Rapidly-exploring random trees : a new tool for path planning

By Steven M. LaValle. 1998

How researchers see this paper

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

Citations in the corpus

MOReL : Model-Based Offline Reinforcement Learning (2020, methodology): “A number of algorithms based on MPC [23, 64], search-based planning [65, 25], dynamic programming [49, 26], or policy optimization [27, 51, 66, 67] can be used to approximately realize this.”
Go-Explore: a New Approach for Hard-Exploration Problems (2019, methodology): “Graph-search algorithms as a means of exploration in planning have been investigated in algorithms such as Rapidly-exploring Random Trees (RRTs) [99], which were recently used to explore Atari games by Zhan et al.”
Optimal trajectory generation for dynamic street scenarios in a Frenét Frame (2010, methodology): “In [9], a tree of trajectories is sampled by simulating the closed loop system using the rapidly exploring random tree algorithm [10].”
Dynamic-Domain RRTs: Efficient Exploration by Controlling the Sampling Domain (2005, methodology): “Rapidly-exploring Random Trees (RRTs) were primarily designed for targeting single-query holonomic problems and problems with differential constraints [21], [23], [25].”
iGibson, a Simulation Environment for Interactive Tasks in Large Realistic Scenes (2020, background): “sampling-based motion planners: rapidly growing random trees (RRT [58]) and its bidirectional variant (BiRRT [59]), and lazy probabilistic road-maps (lazyPRM [60]), adapted from [61].”
Curiosity driven reinforcement learning for motion planning on humanoids (2014, methodology): “Single query algorithms, such as Rapidly Exploring Random Trees (RRT) (LaValle, 1998; Perez et al., 2011), interpolate two points in conﬁguration space, without reusing knowledge from one query to the next.”
Combining Optimal Control and Learning for Visual Navigation in Novel Environments (2019, methodology): “ate trajectories [24, 30, 44]. Classical Robot Navigation. Classical robotics factorizes the problem of robot navigation [12, 41] into sub-problems of mapping and localization [17, 41], path planning [8, 22, 25] and trajectory tracking via optimal control as described above. Mapping refers to estima”
Path Planning for Autonomous Vehicles in Unknown Semi-structured Environments (2010, methodology): “This work was motivated by and experimentally validated in the”
RRT-connect: An efficient approach to single-query path planning (2000, methodology): “We present a simple path planning method called RRT-Connect that combines Rapidly-exploring Random Trees (RRTs) [18] with a simple greedy heuristic that aggressively tries to connect two trees, one from the initial configuration and the other from the goal.”
Perception, Planning, Control, and Coordination for Autonomous Vehicles (2017, background): “Paths can be generated from directly sampling admissible controls [240], however these methods do not optimize paths through tree rewiring, and popular asymptotically optimal planners, such as RRT* [207] require sampling from the configuration space.”
Alternative Paths Planner (APP) for Provably Fixed-time Manipulation Planning in Semi-structured Environments (2020, methodology): “Commonly used algorithms such as RRTs [1], [2] neither exploit the distinction between static and movable obstacles nor take advantage of the repetitive nature of planning problems to speedup planning.”
Reset-free Trial-and-Error Learning for Robot Damage Recovery (2016, background): “ning Sample-based planning is one of the main philosophies that addresses the motion planning problem [41]. The traditional algorithms in this category are \Rapidly Exploring Random Trees" (RRT) [42] and \Probabilistic Roadmaps for path planning in high-dimensional conguration spaces" (PRM”
A Survey of Monte Carlo Tree Search Methods (2012, background): “dense trees (RTDs), were first introduced by LaValle [126].”
Autonomous Vehicle Technologies for Small Fixed-Wing UAVs (2003, unknown): “u̇ = −g sin θ +Ax + vr − wq (4) v̇ = g sinφ cos θ +Ay − wr + wp (5) ẇ = g cosφ cos θ +Az + uq − vp (6)”
Receding Horizon "Next-Best-View" Planner for 3D Exploration (2016, methodology): “Starting from the current conﬁguration of the vehicle ξ 0 , a geometric tree T is incrementally built in the conﬁguration space, within the scope of this work using the RRT algorithm [12].”
Sampling-Based Path Planning on Configuration-Space Costmaps (2010, methodology): “Similar to the Extend version of the basic RRT algorithm [20], a randomly sampled configuration qrand is used to determine both the nearest tree node qnear to be extended and the extension direction.”