Learning-Guided Exploration for Efficient Sampling-Based Motion Planning in High Dimensions

Schramm, Liam; Boularias, Abdeslam

doi:10.1109/icra46639.2022.9812184

Cited by 6 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several approaches have tried to combine the exploratory ability of SBP with RL, leveraging planning for global exploration while learning a local control policy via RL [20][21][22]. These methods were primarily developed for and tested on navigation tasks, where nearby state space samples are generally easy to connect by an RL agent acting as a local planner.…”

Section: Related Workmentioning

confidence: 99%

Sampling-based Exploration for Reinforcement Learning of Dexterous Manipulation

Khandate¹,

Shang²,

Chang³

et al. 2023

Robotics: Science and Systems XIX

View full text Add to dashboard Cite

In this paper, we present a novel method for achieving dexterous manipulation of complex objects, while simultaneously securing the object without the use of passive support surfaces. We posit that a key difficulty for training such policies in a Reinforcement Learning framework is the difficulty of exploring the problem state space, as the accessible regions of this space form a complex structure along manifolds of a high-dimensional space. To address this challenge, we use two versions of the non-holonomic Rapidly-Exploring Random Trees algorithm; one version is more general, but requires explicit use of the environment's transition function, while the second version uses manipulation-specific kinematic constraints to attain better sample efficiency. In both cases, we use states found via sampling-based exploration to generate reset distributions that enable training control policies under full dynamic constraints via model-free Reinforcement Learning. We show that these policies are effective at manipulation problems of higher difficulty than previously shown, and also transfer effectively to real robots. A number of example videos can also be found on the project website: sbrl.cs.columbia.edu Fig. 7: Key frames of the finger-gaiting in simulation and on the real hand for representative objects in simulation and on real hand. Representative videos of these tasks can be found on our project website sbrl.cs.columbia.edu

show abstract

Section: Related Workmentioning

confidence: 99%

Sampling-based Exploration for Reinforcement Learning of Dexterous Manipulation

Khandate¹,

Shang²,

Chang³

et al. 2023

Robotics: Science and Systems XIX

View full text Add to dashboard Cite

show abstract

“…Deep learning techniques such as Conditional Variational AutoEncoder (CVAE), CNN, GAN and their variants have been widely used to solve motion‐planning algorithms by generating processed configuration space in advance to guide the expansion of classical motion‐planning algorithms [19–30].…”

Section: Supervised Learning Based Motion Planningmentioning

confidence: 99%

“…Naman et al. [20] trained a CNN model with U‐Net [32] as the backbone to predict promising states of the given environment and the sampling distribution for robot joints. In Ref.…”

Section: Supervised Learning Based Motion Planningmentioning

confidence: 99%

A survey of learning‐based robot motion planning

Wang

Zhang

et al. 2021

IET Cyber-Syst and Robotics

View full text Add to dashboard Cite

A fundamental task in robotics is to plan collision-free motions among a set of obstacles. Recently, learning-based motion-planning methods have shown significant advantages in solving different planning problems in high-dimensional spaces and complex environments. This article serves as a survey of various different learning-based methods that have been applied to robot motion-planning problems, including supervised, unsupervised learning, and reinforcement learning. These learning-based methods either rely on a human-crafted reward function for specific tasks or learn from successful planning experiences. The classical definition and learning-related definition of motion-planning problem are provided in this article. Different learning-based motion-planning algorithms are introduced, and the combination of classical motion-planning and learning techniques is discussed in detail.This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.

show abstract

Obstacle Avoidance Control Method for Robotic Assembly Process Based on Lagrange PPO

Quan,

Zhu,

et al. 2023

Communications in Computer and Information Science

View full text Add to dashboard Cite

Learning-Guided Exploration for Efficient Sampling-Based Motion Planning in High Dimensions

Cited by 6 publications

References 18 publications

Sampling-based Exploration for Reinforcement Learning of Dexterous Manipulation

Sampling-based Exploration for Reinforcement Learning of Dexterous Manipulation

A survey of learning‐based robot motion planning

Obstacle Avoidance Control Method for Robotic Assembly Process Based on Lagrange PPO

Contact Info

Product

Resources

About