Energy-efficient high-dimensional motion planning for humanoids using stochastic optimization

Sampling-based search algorithms such as Rapidly-Exploring Random Trees (RRT) have been utilized for mobile robot path planning and motion planning in high dimensional continuous spaces. This paper presents a path planning method for a planetary exploration rover in rough terrain. The proposed method exploits the framework of a sampling-based search, the optimal RRT (RRT*) algorithm. The terrain geometry used for planning is composed of point cloud data close to continuous space captured by a light detection and ranging (LIDAR) sensor. During the path planning phase, the proposed RRT*algorithm directly samples a point (node) from the LIDAR point cloud data. The path planner then considers the rough terrain traversability of the rover during the tree expansion process of RRT*. This process improves conventional RRT*in that the generated path is safe and feasible for the rover in rough terrain. In this paper, simulation study on the proposed path planning algorithm in various real terrain data confirms its usefulness.

As a sampling based path planning method, Rapidly-exploring Random Tree (RRT) is powerful for its high efficiency in finding feasible solutions. Optimal RRT (RRT*) improves RRT by asymptotically searching the optimal solution, however, at the cost of time consuming. This paper proposes an efficient optimal planning algorithm based on RRT* with adaptive restricted sampling space, which is inspired by the tropism of plants and named as tropistic RRT*. Tropistic RRT* improves the efficiency of the path planning by restricting the sampling space to approach the goal position just like the phototropism of plants. To validate our proposed algorithm, we carry out both path planning and motion planning experiments in 2D environments. In the path planning experiments, we compare the proposed algorithm with RRT* and Informed RRT* and experimental results show that our method outperforms the other two in the convergence rate, final solution cost and robustness. Furthermore, we also implement our algorithm in solving motion planning problem for a nonholonomic mobile robot and compare the time cost in the robot navigation process. Compared results exhibit that the time cost of our algorithm is much less than that of Real-Time RRT* in both static and dynamic environments.

Path planning plays a vital role in robot navigation and manipulation, and multiple types of algorithms have been introduced to address this problem. Rapidly-exploring Random Tree (RRT) based algorithms have many advantages over other path planning algorithms. For example, RRT is suitable to solve the path planning problem in high dimensional space and can easily handle robot differential constraints. Informed RRT* is a method that uses the prolate hyper-spheroid to speed up the optimization process, but its efficiency will decrease to the same level as RRT* when the hyper-spheroid covers most of the state space. To overcome this drawback, we further propose a Sliding-Window Informed RRT* (SWIRRT*), which combines the sliding-window thought into the Informed RRT*, taking the advantage of the initial path and make the path optimization much faster. Simulations in 2D space have been carried out to demonstrate that our proposed method can improve the RRT-like algorithm's convergence speed.

The online cooperative path planning problem is discussed for multi-quadrotor maneuvering in an unknown dynamic environment. Based on the related basic concepts, typical three-dimensional obstacle models, such as spherical and cubic, and their collision checking criteria are presented in this article. An improved rapidly exploring random tree (RRT) algorithm with goal bias and greed property is proposed based on the heuristic search strategy to overcome the shortcomings of the classical RRT algorithm. Not only are the kinematic constraints of the quadrotor established but the time and space coordination strategy matching with the improved RRT algorithm is also presented in this article. Furthermore, a novel online collision avoidance strategy according to the partial information of the surrounding environment is proposed. On the basis of the above work, a distributed online path planning strategy is proposed to obtain the feasible path for each quadrotor. Numerical simulation results show that the improved RRT algorithm has better search efficiency than the classical RRT algorithm. And the satisfactory path planning and path tracking results prove that the above model and related planning strategies are reasonable and effective.

In this paper, an improved APF-GFARRT* (artificial potential field-guided fuzzy adaptive rapidly exploring random trees) algorithm based on APF (artificial potential field) guided sampling and fuzzy adaptive expansion is proposed to solve the problems of weak orientation and low search success rate when randomly expanding nodes using the RRT (rapidly exploring random trees) algorithm for disinfecting robots in the dense environment of disinfection operation. Considering the inherent randomness of tree growth in the RRT* algorithm, a combination of APF with RRT* is introduced to enhance the purposefulness of the sampling process. In addition, in the context of RRT* facing dense and restricted environments such as narrow passages, adaptive step-size adjustment is implemented using fuzzy control. It accelerates the algorithm’s convergence and improves search efficiency in a specific area. The proposed algorithm is validated and analyzed in a specialized environment designed in MATLAB, and comparisons are made with existing path planning algorithms, including RRT, RRT*, and APF-RRT*. Experimental results show the excellent exploration speed of the improved algorithm, reducing the average initial path search time by about 46.52% compared to the other three algorithms. In addition, the improved algorithm exhibits faster convergence, significantly reducing the average iteration count and the average final path cost by about 10.01%. The algorithm’s enhanced adaptability in unique environments is particularly noteworthy, increasing the chances of successfully finding paths and generating more rational and smoother paths than other algorithms. Experimental results validate the proposed algorithm as a practical and feasible solution for similar problems.

In this paper a novel combination of data structures and algorithms is presented as a fast and efcient practical approach to path planning for unmanned vehicles. This approach utilizes an architecture that integrates effective obstacle representation using an efcient Quadtree data structure, with path planning based on a modied Rapidly-exploring Random Tree (RRT) algorithm, and a path pruning technique based on Dijkstra’s algorithm, resulting in rapid discovery of sub-optimal feasible paths. One of the computationally expensive steps of the RRT algorithm is checking RRT segments for collision with obstacles. To address this problem, an efcient obstacle representation using Quadtrees is implemented enabling fast segment checks. While the RRT approach is guaranteed to nd a feasible path through complex obstacle elds with the probability of discovery approaching one as the number of iterations increases, the resulting paths may be far from optimal as the only criterion embedded in the RRT search is feasibility. For this reason, the paths generated by the RRT algorithm are passed through Dijkstra algorithm that nds a shortest obstacle-free path among the points on the path. Dijkstra algorithm that re-samples the segments of the path and nds the shortest path among the new points is implemented resulting in paths that are very close to the optimal ones. To speed up the computation, the basic search algorithm is implemented as a dual RRT from the initial and nal points. To account for motion transients along the path, a suitable size corridor is introduced, assuring that the vehicle has enough room for maneuvering among the obstacles. This computationally efcient architecture lends itself to real-time implementation for both pre-planning with known obstacles as well as rapid reactive re-planning in the presence of new pop-up obstacles. The proposed technique is evaluated using several challenging path-planning examples characterized by a large number of non-convex constraints arising in cluttered obstacle elds with known and unknown obstacles. A modication that allows an easy way to introduce vehicle dynamics constraints or actuation failures is also implemented. Algorithms have been implemented for two as well as three dimensional path planning applications.

Many path planning algorithms have been introduced so far, but most are costly, in path cost and in processing time, in large-scale uncluttered 3D environments such as underground mining stopes explored by an unmanned aerial vehicle (UAV). Rapidly-exploring Random Tree (RRT) algorithms are popular because of their probabilistic completeness and rapidity in finding a feasible path in single-query problems. Many of the algorithms (e.g. Informed RRT*, RRT#) developed to improve RRT need considerable time to converge in large environments. Shortcutting an RRT is an old idea that has been proven to outperform RRT variants. This paper introduces a new method, RRT-Rope, that aims at finding a near-optimal solution in a drastically shorter amount of time. The proposed approach benefits from fast computation of a feasible path with an altered version of RRT-connect, and post-processes it quickly with a deterministic shortcutting technique, taking advantage of intermediate nodes added to each branch of the tree. This paper presents simulations and statistics carried out to show the efficiency of RRT-Rope, which gives better results in terms of path cost and computation time than other popular RRT variations and shortening techniques in all our simulation environments, and is up to 70% faster than the next best algorithm in a representative stope.

This research aims to create a simulator for solving the global path planning of mobile robots. Various sampling-based methods such as Rapidly-exploring Random Tree (RRT), RRT*, and Fast-RRT, along with other derivative algorithms, have been widely used to solve path-planning problems in mobile robots. The level of computational efficiency, path optimality, and the ability to adapt to variant environments are some of the issues that still arise, although these techniques have shown good results in many cases. Although the existing solutions are innovative, comparison between the existing methods is still difficult due to significant differences in convergence speed, implementation complexity, and quality of the resulting paths. This makes choosing the most suitable method for a particular application difficult. The simulator uses sampling-based path planning algorithms such as RRT*, Fast RRT*, RRT*-Smart, informed-RRT*, and Honey Bee Mating Optimization-based Fast-RRT*. With this simulator, users can easily compare the performance of each algorithm and see the characteristics and efficiency of each algorithm in various situations. By running all methods through this simulator, the user can easily compare the methods based on convergence speed and optimality. Therefore, it will effectively help users understand robot navigation, improve the quality of learning, and promote the development of path-planning technology for mobile robots.

Rapidly-Exploring Random Tree (RRT) has been widely used in robot navigation as a fast and efficient path planning method. Rapidly-Exploring Random Tree Star (RRT*) is one of the extensions of RRT, which outperforms the RRT algorithm because it can approximate the optimal path as the number of iterations increases. However, as the number of sampling points increases, the time to obtain the optimal path is too long, the algorithm converges significantly slower, and it is difficult to pass narrow obstacles in a short time. In this paper, we propose an improved RRT* algorithm, which first samples nodes in the dynamic target region to narrow the sampling range; expands tree nodes by target biasing strategy to reduce the randomness of tree growth; and generates more sampled nodes near the narrow obstacle nodes to make them have a higher probability of passing through the narrow channel. Simulation results show that our algorithm can find feasible paths quickly. Compared with the original RRT* algorithm, the algorithm performs better in terms of time and path cost.

Autonomous unmanned aerial vehicle (UAV) can be utilized to replace humans to do hard work or work in dangerous environment. Path planning is one of the crucial technologies for intelligent flight of UAV. The Rapidly-exploring Random Tree (RRT) has a wide range of applications in path planning with the advantage of the sampling-based path planning which avoids complex construction of the configuration space. However, these methods perform a uniform random sampling and thus do not lead to the most efficient solution. In this paper, in order to improve the efficiency of the traditional RRT, a heuristic strategy with goal-bias was exploited and incorporated in the traditional RRT. A simulation platform was built to assess the performance of the improved algorithm and analyze the influences of the parameters, and a flight test platform was established based on the DJI Matrice 100 to carry out the flight experiments of UAV path planning. The simulations proved that the heuristic RRT is much higher efficient than the standard version. The experiments validated the feasibility to apply the new RRT in the navigation for UAVs in reality.

The problem of three-dimensional path planning in obstacle-crowded environments is a challenge (an NP-hard problem), which becomes even more complex when considering environmental uncertainty and system control. Int this paper, we mainly focused on more challenging problem, that is, path planning in obstacle-crowded environments, and we try to find the relation between contact information and obstacle modeling. We proposed a newactive exploring sampling-based algorithm based on rapidly exploring random tree (RRT), namely, guiding attraction–based random tree (GART). GART introduces bidirectional potential field to redistribute each newly sampled state, such that the in-collision samples can be redistributed for extension. Furthermore, dynamic constraints are deployed to establish forward extending region by GART. Thus, GART can ensure kinodynamic reachability as well as smoothness. Theoretical analysis demonstrate that GART is probabilistic complete, and it obtains faster convergence rate because of its redistribution ability. In addition to theoretical analysis, this article provides comparative simulations as well as experiments under typical situations. Results demonstrate that GART has a much better time-efficiency performance than RRT*, retraction-based RRT, and other referred algorithms when applying redistribution and dynamic constraints on random exploration.

Random sampling based path planning algorithms have shown their high efficiency in robotics, navigation and related fields. The Rapidly-Exploring Random Trees (RRT) is the typical method and works well in a variety of applications. Due to the sub-optimal issue of original RRT, the recent algorithm, known as RRT*, significantly improves the optimality of solution by adding the “cost review” procedure. However, the original RRT experiences the bottle neck of complicated iterations and it becomes worse in RRT*. This paper presents the developed hardware architecture for RRT*, which fully exploits the parallel potential of algorithm. Unlike the sequential execution in software, the “exploration” and “review” are identified as independent processes and executed in parallel. For the complicated operation of inserting vertexes, one pipelined Kd-tree constructor is designed to fast rebuild the tree when new vertex generated. Furthermore, to speed up the near neighbors and nearest neighbor searching, the vertexes are stored in separate Kd-trees so that the search processes can be carried out concurrently in each data tree. This work explores the possible and power-efficient RRT* hardware architecture on FPGAs compared to PC implementation.

This paper introduces an efficient motion planning method for on-road driving of the autonomous vehicles, which is based on the rapidly exploring random tree (RRT) algorithm. RRT is an incremental sampling-based algorithm and is widely used to solve the planning problem of mobile robots. However, due to the meandering path, the inaccurate terminal state, and the slow exploration, it is often inefficient in many applications such as autonomous vehicles. To address these issues and considering the realistic context of on-road autonomous driving, we propose a fast RRT algorithm that introduces a rule-template set based on the traffic scenes and an aggressive extension strategy of search tree. Both improvements lead to a faster and more accurate RRT toward the goal state compared with the basic RRT algorithm. Meanwhile, a model-based prediction postprocess approach is adopted, by which the generated trajectory can be further smoothed and a feasible control sequence for the vehicle would be obtained. Furthermore, in the environments with dynamic obstacles, an integrated approach of the fast RRT algorithm and the configuration-time space can be used to improve the quality of the planned trajectory and the replanning. A large number of experimental results illustrate that our method is fast and efficient in solving planning queries of on-road autonomous driving and demonstrate its superior performances over previous approaches.

A two-stage ship path planning method is proposed, based on the Rapid-exploring Random Tree (RRT) algorithm, which is composed of global path planning and local path planning, addressing the important problem of finding an economical and safe path from start to destination for ships under dynamic environment, especially in waters with multiple obstacles and multiple target ships. The global path planning takes into consideration the ship draft and Under Keel Clearance to find navigable water using RRT, and reduces the path length and waypoints based on elliptic sampling and smoothing. In the local path planning, a dynamic collision risk detection model is constructed by introducing the Quaternion Ship Domain under a dynamic environment, and the restrictions of ship manoeuvrability and COLREGs are also involved. The simulation results show that the proposed model can find a satisfactory path within a few iterations, and keep clear of both static obstacles and dynamic ships. The research can be used to make and verify planned ship routes before sailing and to guide officers to make decisions regarding collision avoidance.

In today’s world, robots are becoming extremely useful in many facets of life. With the recent increase in applicable uses of robots, multi-robot path planning has emerged as a fundamental research area. Multi-robot path planning is the process of developing a coordinated plan which is utilized by multiple robots to efficiently work together to complete a common goal. Over the history of multi-robot path planning, many new path planning methodologies have been developed with the goal of outperforming the last, boasting better efficiency and optimality. In this thesis, an analysis of various multi-robot path planning methodologies is carried out with the goal of comparing and contrasting the advantages and limitations of each. This study puts sampling-based algorithms such as RRT (Rapidly-exploring Random Trees), RRT*, and M* to the test to determine which has the best performance in terms of time spent developing and executing the path plan, overall path plan route length, completion success rate, and scalability to more complex situations. A reinforcement learning approach is also applied, with the aim to increase the completion success rate and overall scalability while maintaining comparable time and route efficiency metrics. The simulation results show that the reinforcement learning approach produces much higher completion success rates, increased scalability, and comparable route efficiency metrics at the cost of much higher computation times as compared to the sampling-based algorithms.