Probabilistic Roadmap Planners Research Articles

An Improved Probabilistic Roadmap Planning Method for Safe Indoor Flights of Unmanned Aerial Vehicles

Unmanned aerial vehicles (UAVs) have been widely used in industry and daily life, where safety is the primary consideration, resulting in their use in open outdoor environments, which are wider than complex indoor environments. However, the demand is growing for deploying UAVs indoors for specific tasks such as inspection, supervision, transportation, and management. To broaden indoor applications while ensuring safety, the quadrotor is notable for its motion flexibility, particularly in the vertical direction. In this study, we developed an improved probabilistic roadmap (PRM) planning method for safe indoor flights based on the assumption of a quadrotor model UAV. First, to represent and model a 3D environment, we generated a reduced-dimensional map using a point cloud projection method. Second, to deploy UAV indoor missions and ensure safety, we improved the PRM planning method and obtained a collision-free flight path for the UAV. Lastly, to optimize the overall mission, we performed postprocessing optimization on the path, avoiding redundant flights. We conducted experiments to validate the effectiveness and efficiency of the proposed method on both desktop and onboard PC, in terms of path-finding success rate, planning time, and path length. The results showed that our method ensures safe indoor UAV flights while significantly improving computational efficiency.

Gesture- and vision-based automatic grasping and flexible placement in teleoperation

The teleoperation system has attracted a lot of attention because of its advantages in dangerous or unknown environments. It is very difficult to develop an operating system that can complete complex tasks in a completely autonomous. This paper proposes a robot arm control strategy based on gestures and visual perception. The strategy combines the advantages of humans and robots to obtain a convenient and flexible interaction model. The hand’s data were obtained by Leap-Motion. Then a neural network algorithm was used to classify the nine gestures, which were used for robots control through a finite state machine. The control mode switched between indicative control and mapping control. The robot acquired an autonomous grasp ability by incorporating YOLO 6D, depth data and a probabilistic roadmap planner algorithm. The robot completed most of the trajectory independently, while a few flexible trajectories required users to do mapping actions. This interactive mode reduces the burden of the users to a certain extent that makes up for the shortcomings of traditional teleoperation.

Human–Robot Collaborative Assembly Based on Eye-Hand and a Finite State Machine in a Virtual Environment

With the development of the global economy, the demand for manufacturing is increasing. Accordingly, human–robot collaborative assembly has become a research hotspot. This paper aims to solve the efficiency problems inherent in traditional human-machine collaboration. Based on eye–hand and finite state machines, a collaborative assembly method is proposed. The method determines the human’s intention by collecting posture and eye data, which can control a robot to grasp an object, move it, and perform co-assembly. The robot’s automatic path planning is based on a probabilistic roadmap planner. Virtual reality tests show that the proposed method is more efficient than traditional methods.

Surface-driven Next-Best-View planning for exploration of large-scale 3D environments

In this paper, we propose a novel cluster-based informative path planning algorithm to simultaneously explore and inspect a large-scale unknown environment with an Unmanned Aerial Vehicle (UAV). Most of the existing methods address the surface inspection problem as a volume exploration problem, and consider that the surface has been scanned when the corresponding volume has been covered. Unfortunately, this approach may lead to inaccurate 3D models of the environment, and the UAV may not achieve global coverage. To overcome these critical limitations, we introduce a 3D reconstruction method based on TSDF (Truncated Signed Distance Function) mapping, which leverages the surfaces present in the environment to generate an informative exploration path for the UAV. A Probabilistic Roadmap planner, used to solve a TSP (Travelling Salesman Problem) over clusters of viewpoint configurations, ensures that the resulting 3D model is accurate and complete. Two challenging structures (a power plant and the Statue of Liberty) have been chosen to conduct realistic numerical experiments with a quadrotor UAV. Our results provide evidence that the proposed method is effective and robust.

Probabilistic Roadmaps with Higher Expressive Power

Sampling-based motion planning had an enormous impact on robot motion planning because of its efficiency and scalability. Many sampling-based motion planners construct a probabilistic roadmap (PRM) that captures the connectivity of the robot's free configuration space. A valid node of a PRM contains a collision-free robot configuration (also known as a sample) and a valid edge of a PRM connects two valid nodes with a collision-free path. Nodes connected by an edge are usually also required to satisfy additional requirements based on the distance between them. PRM planners use PRMs. Increasing the expressive power will allow PRMs to be used for a wider set of motion planning problems. In this paper we report on increasing the expressive power of PRMs by including the following five features in PRMs-nodes with multiple samples that need not be organized as a graph, temporal intervals of validity of nodes and edges, nodes with samples of multiple robots, special edges for the state transitions performed by humans sharing a workspace with robots, and conditional validity of samples and edges. We report on motion planning problems solvable using these new features.

How to construct small probabilistic roadmaps with a good coverage?

We investigate how we can construct small probabilistic roadmaps in a reasonable time while still keeping a good coverage and connectivity. We propose a new neighborhood-based method that can reduce the size of the roadmaps by filtering out unnecessary nodes. We then experimentally test it against a basic probabilistic roadmap planner and a visibility-based planner. We use both a uniform sampling and a bridge test sampling in our tests. The results show that the neighborhood-based method can reduce the number of nodes considerably. The neighborhood-based method is simple to implement, it works well with a uniform sampling, and it does not need any additional parameters when compared with the basic planner.

Speeding up probabilistic roadmap planners with locality-sensitive hashing

SUMMARYA crucial part of probabilistic roadmap planners is the nearest neighbor search, which is typically done by exact methods. Unfortunately, searching the neighbors can become a major bottleneck for the performance. This can occur when the roadmap size grows especially in high-dimensional spaces. In this paper, we investigate how well the approximate nearest neighbor searching works with probabilistic roadmap planners. We propose a method that is based on the locality-sensitive hashing and show that it can speed up the construction of the roadmap considerably without reducing the quality of the produced roadmap.

Biologically Inspired Node Generation Algorithm for Path Planning of Hyper-redundant Manipulators Using Probabilistic Roadmap

This article describes a biologically inspired node generator for the path planning of serially connected hyper-redundant manipulators using probabilistic roadmap planners. The generator searches the configuration space surrounding existing nodes in the roadmap and uses a combination of random and deterministic search methods that emulate the behaviour of octopus limbs. The strategy consists of randomly mutating the states of the links near the end-effector, and mutating the states of the links near the base of the robot toward the states of the goal configuration. When combined with the small tree probabilistic roadmap planner, the method was successfully used to solve the narrow passage motion planning problem of a 17 degree-of-freedom manipulator.

Analysis of Obstacle based Probabilistic RoadMap Method using Geometric Probability

Sampling based planners have been successful in robot motion planning, with many degrees of freedom, but still remain ineffective in the presence of narrow passages within the configuration space. There exist several heuristics, which generate samples in the critical regions and improve the efficiency of probabilistic roadmap planners. In this paper, we present an evaluation of success probability of one such heuristic method, called obstacle based probabilistic roadmap planners or OBPRM, using geometric probability theory. The result indicates that the probability of success of generating free sample points around the surface of the n dimensional configuration space obstacle is directly proportional to the surface area of the obstacles.

Probabilistic Multi Robot Path Planning in Dynamic Environments: A Comparison between A* and DFS

paper, a probabilistic roadmap planner algorithm with the multi robot path planning problem have been proposed by using the A* search algorithm in a dynamic environment. The whole process consists of two phases. In the first phase: Preprocessing phase, the work space is converted into the configuration space, constructing a probabilistic roadmap graph in the free space, and finding the optimal path for each robot using a global planner that avoids the collision with the static obstacles. The second phase: Moving phase, moves each robot in a prioritized manner from its starting point to its ending point through a near optimal path with avoiding collision with the moving obstacles and the other robots. A comparison has been done with the depth first algorithm to see the difference. The simulation results shows that choosing A* search algorithm affect positively the speed of the two phases together in comparison to the depth first search algorithm.

Using probabilistic roadmaps in changing environments

ABSTRACTIn this paper, we examine how a path planning problem can be solved in changing environments using probabilistic roadmap planners. A probabilistic roadmap is built in static environment where all obstacles are known in advance, but we show that a roadmap can be built in such a way that it works well even when new obstacles are added to the workspace. However, our experiments show that the roadmap graph must be built carefully. We compare three different methods that are used to decide which edges are added to the roadmap graph to connect the nodes. One of these is a distance‐based method, which we present in this paper. In the tests, we built a roadmap by using only the static obstacles. Then, we added additional obstacles to the environment and tested how well the roadmap still worked. The tests showed that our distance‐based method worked quickly and that it produced roadmaps, which could be used to find a path amid additional obstacles with a high success rate.Copyright © 2013 John Wiley & Sons, Ltd.

A configuration deactivation algorithm for boosting probabilistic roadmap planning of robots

We present a method to improve the execution time used to build the roadmap in probabilistic roadmap planners. Our method intelligently deactivates some of the configurations during the learning phase and allows the planner to concentrate on those configurations that are most likely going to be useful when building the roadmap. The method can be used with many of the existing sampling algorithms. We ran tests with four simulated robot problems typical in robotics literature. The sampling methods applied were purely random, using Halton numbers, Gaussian distribution, and bridge test technique. In our tests, the deactivation method clearly improved the execution times. Compared with pure random selections, the deactivation method also significantly decreased the size of the roadmap, which is a useful property to simplify roadmap planning tasks.

Autonomous motion planning of a hand-arm robotic system based on captured human-like hand postures

The paper deals with the problem of motion planning of anthropomorphic mechanical hands avoiding collisions and trying to mimic real human hand postures. The approach uses the concept of motion directions to reduce the dimension of the search space in order to obtain results with a compromise between motion optimality and planning complexity (time). Basically, the work includes the following phases: capturing the human hand workspace using a sensorized glove and mapping it to the mechanical hand workspace, reducing the space dimension by looking for the most relevant principal motion directions, and planning the hand movements using a probabilistic roadmap planner. The approach has been implemented for a four finger anthropomorphic mechanical hand (17 joints with 13 independent degrees of freedom) assembled on an industrial robot (6 independent degrees of freedom), and experimental examples are included to illustrate its validity.

Guiding the Generation of Manipulation Plans by Qualitative Spatial Reasoning

Manipulation planning is a complex task for robots with a manipulator arm that need to grasp objects in the environment, specifically under narrow spatial conditions restricting the workspace of the robot. A popular approach for generating motion plans is probabilistic roadmap planning. However, the sampling strategy of such planners is usually unguided, and hence may lead to motion plans that seem counterintuitive for a human observer. In this article we present an approach that generates heuristics for the probabilistic sampling strategy from spatial plans that abstract from concrete metric data. These spatial plans describe a free trajectory in the workspace of the robot on a purely qualitative level, i.e., by employing spatial relations from formalisms considered in the domain of Qualitative Spatial and Temporal Reasoning. We discuss how such formalisms and constraint-based reasoning methods can be applied to approximate geometrically feasible motions. The paper is completed by an evaluation of a hybrid planning system in different spatial settings showing that run-times are notably improved when an abstract plan is considered as a guidance heuristic.

A Connectivity-Based Method for Enhancing Sampling in Probabilistic Roadmap Planners

The motion planning is a difficult problem but nevertheless, a crucial part of robotics. The probabilistic roadmap planners have shown to be an efficient way to solve these planning problems. In this paper, we present a new algorithm that is based on the principles of the probabilistic roadmap planners. Our algorithm enhances the sampling by intelligently detecting which areas of the configuration space are easy and which parts are not. The algorithm then biases the sampling only to the difficult areas that may contain narrow passages. Our algorithm works by dividing the configuration space into regions at the beginning and then sampling configurations inside each region. Based on the connectivity of the roadmap inside each region, our algorithm aims to detect whether the region is easy or difficult. We tested our algorithm with three different simulated environments and compared it with two other planners. Our experiments showed that with our method it is possible to achieve significantly better results than with other tested planners. Our algorithm was also able to reduce the size of roadmaps.

Multi-modal Motion Planning in Non-expansive Spaces

Motion planning problems encountered in manipulation and legged locomotion have a distinctive multi-modal structure, where the space of feasible configurations consists of intersecting submanifolds, often of different dimensionalities. Such a feasible space does not possess expansiveness, a property that characterizes whether planning queries can be solved efficiently with traditional probabilistic roadmap (PRM) planners. In this paper we present a new PRM-based multi-modal planning algorithm for problems where the number of intersecting manifolds is finite. We also analyze the completeness properties of this algorithm. More specifically, we show that the algorithm converges quickly when each submanifold is individually expansive and establish a bound on the expected running time in that case. We also present an incremental variant of the algorithm that has the same convergence properties, but works better for problems with a large number of submanifolds by considering subsets of submanifolds likely to contain a solution path. These algorithms are demonstrated in geometric examples and in a legged locomotion planner.

Path Deformation Roadmaps: Compact Graphs with Useful Cycles for Motion Planning

In this paper we describe a new approach to sampling-based motion planning with Probabilistic Roadmap Planner (PRM) methods. Our aim is to compute good quality roadmaps which encode the multiple connectedness of the configuration space inside small but yet representative graphs which capture the different varieties of free paths well. The proposed Path Deformation Roadmaps (PDRs) rely on a notion of path deformability indicating whether or not a given path can be continuously deformed into another existing path. By considering a simpler form of deformation than that allowed between homotopic paths, we propose a method that extends the Visibility-PRM technique to construct compact roadmaps which encode richer and more suitable information than representative paths of the homotopy classes. PDRs contain additional useful cycles between paths in the same homotopy class that can be hardly deformed into each other. Experimental results show that the technique enables small roadmaps to reliably capture the multiple connectedness of complex spaces in various problems involving free-flying and articulated robots in both two- and three-dimensional environments.

Reachability-based analysis for Probabilistic Roadmap planners

In the last fifteen years, sampling-based planners like the Probabilistic Roadmap Method ( prm) have proved to be successful in solving complex motion planning problems. While theoretically, the complexity of the motion planning problem is exponential in the number of degrees of freedom, sampling-based planners can successfully handle this curse of dimensionality in practice. We give a reachability-based analysis for these planners which leads to a better understanding of the success of the approach. This analysis compares the techniques based on coverage and connectivity of the free configuration space. The experiments show, contrary to general belief, that the main challenge is not getting the free space covered but getting the nodes connected, especially when the problems get more complicated, e.g. when a narrow passage is present. By using this knowledge, we can tackle the narrow passage problem by incorporating a refined neighbor selection strategy, a hybrid sampling strategy, and a more powerful local planner, leading to a considerable speed-up.

On the Probabilistic Foundations of Probabilistic Roadmap Planning

Why is probabilistic roadmap (PRM) planning probabilistic? How does the probability measure used for sampling a robot’s configuration space affect the performance of a PRM planner? These questions have received little attention to date. This paper tries to fill this gap and identify promising directions to improve future planners. It introduces the probabilistic foundations of PRM planning and examines previous work in this context. It shows that the success of PRM planning depends mainly and critically on favorable “visibility” properties of a robot’s configuration space. A promising direction for speeding up PRM planners is to infer partial knowledge of such properties from both workspace geometry and information gathered during roadmap construction, and to use this knowledge to adapt the probability measure for sampling. This paper also shows that the choice of the sampling source—pseudo-random or deterministic—has small impact on a PRM planner’s performance, compared with that of the sampling measure. These conclusions are supported by both theoretical and empirical results.

On boundaries of highly visible spaces and applications

The purpose of this paper is to investigate the properties of a certain class of highly visible spaces. For a given geometric space C containing obstacles specified by disjoint subsets of C , the free space F is defined to be the portion of C not occupied by these obstacles. The space is said to be highly visible if at each point in F a viewer can see at least an ε fraction of the entire F . This assumption has been used for robotic motion planning in the analysis of random sampling of points in the robot's configuration space, as well as the upper bound of the minimum number of guards needed for art gallery problems. However, there is no prior result on the implication of this assumption to the geometry of the space under study. For the two-dimensional case, with the additional assumptions that C is bounded within a rectangle of constant aspect ratio and that the volume ratio between F and C is a constant, we use the proof technique of “charging” each obstacle boundary segment by a certain portion of C to show that the total length of all obstacle boundaries in C is O ( n μ ( F ) / ε ) , if C contains polygonal obstacles with a total of n boundary edges; or O ( n μ ( F ) / ε ) , if C contains n convex obstacles that are piecewise smooth. In both cases, μ ( F ) is the volume of F . For the polygonal case, this bound is tight as we can construct a space whose boundary size is Θ ( n μ ( F ) / ε ) . These results can be partially extended to three dimensions. We show that these results can be applied to the analysis of certain probabilistic roadmap planners, as well as a variant of the art gallery problem. We also propose a number of conjectures on the properties of these highly visible spaces.