Robowflex: Robot Motion Planning with MoveIt Made Easy

Kingston, Zachary; Kavraki, Lydia E.

doi:10.48550/arxiv.2103.12826

Cited by 2 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…V-C). For our experiments we used Robowflex with MoveIt [55], [56] and the OMPL benchmarking tools [57]. The sampling parameters for FIRE were the same as [12] (σ 2 = 0.2, λ = 0.5).…”

Section: Methodsmentioning

confidence: 99%

Learning to Retrieve Relevant Experiences for Motion Planning

Chamzas¹,

Cullen²,

Shrivastava³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Recent work has demonstrated that motion planners' performance can be significantly improved by retrieving past experiences from a database. Typically, the experience database is queried for past similar problems using a similarity function defined over the motion planning problems. However, to date, most works rely on simple hand-crafted similarity functions and fail to generalize outside their corresponding training dataset. To address this limitation, we propose (FIRE), a framework that extracts local representations of planning problems and learns a similarity function over them. To generate the training data we introduce a novel self-supervised method that identifies similar and dissimilar pairs of local primitives from past solution paths. With these pairs, a Siamese network is trained with the contrastive loss and the similarity function is realized in the network's latent space. We evaluate FIRE on an 8-DOF manipulator in five categories of motion planning problems with sensed environments. Our experiments show that FIRE retrieves relevant experiences which can informatively guide sampling-based planners even in problems outside its training distribution, outperforming other baselines.

show abstract

“…V-C). For our experiments we used Robowflex with MoveIt [55], [56] and the OMPL benchmarking tools [57]. The sampling parameters for FIRE were the same as [12] (σ 2 = 0.2, λ = 0.5).…”

Section: Methodsmentioning

confidence: 99%

Learning to Retrieve Relevant Experiences for Motion Planning

Chamzas¹,

Cullen²,

Shrivastava³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Once loaded, Setup can create instances of a robot (line 3) and a planner (line 4). Our library takes advantage of the Robowflex [14] library to provide these constructs-Robowflex encapsulates the MoveIt [13] library for motion planning and provides capabilities for planning inside simple scripts.…”

Section: Setupmentioning

confidence: 99%

“…MOTIONBENCH-MAKER also provides the ability to convert scenes described with geometric primitives and meshes to a "sensed" representation, i.e., point clouds and octomaps [11]. MOTIONBENCH-MAKER is fully compatible with the ROS [12] ecosystem of tools and interfaces such as visualization with RViz and motion planning through MoveIt [13] and Robowflex [14]. To summarize, with MOTIONBENCHMAKER we contribute a tool which…”

Section: Introductionmentioning

confidence: 99%

MotionBenchMaker: A Tool to Generate and Benchmark Motion Planning Datasets

Chamzas,

Quintero-Peña,

Kingston

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Recently, there has been a wealth of development in motion planning for robotic manipulation-new motion planners are continuously proposed, each with their own unique strengths and weaknesses. However, evaluating new planners is challenging and researchers often create their own ad-hoc problems for benchmarking, which is time-consuming, prone to bias, and does not directly compare against other state-of-the-art planners. We present MOTIONBENCHMAKER, an open-source tool to generate benchmarking datasets for realistic robot manipulation problems. MOTIONBENCHMAKER is designed to be an extensible, easyto-use tool that allows users to both generate datasets and benchmark them by comparing motion planning algorithms. Empirically, we show the benefit of using MOTIONBENCHMAKER as a tool to procedurally generate datasets which helps in the fair evaluation of planners. We also present a suite of 40 prefabricated datasets, with 5 different commonly used robots in 8 environments, to serve as a common ground to accelerate motion planning research.

show abstract

Robowflex: Robot Motion Planning with MoveIt Made Easy

Cited by 2 publications

References 22 publications

Learning to Retrieve Relevant Experiences for Motion Planning

Learning to Retrieve Relevant Experiences for Motion Planning

MotionBenchMaker: A Tool to Generate and Benchmark Motion Planning Datasets

Contact Info

Product

Resources

About