Randomized Kinodynamic Planning

By Steven M. LaValle, James J. Kuffner Jr.. 1999

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

Citations in the corpus

Learning Trajectory Preferences for Manipulators via Iterative Improvement (2013, methodology): “[4], we sample trajectories using rapidly-exploring random tree (RRT) [20].”
Deep Reinforcement Learning for Autonomous Driving: A Survey (2020, background): “Rapidly-exploring random trees (RRT) [12] are non-holonomic algorithms that explore the conﬁguration space by random sampling and obstacle free path generation.”
A Survey of Autonomous Driving: Common Practices and Emerging Technologies (2019, methodology): “RRT is faster than PRM and both are probabilistically complete [253], which means a path that satisﬁes the given conditions will be guaranteed to be found with enough runtime.”
A Survey of Motion Planning and Control Techniques for Self-Driving Urban Vehicles (2016, background): “As shown in Algorithm 4, the RRT* at every iteration considers a set of vertices that lie in the neighborhood of newly added vertex xnew and a) connects xnew to the vertex in the neighborhood that minimizes the cost of path from xinit to xnew and b) rewires any vertex in the neighborhood to xnew if ”
Optimization-Based Collision Avoidance (2017, methodology): “In this article, we do not review, or compare, optimization-based collision avoidance methods with alternative approaches, such as those based on dynamic programming [17], reachability analysis [18]–[20], graph search methods, such as A and Hybrid A [21]–[23], (random) sampling, such as rapidly expl”
Inevitable collision states. A step towards safer robots? (2003, background): “Except for a brief mention of it in [9], this concept does not seem to have been considered before by the Robotics community.”
Anytime Motion Planning using the RRT* (2011, methodology): “Sampling-based approaches, including algorithms such as the Probabilistic RoadMap (PRM) [6] and the RRT [7], form a relatively recent line of research in this direction.”
RRT-connect: An efficient approach to single-query path planning (2000, methodology): “Adapting this planner to problems that involve differential constraints would most likely give significant performance improvement over the planner in [19].”
Rapidly-exploring random trees : a new tool for path planning (1998, background): “For a kinodynamic planning problem, X = T (C), which is the tangent bundle of the con guration space [7] (a state encodes both con guration and velocity).”
Belief space planning assuming maximum likelihood observations (2010, background): “A number of planning methods that are applied to underactuated systems are relevant to the belief space planning problem: rapidly expanding random trees (RRTs) [11], LQR-trees [12], and nonlinear optimization methods [13].”
Manipulation planning on constraint manifolds (2009, background): “This is a common assumption when planning trajectories in high dimensional spaces but RRTs have been applied to kinodynamic (position-velocity) spaces as well[16].”
Safe motion planning in dynamic environments (2005, unknown): “The exploration method used is the well known Rapidly-Exploring Random Tree method (RRT) [24].”
Motion planning for robotic manipulation of deformable linear objects (2006, result): “Our approach is similar to those proposed in [6] and [9] to plan trajectories under kinodynamic constraints.”
Sampling-Based Robot Motion Planning: A Review (2014, background): “LaValle and Kuffner [60] proposed modification of the termination condition in a way such that the SBP keeps running to iteratively converge the path cost.”
The Open Motion Planning Library (2012, methodology): “, RRT [15]), two separate implementations are provided for that algorithm, one for each type of computed motion.”
Sampling-based algorithms for optimal motion planning (2011, methodology): “In the context of sampling-based motion planning algorithms, the importance of computing optimal solutions has been pointed out in early seminal papers (LaValle and Kuffner 2001).”