of the parts of the space that have been surveyed and the times that they were last surveyed. This information is then used to move the UAVs toward areas that have not been covered in a long time. Moreover, a nonlinear optimization formulation is used to determine the altitude at which each UAV flies. The efficiency and scalability of PARCOV is demonstrated in simulation using complex environments and an increasing number of UAVs to conduct risk-sensitive surveillance.
Book
Full-text available
Provides an introduction to the emerging field of planning and decision making for aerial robots Examines the issues specific to planning and decision making for aerial robots in their environment Presents a variety of techniques and developes some case studies This book provides an introduction to the emerging field of planning and decision making for aerial robots. An aerial robot is the ultimate form of Unmanned Aerial Vehicle, an aircraft endowed with built-in intelligence, requiring no direct human control and able to perform a specific task. It must be able to fly within a partially structured environment, to react and adapt to changing environmental conditions and to accommodate for the uncertainty that exists in the physical world. An aerial robot can be termed as a physical agent that exists and flies in the real 3D world, can sense its environment and act on it to achieve specific goals. So throughout this book, an aerial robot will also be termed as an agent. Fundamental problems in aerial robotics include the tasks of spatial motion, spatial sensing and spatial reasoning. Reasoning in complex environments represents a difficult problem. The issues specific to spatial reasoning are planning and decision making. Planning deals with the trajectory algorithmic development based on the available information, while decision making determines priorities and evaluates potential environmental uncertainties. The issues specific to planning and decision making for aerial robots in their environment are examined in this book and categorized as follows: motion planning, deterministic decision making, decision making under uncertainty, and finally multi-robot planning. A variety of techniques are presented in this book, and a number of relevant case studies are examined. The topics considered in this book are multidisciplinary in nature and lie at the intersection of Robotics, Control Theory, Operational Research and Artificial Intelligence. Content Level » Research Keywords » Aerial Robots - Artificial Intelligence - Decision Making - Planning - UAV Related subjects » Artificial Intelligence - Mechanical Engineering - Robotics
Article
Full-text available
Consumer-grade range cameras such as the Kinect sensor have the potential to be used in mapping applications where accuracy requirements are less strict. To realize this potential insight into the geometric quality of the data acquired by the sensor is essential. In this paper we discuss the calibration of the Kinect sensor, and provide an analysis of the accuracy and resolution of its depth data. Based on a mathematical model of depth measurement from disparity a theoretical error analysis is presented, which provides an insight into the factors influencing the accuracy of the data. Experimental results show that the random error of depth measurement increases with increasing distance to the sensor, and ranges from a few millimeters up to about 4 cm at the maximum range of the sensor. The quality of the data is also found to be influenced by the low resolution of the depth measurements.
Conference Paper
Full-text available
Graphs are powerful data representations favored in many computational domains. Modern GPUs have recently shown promising results in accelerating computationally challenging graph problems but their performance suffered heavily when the graph structure is highly irregular, as most real-world graphs tend to be. In this study, we first observe that the poor performance is caused by work imbalance and is an artifact of a discrepancy between the GPU programming model and the underlying GPU architecture.We then propose a novel virtual warp-centric programming method that exposes the traits of underlying GPU architectures to users. Our method significantly improves the performance of applications with heavily imbalanced workloads, and enables trade-offs between workload imbalance and ALU underutilization for fine-tuning the performance. Our evaluation reveals that our method exhibits up to 9x speedup over previous GPU algorithms and 12x over single thread CPU execution on irregular graphs. When properly configured, it also yields up to 30% improvement over previous GPU algorithms on regular graphs. In addition to performance gains on graph algorithms, our programming method achieves 1.3x to 15.1x speedup on a set of GPU benchmark applications. Our study also confirms that the performance gap between GPUs and other multi-threaded CPU graph implementations is primarily due to the large difference in memory bandwidth.
Article
Coverage Path Planning (CPP) is the task of determining a path that passes over all points of an area or volume of interest while avoiding obstacles. This task is integral to many robotic applications, such as vacuum cleaning robots, painter robots, autonomous underwater vehicles creating image mosaics, demining robots, lawn mowers, automated harvesters, window cleaners and inspection of complex structures, just to name a few. A considerable body of research has addressed the CPP problem. However, no updated surveys on CPP reflecting recent advances in the field have been presented in the past ten years. In this paper, we present a review of the most successful CPP methods, focusing on the achievements made in the past decade. Furthermore, we discuss reported field applications of the described CPP methods. This work aims to become a starting point for researchers who are initiating their endeavors in CPP. Likewise, this work aims to present a comprehensive review of the recent breakthroughs in the field, providing links to the most interesting and successful works.
Article
Three-dimensional models provide a volumetric representation of space which is important for a variety of robotic applications including flying robots and robots that are equipped with manipulators. In this paper, we present an open-source framework to generate volumetric 3D environment models. Our mapping approach is based on octrees and uses probabilistic occupancy estimation. It explicitly represents not only occupied space, but also free and unknown areas. Furthermore, we propose an octree map compression method that keeps the 3D models compact. Our framework is available as an open-source C++ library and has already been successfully applied in several robotics projects. We present a series of experimental results carried out with real robots and on publicly available real-world datasets. The results demonstrate that our approach is able to update the representation efficiently and models the data consistently while keeping the memory requirement at a minimum.