Path planning using lazy PRM

By Robert Bohlin, Lydia E. Kavraki. Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065), 2000

1,016 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Software

View Paper: https://www.semanticscholar.org/paper/d814024a263675beb803557a2180a65a9b0b70dd

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Software

Citations in the corpus

Alternative Paths Planner (APP) for Provably Fixed-time Manipulation Planning in Semi-structured Environments (2020, background): “Improvements to PRM have minimized expensive collision checks [4], accounted for dynamic environments [5], [6], and captured repetitive motions [7], but their performance can still vary Fig.”
The Belief Roadmap: Efficient Planning in Belief Space by Factoring the Covariance (2009, methodology): “When the state is fully observable, the Probabilistic Roadmap (PRM) algorit hm (Kavraki et al., 1996; Bohlin and Kavraki, 2000) can be used to find a path through Cfree by generating a discrete graph approximation of Cfree.”
A Survey of Motion Planning Algorithms from the Perspective of Autonomous UAV Guidance (2010, methodology): “Bohlin and Kavraki [11] outlines the Lazy PRM, a modified method that overcomes some of the simple PRM’s limitations.”
Dynamically-Stable Motion Planning for Humanoid Robots (2002, methodology): “This has motivated the use of heuristic algorithms, many of which employ randomization (e.g., Barraquand and Latombe, 1990; Horsch et al., 1994; Amato and Wu, 1996; Kavraki et al., 1996; Hsu et al., 1997; Mazer et al., 1998; Boor et al., 1999; Kuffner and LaValle, 2000; Bohlin and Kavraki, 2000 ).”
iGibson 1.0: A Simulation Environment for Interactive Tasks in Large Realistic Scenes (2020, methodology): “In iGibson, we include implementations of the most popular sampling-based motion planners: rapidly growing random trees (RRT [61]) and its bidirectional variant (BiRRT [62]), and lazy probabilistic road-maps (lazyPRM [63]), adapted from [64].”
Elastic Strips: A Framework for Motion Generation in Human Environments (2002, background): “1996) has significantly increased the applicability of motion planning algorithms and remains an active area of research (Amato et al. 1998; LaValle, Yakey, and Kavraki 1999; Hsu et al. 1999; Bohlin and Kavraki 2000; Bohlin 2001).”
Posterior Sampling for Anytime Motion Planning on Graphs with Expensive-to-Evaluate Edges (2020, background): “Lazy search approaches deal with this by only checking edges that lie along the estimated shortest path [3, 8] or the shortest subpath [9, 10].”
Randomized Kinodynamic Motion Planning with Moving Obstacles (2002, methodology): “However, as was shown in Reif (1979), path planning is PSPACE-hard, which is strong indication that any complete planner is likely to be exponential in the number of DoFs of a robot.”
Integrated Task and Motion Planning (2020, background): “For example, in many manipulation applications, collision checking is expensive, due to the geometric complexity of 3D meshes and the need to check at a ﬁne resolution to ensure safety, so we might wish to lazily postpone this operation (57, 58).”
Motion planning for urban driving using RRT (2008, neutral): “The difference from the previous work [14], [15] is that the lazy check in this paper is about re-checking of the constraints for previously feasible edges, whereas the previous work is about delaying the first collision detection in the static environment.”
A Single-Query Bi-Directional Probabilistic Roadmap Planner with Lazy Collision Checking (2001, background): “The planner in [13] distributes points uniformly at random in conﬁguration space.”
Multipartite RRTs for Rapid Replanning in Dynamic Environments (2007, methodology): “We are currently exploring deferred validation of tree and forest nodes, as in [18].”
Autonomous Vehicle Technologies for Small Fixed-Wing UAVs (2003, methodology): “The EKF time update equations are as follows: _ ` = p +q sin`tanµ +rcos`tanµ (1) _ µ = q cos`irsin` (2) _ ˆ = q sin`secµ +rcos`secµ ( 3 ) where p, q, and r are roll, pitch, and yaw rates as measured by on-board rate gyros.”