A robot path planning framework that learns from experience

By Dmitry Berenson, Pieter Abbeel, Ken Goldberg. 2012

229 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Biomedical Engineering, Computer Vision and Pattern Recognition, Reinforcement Learning

How researchers see this paper

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

In Aerospace Engineering

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Reinforcement Learning

Citations in the corpus

Learning Trajectory Preferences for Manipulators via Iterative Improvement (2013, background): “sider robot conﬁgurations, object-object relations, and temporal behavior, and use them to learn a score function representing the preferences in trajectories. In other related works, Berenson et al. [4] and Phillips et al. [24] consider the problem of trajectories for highdimensional manipulators. ”
Alternative Paths Planner (APP) for Provably Fixed-time Manipulation Planning in Semi-structured Environments (2020, methodology): “APP uses Lightning as its underlying motion planner P .”
Learning a Decentralized Multi-arm Motion Planner (2020, background): “Some of these works have improved the speed of SMPs by biasing the sampling distribution of new nodes [14, 15, 16], directly predicting the next node [17], utilizing past experience with an extra lookup table module [18], or reducing the search space through discretization [5, 6, 19].”
Image Object Label 3 D CAD Model Candidate Grasps Google Object Recognition Engine Google Cloud Storage Select Feasible Grasp with Highest Success Probability Pose EstimationCamera Robots Cloud 3 D Sensor (2014, background): “Whichever finishes first is chosen [35] .”
E-Graphs: Bootstrapping Planning with Experience Graphs (2012, background): “Some more recent work [2] also attempts to repair paths from”
Learning Sampling Distributions for Robot Motion Planning (2017, background): “[10] cache paths, and use a learned heuristic to store new paths as well as recall and repair old paths.”
A Survey of Research on Cloud Robotics and Automation (2015, background): “In contrast to automated telephone reservation systems, consider a future scenario where errors and exceptions are detected by robots and automation systems which then contact humans at remote call centers for guidance.”
Motion Planning Networks: Bridging the Gap Between Learning-Based and Classical Motion Planners (2019, methodology): “[37] use a learned heuristic to store new paths, if needed, or to recall and repair”
Cloud-based robot grasping with the google object recognition engine (2013, background): “…humans sharing code, data, algorithms, and hardware designs [6] [8] [46], 4) Collective Robot Learning: robots sharing trajectories, control policies, and outcomes, and 5) Crowdsourcing and call centers: offline and on-demand human guidance for evaluation, learning, and error recovery [13] [41].”
Learning preferences for manipulation tasks from online coactive feedback (2015, background): “Berenson et al. [5] and Phillips et al. [41] consider the problem of trajectories for high-dimensional manipulators.”
Motion Planning Networks (2018, unknown): “[1], which is composed of two modules.”