A Reconfigurable Hardware Library for Robot Scene Perception

A Reconfigurable Hardware Library for Robot Scene Perception
复制标题

用于机器人场景感知的可重构硬件库

DOI:
10.1145/3508352.3561110
复制
发表时间:
2022
期刊:
ACM
影响因子:
--
通讯作者:
Bahar, R. Iris
Bahar, R. Iris
中科院分区:
--
文献类型:
--
作者:
Liu, Yanqi;Opipari, Anthony;Jenkins, Odest Chadwicke;Bahar, R. Iris

文献摘要

参考文献

相似文献

感知物体的位置和方向(即,姿态估计)是机器人在其自然环境中动作的关键先决条件。我们提出了一种硬件加速方法,使实时和节能的关节姿态估计机器人在非结构化环境中运行。我们的硬件加速器实现了非参数置信传播(NBP)来推断关节对象姿态的置信分布。我们的方法平均比高端GPU高26倍的能效,比嵌入式低功耗GPU实现快11倍。此外,我们提出了一个蒙特卡洛感知库产生的高层次的综合,使可重构的硬件设计FPGA结构,更好地调整到用户指定的场景,资源和性能约束。
Perceiving the position and orientation of objects (i.e., pose estimation) is a crucial prerequisite for robots acting within their natural environment. We present a hardware acceleration approach to enable real-time and energy efficient articulated pose estimation for robots operating in unstructured environments. Our hardware accelerator implements Nonparametric Belief Propagation (NBP) to infer the belief distribution of articulated object poses. Our approach is on average, 26× more energy efficient than a high-end GPU and 11× faster than an embedded low-power GPU implementation. Moreover, we present aMonte-Carlo Perception Librarygenerated from high-level synthesis to enable reconfigurable hardware designs on FPGA fabrics that are better tuned to user-specified scene, resource, and performance constraints.
一种基于FPGA和传感器融合的实时姿态估计算法
DOI: --
发表时间: 2018
期刊: Symposium on Intelligent Systems and Informatics
影响因子: --
作者:
Laszlo Schäffer;Zoltán Kincses;Szilveszter Pletl
通讯作者: Szilveszter Pletl
GRIP:对抗环境中语义机器人操作的生成鲁棒推理和感知
DOI: --
发表时间: 2019
期刊: IEEE/RJS International Conference on Intelligent RObots and Systems
影响因子: --
作者:
Xiaotong Chen;R. Chen;Zhiqiang Sui;Zhefan Ye;Yanqi Liu;R. I. Bahar;O. C. Jenkins
通讯作者: O. C. Jenkins
用于关节物体姿态估计和操纵的高效非参数置信传播
DOI: 10.1126/scirobotics.aaw4523
发表时间: 2019
期刊: Science Robotics
影响因子: 25
作者:
Desingh, Karthik;Lu, Shiyang;Opipari, Anthony;Jenkins, Odest Chadwicke
通讯作者: Jenkins, Odest Chadwicke
DOI: 10.1117/12.402510
发表时间: 2000-10
期刊: --
影响因子: --
作者:
M. Gorgon;R. Tadeusiewicz
通讯作者: M. Gorgon;R. Tadeusiewicz
使用生成判别推理进行安全机器人应用的鲁棒对象估计
DOI: 10.1145/3240765.3243493
发表时间: 2018
期刊: 2018 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)
影响因子: --
作者:
Yanqi Liu;A. Costantini;R. I. Bahar;Zhiqiang Sui;Zhefan Ye;Shiyang Lu;O. C. Jenkins
通讯作者: O. C. Jenkins