Anthony Simeonov

Anthony Simeonov

Auto-generated profile, based on publicly available information

Anthony Simeonov

Massachusetts Institute of Technology

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 August 2020 in IEEE Transactions on Robotics
Verified
Journal Article
Closed access
AQAhmed Hussain Qureshi
Ahmed Hussain Qureshi
YMYinglong Miao
Yinglong Miao
ASAnthony Simeonov
Anthony Simeonov
MYMichael C. Yip
Michael C. Yip
This article describes motion planning networks (MPNet), a computationally efficient, learning-based neural planner for solving motion planning problems.MPNet uses neural networks to learn general near-optimal heuristics for path planning in seen and unseen environments. It takes environment information such as raw point cloud from depth sensors, as well as a robot's initial and desired goal configurations and recursively calls itself to bidirectionally generate connectable paths. In addition to finding directly connectable and near-optimal paths in a single pass, we show that worst-case theoretical guarantees can be proven if we merge this neural network strategy with classical sample-based planners in a hybrid approach while still retaining significant computational and optimality improvements. To train the MPNet models, we present an active continual learning approach that enables MPNet to learn from streaming data and actively ask for expert demonstrations when needed, drastically reducing data for training. We validate MPNet against gold-standard and state-of-the-art planning methods in a variety of problems from two-dimensional to seven-dimensional robot configuration spaces in challenging and cluttered environments, with results showing significant and consistently stronger performance metrics, and motivating neural planning in general as a modern strategy for solving motion planning problems efficiently.

2 February 2018 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
ASAnthony Simeonov
Anthony Simeonov
THTaylor Henderson
Taylor Henderson
ZLZixuan Lan
Zixuan Lan
GSGuhan Sundar
Guhan Sundar
AFAdam Factor
Adam Factor
MYMichael Yip
Michael Yip
Super-coiled polymer (SCP) artificial muscles have many attractive properties, such as high energy density, large contractions, and good dynamic range. To fully utilize them for robotic applications, it is necessary to determine how to scale them up effectively. Bundling of SCP actuators, as though they are individual threads in woven textiles, can demonstrate the versatility of SCP actuators and artificial muscles in general. However, this versatility comes with a need to understand how different bundling techniques can be achieved with these actuators and how they may trade off in performance. This letter presents the first quantitative comparison, analysis, and modeling of bundled SCP actuators. By exploiting weaving and braiding techniques, three new types of bundled SCP actuators are created: woven bundles, two-dimensional, and three-dimensional braided bundles. The bundle performance is adjustable by employing different numbers of individual actuators. Experiments are conducted to characterize and compare the force, strain, and speed of different bundles, and a linear model is proposed to predict their performance. This work lays the foundation for model-based SCP-actuated textiles, and physically scaling robots that employ SCP actuators as the driving mechanism.

27 June 2020 in arXiv
Verified
Preprint
Open access
PDF file
AQAhmed H. Qureshi
Ahmed H. Qureshi
YMYinglong Miao
Yinglong Miao
ASAnthony Simeonov
Anthony Simeonov
MYMichael C. Yip
Michael C. Yip
This paper describes Motion Planning Networks (MPNet), a computationally efficient, learning-based neural planner for solving motion planning problems. MPNet uses neural networks to learn general near-optimal heuristics for path planning in seen and unseen environments. It takes environment information such as raw point-cloud from depth sensors, as well as a robot's initial and desired goal configurations and recursively calls itself to bidirectionally generate connectable paths. In addition to finding directly connectable and near-optimal paths in a single pass, we show that worst-case theoretical guarantees can be proven if we merge this neural network strategy with classical sample-based planners in a hybrid approach while still retaining significant computational and optimality improvements. To train the MPNet models, we present an active continual learning approach that enables MPNet to learn from streaming data and actively ask for expert demonstrations when needed, drastically reducing data for training. We validate MPNet against gold-standard and state-of-the-art planning methods in a variety of problems from 2D to 7D robot configuration spaces in challenging and cluttered environments, with results showing significant and consistently stronger performance metrics, and motivating neural planning in general as a modern strategy for solving motion planning problems efficiently.

10 July 2023 in arXiv
Verified
Preprint
Open access
PDF file
ASAnthony Simeonov
Anthony Simeonov
AGAnkit Goyal
Ankit Goyal
LMLucas Manuelli
Lucas Manuelli
LYLin Yen-Chen
Lin Yen-Chen
ASAlina Sarmiento
Alina Sarmiento
DFDieter Fox
Dieter Fox
We propose a system for rearranging objects in a scene to achieve a desired object-scene placing relationship, such as a book inserted in an open slot of a bookshelf. The pipeline generalizes to novel geometries, poses, and layouts of both scenes and objects, and is trained from demonstrations to operate directly on 3D point clouds. Our system overcomes challenges associated with the existence of many geometrically-similar rearrangement solutions for a given scene. By leveraging an iterative pose de-noising training procedure, we can fit multi-modal demonstration data and produce multi-modal outputs while remaining precise and accurate. We also show the advantages of conditioning on relevant local geometric features while ignoring irrelevant global structure that harms both generalization and precision. We demonstrate our approach on three distinct rearrangement tasks that require handling multi-modality and generalization over object shape and pose in both simulation and the real world. Project website, code, and videos: https://anthonysimeonov.github.io/rpdiff-multi-modal/