This article establishes the novel D+∗, a risk-aware and platform-agnostic heterogeneous global path planner for robotic navigation in complex environments. The proposed planner addresses a ...fundamental bottleneck of occupancy-based path planners related to their dependency on accurate and dense maps. More specifically, their performance is highly affected by poorly reconstructed or sparse areas (e.g. holes in the walls or ceilings) leading to faulty generated paths outside the physical boundaries of the 3-dimensional space. As it will be presented, D+∗ addresses this challenge with three novel contributions, integrated into one solution, namely: (a) the proximity risk, (b) the modeling of the unknown space, and (c) the map updates. By adding a risk layer to spaces that are closer to the occupied ones, some holes are filled, and thus the problematic short-cutting through them to the final goal is prevented. The novel established D+∗ also provides safety marginals to the walls and other obstacles, a property that results in paths that do not cut the corners that could potentially disrupt the platform operation. D+∗ has also the capability to model the unknown space as risk-free areas that should keep the paths inside, e.g in a tunnel environment, and thus heavily reducing the risk of larger shortcuts through openings in the walls. D+∗ is also introducing a dynamic map handling capability that continuously updates with the latest information acquired during the map building process, allowing the planner to use constant map growth and resolve cases of planning over outdated sparser map reconstructions. The proposed path planner is also capable to plan 2D and 3D paths by only changing the input map to a 2D or 3D map and it is independent of the dynamics of the robotic platform. The efficiency of the proposed scheme is experimentally evaluated in multiple real-life experiments where D+∗ is producing successfully proper planned paths, either in 2D in the use case of the Boston dynamics Spot robot or 3D paths in the case of an unmanned areal vehicle in varying and challenging scenarios.
•D+∗ occupancy-based risk-aware, platform-agnostic, heterogeneous global path planner.•Risk areas in proximity to occupied spaces.•Explicitly unknown areas as a risk.•Dynamic 3D map updates and expansions for planning.•D+∗ has been tested and evaluated on a quadruped Spot robot and an UAV in the field.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Tiling robotics have been deployed in autonomous complete area coverage tasks such as floor cleaning, building inspection, and maintenance, surface painting. One class of tiling robotics, ...polyomino-based reconfigurable robots, overcome the limitation of fixed-form robots in achieving high-efficiency area coverage by adopting different morphologies to suit the needs of the current environment. Since the reconfigurable actions of these robots are produced by real-time intelligent decisions during operations, an optimal path planning algorithm is paramount to maximize the area coverage while minimizing the energy consumed by these robots. This paper proposes a complete coverage path planning (CCPP) model trained using deep blackreinforcement learning (RL) for the tetromino based reconfigurable robot platform called hTetro to simultaneously generate the optimal set of shapes for any pretrained arbitrary environment shape with a trajectory that has the least overall cost. To this end, a Convolutional Neural Network (CNN) with Long Short Term Memory (LSTM) layers is trained using Actor Critic Experience Replay (ACER) reinforcement learning algorithm. The results are compared with existing approaches which are based on the traditional tiling theory model, including zigzag, spiral, and greedy search schemes. The model is also compared with the Travelling salesman problem (TSP) based Genetic Algorithm (GA) and Ant Colony Optimization (ACO) schemes. The proposed scheme generates a path with lower cost while also requiring lesser time to generate it. The model is also highly robust and can generate a path in any pretrained arbitrary environments.
•The reinforcement learning based complete coverage path planning is tested on reconfigurable tiling robot called hTetro.•The model minimizing the transformational and rotational actions generates the path with lower cost than tiling methods.•The model is able to determine the optimal set of morphologies required for each environment.•The algorithm can generate a path in a plethora of environments with different obstacle settings.•The model also takes lesser time to generate this path compared to conventional methods.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Eliminating pathogen exposure is an important approach to control outbreaks of epidemics such as COVID-19 (coronavirus disease 2019). To deal with pathogenic environments, using disinfection robots ...is a practicable choice. This research formulates a 3D (three-dimensional) spatial disinfection strategy for a disinfection robot. First, a disinfection robot is designed with an extensible control framework for the integration of additional functions. The robot has eight degrees of freedom that can handle disinfection tasks in complex 3D environments where normal disinfection robots lack the capability to ensure complete disinfection. An ingenious clamping mechanism is designed to increase flexibility and adaptability. Secondly, a new coverage path planning algorithm targeted at the spraying area is used. This algorithm aims to achieve an optimal path via the rotating calipers algorithm after transformation between a 2D (two-dimensional) array and 3D space. Finally, the performance of the designed robot is tested through a series of simulations and experiments in various spaces that humans usually live in. The results demonstrate that the robot can effectively perform disinfection tasks both in computer simulation and in reality.
Sheet metal parts with high-quality surface have wide applications in many manufacturing procedures. However, polishing these parts are challenging due to occurrence of deformations at contact area ...between the polishing tool and part. This stems from the thinness of these parts, making them susceptible to deformations, compared to thick solid parts. To address the above challenge, this study proposes a new robotic polishing path planing method that accounts for such deformations. The proposed method starts by estimating the contact area between the tool head, and the free-form surface of the sheet metal part is estimated using Hertz theory and differential geometry. Next, it uses a polynomial equation—that is derived from FEM-based contact analysis of the part—to calculate the true tool-part contact area under deformations. Then, it combines the contact-area information with a new constant speed robot path planing technique to ensure high-quality robot polishing. Numerical studies on several sample geometries verify the effectiveness of the method.
Full text
Available for:
DOBA, EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, IZUM, KILJ, KISLJ, MFDPS, NLZOH, NUK, OILJ, PILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, SIK, UILJ, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
Optimal path planning for robot manipulator plays an important role in the domain of robotics. In this work, we use Ant colony algorithm as an optimization tool because ACO has been known to be ...robust for search and optimization problems. The Ant colony algorithm has been used to find the optimal path from an initial to a final position in the presence of five obstacles with rectangular shapes and sizes in the robot environment. The algorithm has been tested in simulation and the obtained results show the efficiency and reliability of the proposed method.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Navigation in a dynamic environment requires reactive actions to avoid collision and navigate safely. This paper deals with optimal and reactive motion planning for unmanned air vehicles in a dynamic ...world. A virtual space representation is used to formulate and solve the problem and derive real time optimal trajectories. This formulation allows for the construction of different control subspaces from which optimal control laws for the speed, the flight path angle, and the heading angle are derived. The safety margins are translated to the control subspaces as speed and orientation margins. Closed-form reactive optimal solutions are calculated to achieve reactive motion and avoid collision in each subspace. The dynamic and kinematic constraints are taken into account when planning motion in the control subspaces. Simulation results show the effectiveness of the proposed methods.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
Large-scale spatial data such as air quality, thermal conditions and location signatures play a vital role in a variety of applications. Collecting such data manually can be tedious and labour ...intensive. With the advancement of robotic technologies, it is feasible to automate such tasks using mobile robots with sensing and navigation capabilities. However, due to limited battery lifetime and scarcity of charging stations, it is important to plan paths for the robots that maximize the utility of data collection, also known as the informative path planning (IPP) problem. In this paper, we propose a novel IPP algorithm using reinforcement learning (RL). A constrained exploration and exploitation strategy is designed to address the unique challenges of IPP, and is shown to have fast convergence and better optimality than a classical reinforcement learning approach. Extensive experiments using real-world measurement data demonstrate that the proposed algorithm outperforms state-of-the-art algorithms in most test cases. Interestingly, unlike existing solutions that have to be re-executed when any input parameter changes, our RL-based solution allows a degree of transferability across different problem instances.
Path planning is the basis and prerequisite for unmanned aerial vehicle (UAV) to perform tasks, and it is important to achieve precise location in path planning. This paper focuses on solving the UAV ...path planning problem under the constraint of system positioning error. Some nodes can re-initiate the accumulated flight error to zero and this type of scenario can be modeled as the resource-constrained shortest path problem with re-initialization (RCSPP-R). The additional re-initiation conditions expand the set of viable paths for the original constrained shortest path problem and increasing the search cost. To solve the problem, an effective preprocessing method is proposed to reduce the network nodes. At the same time, a relaxed pruning strategy is introduced into the traditional Pulse algorithm to reduce the search space and avoid more redundant calculations on unfavorable scalable nodes by the proposed heuristic search strategy. To evaluate the accuracy and effectiveness of the proposed algorithm, some numerical experiments were carried out. The results indicate that the three strategies can reduce the search space by 99%, 97% and 80%, respectively, and in the case of a large network, the heuristic algorithm combining the three strategies can improve the efficiency by an average of 80% compared to some classical solution.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, UILJ, UKNU, UL, UM, UPUK
This Special Issue on advanced sensor technologies contains contributions on the latest developments in mobile robotic systems and related research. Various topics with different ideas and ...applications from mobile robotics have found their place. New ideas are presented for mobile robots that specialise in cleaning floors, power lines and HVAC systems. We also find innovative approaches for navigation path planning using local minima-free potential fields, novel path primitives and/or their parameterisation for minimum-time planning, and various control approaches ranging from visual serving to model predictive and adaptive trajectory tracking, applied to wheeled robots, humanoid manipulators and flying robots. Localisation approaches using LiDAR, motion capture systems, fingerprint-based and biomechanical gait systems are also discussed. In addition to advances in methodology, applications in healthcare, mining tunnels, cleaning, warehouses and other areas are mentioned.
Active object detection (AOD) offers significant advantage in expanding the perceptual capacity of a robotics system. AOD is formulated as a sequential action decision process to determine optimal ...viewpoints to identify objects of interest in a visual scene. While reinforcement learning (RL) has been successfully used to solve many AOD problems, conventional RL methods suffer from (i) sample inefficiency, and (ii) unstable outcome due to inter-dependencies of action type (direction of view change) and action range (step size of view change). To address these issues, we propose a novel self-supervised RL method, which employs self-supervised representations of viewpoints to initialize the policy network, and a self-supervised loss on action range to enhance the network parameter optimization. The output and target pairs of self-supervised learning loss are automatically generated from the policy network online prediction and a range shrinkage algorithm (RSA), respectively. The proposed method is evaluated and benchmarked on two public datasets (T-LESS and AVD) using on-policy and off-policy RL algorithms. The results show that our method enhances detection accuracy and achieves faster convergence on both datasets. By evaluating on a more complex environment with a larger state space (where viewpoints are more densely sampled), our method achieves more robust and stable performance. Our experiment on real robot application scenario to disambiguate similar objects in a cluttered scene has also demonstrated the effectiveness of the proposed method.
PDF
