24 February 2021 in IEEE Robotics and Automation Letters
With the aim of bridging the gap between high quality reconstruction and robot motion planning, we propose an efficient system that leverages the concept of adaptive-resolution volumetric mapping, which naturally integrates with the hierarchical decomposition of space in an octree data structure. Instead of a Truncated Signed Distance Function (TSDF), we adopt mapping of occupancy probabilities in log-odds representation, which allows to represent both surfaces, as well as the entire free, i.e. observed space, as opposed to unobserved space. We introduce a method for choosing resolution -on the fly- in real-time by means of a multi-scale max-min pooling of the input depth image. The notion of explicit free space mapping paired with the spatial hierarchy in the data structure, as well as map resolution, allows for collision queries, as needed for robot motion planning, at unprecedented speed. We quantitatively evaluate mapping accuracy, memory, runtime performance, and planning performance showing improvements over the state of the art, particularly in cases requiring high resolution maps.
1 June 2017 in Robotics and Autonomous Systems
31 March 2021 in IEEE Robotics and Automation Letters
In robotic applications, a key requirement for safe and efficient motion planning is the ability to map obstacle-free space in unknown, cluttered 3D environments. However, commodity-grade RGB-D cameras commonly used for sensing fail to register valid depth values on shiny, glossy, bright, or distant surfaces, leading to missing data in the map. To address this issue, we propose a framework leveraging probabilistic depth completion as an additional input for spatial mapping. We introduce a deep learning architecture providing uncertainty estimates for the depth completion of RGB-D images. Our pipeline exploits the inferred missing depth values and depth uncertainty to complement raw depth images and improve the speed and quality of free space mapping. Evaluations on synthetic data show that our approach maps significantly more correct free space with relatively low error when compared against using raw data alone in different indoor environments; thereby producing more complete maps that can be directly used for robotic navigation tasks. The performance of our framework is validated using real-world data.
1 September 2018 in International Journal of Advanced Robotic Systems
KGKonstantinos Giannousakis
Konstantinos Giannousakis
This article examines the static area coverage problem by a network of mobile, sensor-equipped agents with imprecise localization. Each agent has uniform radial sensing ability and is governed by first-order kinodynamics. To partition the region of interest, a novel partitioning scheme, the Additively Weighted Guaranteed Voronoi diagram is introduced which takes into account both the agents’ positioning uncertainty and their heterogeneous sensing performance. Each agent’s region of responsibility corresponds to its Additively Weighted Guaranteed Voronoi cell, bounded by hyperbolic arcs. An appropriate gradient ascent-based control scheme is derived so that it guarantees monotonic increase of a coverage objective and is extended with collision avoidance properties. Additionally, a computationally efficient simplified control scheme is offered that is able to achieve comparable performance. Several simulation studies are offered to evaluate the performance of the two control schemes. Finally, two experiments using small differential drive-like robots and an ultra-wideband positioning system were conducted, highlighting the performance of the proposed control scheme in a real world scenario.
8 June 2018 in IEEE Control Systems Letters
A control scheme for the coverage of a convex region by a team of Mobile Aerial Agents (MAAs) under positioning uncertainty is presented in this article. Each MAA is outfitted with a downwards facing camera, the field of view of which differs among agents, resulting in a sensed area which depends on the MAA’s altitude and the view angle of its camera. Additionally, the MAAs’ projections on the ground and altitudes are assumed to be known with varying uncertainty. In order to take into account the MAAs’ positioning uncertainty as well as their varying sensed areas, an Additively Weighted Guaranteed Voronoi (AWGV) partitioning of the region is utilized. Based on this partitioning scheme, a gradient–based algorithm is derived in order to guarantee monotonic increase of an area coverage metric, despite the positioning uncertainty, while also constraining the MAAs’ altitudes. The proposed scheme is evaluated through simulation studies.
24 August 2023 in IEEE Robotics and Automation Letters
Successful path planning for Unmanned Aerial Vehicles (UAVs) in challenging environments with narrow openings, such as disaster areas, requires attitude to be considered. State-of-the-art methods incorporate attitude only in the refinement stage. We introduce a first-of-a-kind global minimum cost path search method based on A* that considers attitude along the path. To make the problem tractable, our method exploits an adaptive and coarse-to-fine approach using global and local A* runs, plus an efficient method to introduce the UAV attitude in the process. We integrate our method with an SE(3) trajectory optimisation method based on a safe-flight-corridor, yielding a complete path planning pipeline. Extensive evaluation is undertaken using the AirSim flight simulator under closed loop control in a set of randomised maps, allowing us to quantitatively assess our method. We show that it achieves significantly higher success rates than the baselines, at a reduced computational burden.