2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2018
DOI: 10.1109/iros.2018.8593947
|View full text |Cite
|
Sign up to set email alerts
|

Deep Sequential Models for Sampling-Based Planning

Abstract: We demonstrate how a sequence model and a sampling-based planner can influence each other to produce efficient plans and how such a model can automatically learn to take advantage of observations of the environment. Samplingbased planners such as RRT generally know nothing of their environments even if they have traversed similar spaces many times. A sequence model, such as an HMM or LSTM, guides the search for good paths. The resulting model, called DeRRT * , observes the state of the planner and the local en… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
11
0

Year Published

2019
2019
2021
2021

Publication Types

Select...
8

Relationship

1
7

Authors

Journals

citations
Cited by 16 publications
(11 citation statements)
references
References 32 publications
0
11
0
Order By: Relevance
“…Recent works [9][10] [11] [12] [13] [14] [15] have explored learning-based approaches to solving motion planning problems. While some employ a supervised imitation learning approach to train a model to mimic example paths, others use reinforcement learning techniques to learn path generation by trial and error.…”
Section: A Learning-based Planningmentioning
confidence: 99%
“…Recent works [9][10] [11] [12] [13] [14] [15] have explored learning-based approaches to solving motion planning problems. While some employ a supervised imitation learning approach to train a model to mimic example paths, others use reinforcement learning techniques to learn path generation by trial and error.…”
Section: A Learning-based Planningmentioning
confidence: 99%
“…Here we describe how to augment them with networks that efficiently learn language, how to guide the planning process, and how to recognize when a plan described by a sentence has been completed. This is related to the approach of Kuo et al [7], DeRRT, which introduced deep sequential models for sampling-based planning. It took an RRT-based and described how to guide its behavior with a neural network.…”
Section: A Planning With Deep Rrtmentioning
confidence: 99%
“…Powerful models can control agents but do so from moment to moment without planning complex actions [1,2,3]. Planners on the other hand efficiently explore configuration spaces, often by building search trees [4,5], but require a target final configuration [6,7,8] or a symbolic specification of constraints [9,10].…”
Section: Introductionmentioning
confidence: 99%
“…Diankov and Kuffner [28] employs statistical techniques to sample around a search tree. Zucker et al [29], Kuo et al [30] formalize sampling as a model-free reinforcement learning problem and learn a parametric distribution. Since these problems are non i.i.d learning problems, they do require interactive learning and do not enjoy the strong guarantees of supervised learning.…”
Section: Related Workmentioning
confidence: 99%