Výsledky vyhledávání - "Peter R. Florence"

Learning to Rearrange Deformable Cables, Fabrics, and Bags with Goal-Conditioned Transporter Networks

Autor: Daniel Seita, Jonathan Tompson, Erwin Coumans, Vikas Sindhwani, Ken Goldberg, Andy Zeng, Peter R. Florence

Publikováno v: ICRA

Rearranging and manipulating deformable objects such as cables, fabrics, and bags is a long-standing challenge in robotic manipulation. The complex dynamics and high-dimensional configuration spaces of deformables, compared to rigid objects, make man

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1973ce20eead68e03c2d36cb5d0feb60
http://arxiv.org/abs/2012.03385

Zobrazit plný text záznamu

Integrated Perception and Control at High Speed: Evaluating Collision Avoidance Maneuvers Without Maps

Autor: J. D. Carter, Peter R. Florence, Russ Tedrake

Publikováno v: Springer Proceedings in Advanced Robotics ISBN: 9783030430887
WAFR

We present a method for robust high-speed quadrotor flight through unknown cluttered environments using integrated perception and control. Motivated by experiments in which the difficulty of accurate state estimation was a primary limitation on speed

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::5a05d8534af0bf061c623eadb226b081
https://doi.org/10.1007/978-3-030-43089-4_20

Zobrazit plný text záznamu

Self-Supervised Correspondence in Visuomotor Policy Learning

Autor: Peter R. Florence, Lucas Manuelli, Russ Tedrake

Publikováno v: MIT web domain

In this paper we explore using self-supervised correspondence for improving the generalization performance and sample efficiency of visuomotor policy learning. Prior work has primarily used approaches such as autoencoding, pose-based losses, and end-

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e7759652a4135c2e917082dfe0e092e5
https://hdl.handle.net/1721.1/135421

Zobrazit plný text záznamu

DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation

Autor: Peter R. Florence, Steven Lovegrove, Richard Newcombe, Julian Straub, Jeong Joon Park

Publikováno v: CVPR

Computer graphics, 3D computer vision and robotics communities have produced multiple approaches to representing 3D geometry for rendering and reconstruction. These provide trade-offs across fidelity, efficiency and compression capabilities. In this

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b94ea123c7bf94f77168f9e553f90f76
http://arxiv.org/abs/1901.05103

Zobrazit plný text záznamu

NanoMap: Fast, Uncertainty-Aware Proximity Queries with Lazy Search Over Local 3D Data

Autor: Russ Tedrake, Jake Ware, John Carter, Peter R. Florence

Publikováno v: arXiv
ICRA

We would like robots to be able to safely navigate at high speed, efficiently use local 3D information, and robustly plan motions that consider pose uncertainty of measurements in a local map structure. This is hard to do with previously existing map

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e9e1bb5f394220069683d6cbfd993e1e
https://hdl.handle.net/1721.1/137099

Zobrazit plný text záznamu

Label Fusion: A Pipeline for Generating Ground Truth Labels for Real RGBD Data of Cluttered Scenes

Autor: Peter R. Florence, Lucas Manuelli, Russ Tedrake, Pat Marion

Publikováno v: arXiv
ICRA

Deep neural network (DNN) architectures have been shown to outperform traditional pipelines for object segmentation and pose estimation using RGBD data, but the performance of these DNN pipelines is directly tied to how representative the training da

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::26722941bb4e2fe7367f12b3ab1fcbc8
https://hdl.handle.net/1721.1/129426

Zobrazit plný text záznamu

High‐speed autonomous obstacle avoidance with pushbroom stereo

Autor: Peter R. Florence, Andrew J. Barry, Russ Tedrake

Publikováno v: MIT web domain

© 2017 Wiley Periodicals, Inc. We present the design and implementation of a small autonomous unmanned aerial vehicle capable of high-speed flight through complex natural environments. Using only onboard GPS-denied sensing and computation, we perfor

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d16fcb57f18de52652fd8af89543fcac
https://hdl.handle.net/1721.1/133998

Zobrazit plný text záznamu

Surface dipole engineering for conducting polymers

Autor: Antoine Kahn, Peter R. Florence, Jeffrey Schwartz, Andrew L. Shu, William E. McClain

Publikováno v: Organic Electronics. 14:411-415

The first example of systematic control of the work function of a conducting polymer is illustrated for PEDOT:PSS. A nanometer-thick film of TiO 2 is formed on the PEDOT:PSS surface and forms an adhesion layer to bond phosphonic acids to the polymer;

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::b419415ffc3bbea04142d3b9728807dd
https://doi.org/10.1016/j.orgel.2012.11.019

Zobrazit plný text záznamu

Aggressive quadrotor flight through cluttered environments using mixed integer programming

Autor: Russ Tedrake, Benoit Landry, Robin Deits, Peter R. Florence

Publikováno v: MIT web domain
ICRA

Quadrotor flight has typically been limited to sparse environments due to numerical complications that arise when dealing with large numbers of obstacles. We hypothesized that it would be possible to plan and robustly execute trajectories in obstacle

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f8b15f67b0272655d8c22a4f0dd8cb1a
https://hdl.handle.net/1721.1/122048

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání