RRT*-SMART: A Rapid Convergence Implementation of RRT*

Nasir, Jauwairia; Islam, Fahad; Malik, Usman; Ayaz, Yasar; Hasan, Osman; Khan, Mushtaq; Muhammad, Mannan Saeed

doi:10.5772/56718

Cited by 185 publications

(95 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Such memory efficient versions of RRT* are useful in robots and embedded systems with limited memory [33]. Nasir et al [35] presented an offline variant of RRT* called RRT*-Smart to address the issue of slow convergence. RRT*-Smart introduced two major features called intelligent sampling and path optimization.…”

Section: A Single Directional Holonomic Rrt* Approachesmentioning

confidence: 99%

“…Initial path finding procedure in RRT*-Smart is similar to RRT*. However, once a path is found, it is optimized based on triangular inequality principle to remove redundant nodes [35]. Optimization task generates beacon nodes to further improve path cost.…”

Section: A Single Directional Holonomic Rrt* Approachesmentioning

confidence: 99%

“…Nasir et al [35], 2013 RRT*-Smart  Two new features intelligent sampling and path optimization were introduced.  It accelerated the convergence rate with improved efficiency with respect to both time and cost  It is dependent upon a heuristic called Biasing Ratio which has a trade-off between convergence rate and exploration of space.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Optimal Path Planning using RRT* based Approaches: A Survey and Future Directions

Noreen¹,

Khan²,

Habib³

2016

ijacsa

201

View full text Add to dashboard Cite

Abstract-Optimal path planning refers to find the collision free, shortest, and smooth route between start and goal positions. This task is essential in many robotic applications such as autonomous car, surveillance operations, agricultural robots, planetary and space exploration missions. Rapidly-exploring Random Tree Star (RRT*) is a renowned sampling based planning approach. It has gained immense popularity due to its support for high dimensional complex problems. A significant body of research has addressed the problem of optimal path planning for mobile robots using RRT* based approaches. However, no updated survey on RRT* based approaches is available. Considering the rapid pace of development in this field, this paper presents a comprehensive review of RRT* based path planning approaches. Current issues relevant to noticeable advancements in the field are investigated and whole discussion is concluded with challenges and future research directions.

show abstract

Section: A Single Directional Holonomic Rrt* Approachesmentioning

confidence: 99%

Section: A Single Directional Holonomic Rrt* Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Optimal Path Planning using RRT* based Approaches: A Survey and Future Directions

Noreen¹,

Khan²,

Habib³

2016

ijacsa

201

View full text Add to dashboard Cite

show abstract

“…A lazy strategy is also adopted in lazy PRM* [10] and lazy RRG [11], where the core idea is to delay the collision check until it absolutely necessary. Additionally, many different heuristics for speeding up convergence are presented in [12][13][14][15][16][17].…”

Section: Introductionmentioning

confidence: 99%

A Region-Specific Hybrid Sampling Method for Optimal Path Planning

Zhong

Liu

2016

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Finding high quality paths within a limited time in configuration space is a challenging issue for path planning. Recently, an asymptotically optimal method called fast marching tree (FMT*) has been proposed. This method converges significantly faster than its state-of-the-art counterparts when addressing a wide range of problems. However, FMT* appears unable to solve the narrow passage problem in optimal path planning, since it is based on uniform sampling. Aiming at solving this problem, a novel region-based sampling method integrating global scenario information and local region information is proposed in this paper. First, global information related to configuration space is extracted from an initial sample set obtained via hybrid sampling. Then, local regions are constructed and local region information is captured to make intelligent decisions regarding regions that are difficult and need to be boosted. Finally, the initial sample set is sent to FMT* using a modified locally optimal onestep connection strategy in order to find an initial and feasible solution. If no solution is found and time permits, the guided hybrid sampling will be adopted in order to add more useful samples to the sample set until a solution is found or the time for doing so runs out. Simulation results for six benchmark scenarios validate that our method can achieve significantly better results than other state-of-theart methods when applied in challenging scenarios with narrow passages.

show abstract

“…However, as the number of samples increase, the RRT solution hardly changes while the RRT * algorithm constantly improves the result and with 15000 samples, a good approximation of the two straight line segments constituting the optimal solution can be seen. Many modifications to the original formulations can be found in the literature and pruning techniques and different heuristic functions that biases the sampling to interesting regions have been used to speed up the search but they are outside the scope of this thesis (Urmson and Simmons, 2003;Nasir et al, 2013;Kalisiak and van de Panne, 2006;Gammell et al). Karaman and Frazzoli (2011) and is used with courtesy of the authors.…”

Section: Rrt*mentioning

confidence: 99%

Sampling Based Motion Planning for Heavy Duty Autonomous Vehicles

Evestedt¹

View full text Add to dashboard Cite

The automotive industry is undergoing a revolution where the more traditional mechanical values are replaced by an ever increasing number of Advanced Driver Assistance Systems (ADAS) where advanced algorithms and software development are taking a bigger role. Increased safety, reduced emissions and the possibility of completely new business models are driving the development and most automotive companies have started projects that aim towards fully autonomous vehicles. For industrial applications that provide a closed environment, such as mining facilities, harbors, agriculture and airports, full implementation of the technology is already available with increased productivity, reliability and reduced wear on equipment as a result. However, it also gives the opportunity to create a safer working environment when human drivers can be removed from dangerous working conditions. Regardless of the application an important part of any mobile autonomous system is the motion planning layer. In this thesis sampling-based motion planning algorithms are used to solve several non-holonomic and kinodynamic planning problems for car-like robotic vehicles in different application areas that all present different challenges.First we present an extension to the probabilistic sampling-based Closed-Loop Rapidly exploring Random Tree (CL-RRT) framework that significantly increases the probability of drawing a valid sample for platforms with second order differential constraints. When a tree extension is found infeasible a new acceleration profile that tries to brings the vehicle to a full stop before the collision occurs is calculated. A resimulation of the tree extension with the new acceleration profile is then performed. The framework is tested on a heavy-duty Scania G480 mining truck in a simple constructed scenario.Furthermore, we present two different driver assistance systems for the complicated task of reversing with a truck with a dolly-steered trailer. The first is a manual system where the user can easily construct a kinematically feasible path through a graphical user interface. The second is a fully automatic planner, based on the CL-RRT algorithm where only a start and goal position need to be provided. For both approaches, the internal angles of the trailer configuration are stabilized using a Linear Quadratic (LQ) controller and path following is achieved through a pure-pursuit control law. The systems are demonstrated on a small-scale test vehicle with good results.Finally, we look at the planning problem for an autonomous vehicle in an urban setting with dense traffic for two different time-critical maneuvers, namely, intersection merging and highway merging. In these situations, a social interplay between drivers is often necessary in order to perform a safe merge. To model this interaction a prediction engine is developed and used to predict the future evolution of the complete traffic scene given our own intended trajectory. Real-time capabilities are demonstrated through a series of simulations with va...

show abstract

RRT-SMART: A Rapid Convergence Implementation of RRT

Cited by 185 publications

References 18 publications

Optimal Path Planning using RRT* based Approaches: A Survey and Future Directions

Optimal Path Planning using RRT* based Approaches: A Survey and Future Directions

A Region-Specific Hybrid Sampling Method for Optimal Path Planning

Sampling Based Motion Planning for Heavy Duty Autonomous Vehicles

Contact Info

Product

Resources

About