A Fast and Efficient Approach to Path Planning for Unmanned Vehicles

Amin, Jayesh; Bo, Jovan D.; Mehra, Raman K.

doi:10.2514/6.2006-6103

Cited by 53 publications

(39 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The square root operation is a time-intensive step. Amin et al [17] avoid this by implementing a faster octagonal approximation of the Euclidean distance, which is shown to be a good approximation [20]. However, instead of using such an approximation, it may be worthwhile to eliminate the use of the square root function by simply comparing the squares of the distances from each of the nodes.…”

Section: B Rapidly Exploring Random Treementioning

confidence: 95%

“…An optimal global path is first calculated offline, and then when the sensor detects obstacles the path is modified. Simulation experiments conducted by Amin et al [17] demonstrate that this scheme offers a good global planner as well as a reactive algorithm for online collision avoidance. An important disadvantage of RRT is that it is an open loop method, and thus is sensitive to noise.…”

Section: B Rapidly Exploring Random Treementioning

confidence: 95%

“…With appropriate modifications [17], the RRT can be used to plan a global, dynamically feasible and optimal path to the goal, as well as perform replanning when obstacles are detected by the sensor onboard. Sampling-based planners like RRT rely on the availability of a fast collision checker.…”

Section: B Rapidly Exploring Random Treementioning

confidence: 99%

See 2 more Smart Citations

Evolving Philosophies on Autonomous Obstacle/Collision Avoidance of Unmanned Aerial Vehicles

Mujumdar

Padhi

2011

Journal of Aerospace Computing, Information, and Communication

View full text Add to dashboard Cite

Much of the benefits of deploying unmanned aerial vehicles can be derived from autonomous missions. For such missions, however, sense-and-avoid capability (i.e., the ability to detect potential collisions and avoid them) is a critical requirement. Collision avoidance can be broadly classified into global and local path-planning algorithms, both of which need to be addressed in a successful mission. Whereas global path planning (which is mainly done offline) broadly lays out a path that reaches the goal point, local collision-avoidance algorithms, which are usually fast, reactive, and carried out online, ensure safety of the vehicle from unexpected and unforeseen obstacles/collisions. Even though many techniques for both global and local collision avoidance have been proposed in the recent literature, there is a great interest around the globe to solve this important problem comprehensively and efficiently and such techniques are still evolving. This paper presents a brief overview of a few promising and evolving ideas on collision avoidance for unmanned aerial vehicles, with a preferential bias toward local collision avoidance.

show abstract

Section: B Rapidly Exploring Random Treementioning

confidence: 95%

Section: B Rapidly Exploring Random Treementioning

confidence: 95%

See 1 more Smart Citation

Evolving Philosophies on Autonomous Obstacle/Collision Avoidance of Unmanned Aerial Vehicles

Mujumdar

Padhi

2011

Journal of Aerospace Computing, Information, and Communication

View full text Add to dashboard Cite

show abstract

“…These include a Hybrid A* algorithm [9], [10], Voroni polygons [11], [12], probabilistic maps and other graphical methods [13], [14]. Some researchers are experimenting with various analytical techniques to solve these path-planning problems, including singular perturbation [15], genetic algorithms [16], [17] and neighboring optimal control [18] as well as other analytical techniques.…”

Section: Introductionmentioning

confidence: 99%

A Pittsburgh Multi-Objective Classifier for user preferred trajectories and flight navigation

Pham

Bui

Alam

et al. 2010

IEEE Congress on Evolutionary Computation

View full text Add to dashboard Cite

An efficient design of a Multi-Objective LearningClassifier System for multi-flight navigation is presented. A classifier is represented by a set of rules, which are used to simultaneously navigate all the flights in the airspace. Navigation of a flight is based on the relation of the flight with factors of the air traffic environment such as wind, storm as well as other flights. This system continually learns and refines the rules of classifiers by a multi-objective optimization algorithm -NSGAII -to discover the trade-off set of classifiers which navigate flights without any conflict, minimal distance of flying, minimal discomfort defined by storm level and the time duration of flights passing through storm areas, and minimizing total delay time of flights.We propose to detect conflicts between flights by grouping trajectory segments in 3-D (abscissa-x, ordinate-y, and timet) boxes. The conflict detection is only implemented in a box, thus the number of conflict detection times approximates to the number of conflicts. Further, conflicts between flights are resolved using a hill climber by propagating delays in the takeoff time of conflicting flights. The advantage of the proposed system is that the classifier outputs its rules in a symbolic representation, making the overall process transparent to the user and reusable. Moreover, the system successfully discovered rules in all runs to optimize its performance.

show abstract

“…Therefore, the nearest neighbor node selection makes vertices with large Voronoi regions be selected for expansion [5]. The RRT has been demonstrated successfully in real-time applications [6][7][8][9].…”

Section: Introductionmentioning

confidence: 99%

Anytime synchronized-biased-greedy rapidly-exploring random tree path planning in two dimensional complex environments

Yang

2011

Int. J. Control Autom. Syst.

View full text Add to dashboard Cite

A new synchronized biased-greedy RRT is proposed which leverages the strengths of the biased and greedy RRTs. It combines the advantage of the biased RRT that grows trees towards the goal location, with the ability of the greedy RRT that makes trees traverse the environment in a single iteration. The proposed method achieves performance improvements compared to other RRT variants, not only in computational time but also in the quality of the path. Two enhancements are made to the initial path to relax the sub-optimality of the RRT path; first a path pruning algorithm is executed to eliminate redundant nodes and an anytime strategy is adapted to continuously enhance the quality of the path within the deliberation time.

show abstract

A Fast and Efficient Approach to Path Planning for Unmanned Vehicles

Cited by 53 publications

References 6 publications

Evolving Philosophies on Autonomous Obstacle/Collision Avoidance of Unmanned Aerial Vehicles

Evolving Philosophies on Autonomous Obstacle/Collision Avoidance of Unmanned Aerial Vehicles

A Pittsburgh Multi-Objective Classifier for user preferred trajectories and flight navigation

Anytime synchronized-biased-greedy rapidly-exploring random tree path planning in two dimensional complex environments

Contact Info

Product

Resources

About