【免费】ProbabilisticDataAssociationforSemanticSLAM

需积分: 0 151 浏览量更新于2023-05-22 1 收藏 2.57MB PDF 举报

身份认证购VIP最低享 7 折!

领优惠券(最高得80元）

资源详情

资源推荐

Probabilistic Data Association for Semantic SLAM

Sean L. Bowman Nikolay Atanasov Kostas Daniilidis George J. Pappas

Abstract— Traditional approaches to simultaneous localiza-

tion and mapping (SLAM) rely on low-level geometric features

such as points, lines, and planes. They are unable to assign

semantic labels to landmarks observed in the environment.

Furthermore, loop closure recognition based on low-level fea-

tures is often viewpoint-dependent and subject to failure in

ambiguous or repetitive environments. On the other hand,

object recognition methods can infer landmark classes and

scales, resulting in a small set of easily recognizable landmarks,

ideal for view-independent unambiguous loop closure. In a

map with several objects of the same class, however, a crucial

data association problem exists. While data association and

recognition are discrete problems usually solved using discrete

inference, classical SLAM is a continuous optimization over

metric information. In this paper, we formulate an optimization

problem over sensor states and semantic landmark positions

that integrates metric information, semantic information, and

data associations, and decompose it into two interconnected

problems: an estimation of discrete data association and land-

mark class probabilities, and a continuous optimization over the

metric states. The estimated landmark and robot poses affect

the association and class distributions, which in turn affect

the robot-landmark pose optimization. The performance of our

algorithm is demonstrated on indoor and outdoor datasets.

I. INTRODUCTION

In robotics, simultaneous localization and mapping (SLAM)

is the problem of mapping an unknown environment while

estimating a robot’s pose within it. Reliable navigation, object

manipulation, autonomous surveillance, and many other tasks

require accurate knowledge of the robot’s pose and the

surrounding environment. Traditional approaches to SLAM

rely on low-level geometric features such as corners [1],

lines [2], and surface patches [3] to reconstruct the metric

3-D structure of a scene but are mostly unable to infer

semantic content. On the other hand, recent methods for

object recognition [4]–[6] can be combined with approximate

3D reconstruction of the environmental layout from single

frames using priors [7], [8]. These are rather qualitative single

3D snapshots rather than the more precise mapping we need

for a robot to navigate. The goal of this paper is to address the

metric and semantic SLAM problems jointly, taking advantage

of object recognition to tightly integrate both metric and

semantic information into the sensor state and map estimation.

In addition to providing a meaningful interpretation of the

scene, semantically-labeled landmarks address two critical

issues of geometric SLAM: data association (matching sensor

observations to map landmarks) and loop closure (recognizing

previously-visited locations).

The authors are with GRASP Lab, University of Pennsylvania,

Philadelphia, PA 19104, USA,

{seanbow, atanasov, kostas,

pappasg}@seas.upenn.edu.

We gratefully acknowledge support by TerraSwarm, one of six centers

of STARnet, a Semiconductor Research Corporation program sponsored by

MARCO and DARPA and the following grants: ARL MAST-CTA W911NF-

08-2-0004, ARL RCTA W911NF-10-2-0016.

Approaches to SLAM were initially most often based

on ﬁltering methods in which only the most recent robot

pose is estimated [9]. This approach is in general very

computationally efﬁcient, however because of the inability

to estimate past poses and relinearize previous measurement

functions, errors can compound [1]. More recently, batch

methods that optimize over entire trajectories have gained

popularity. Successful batch methods typically represent

optimization variables as a set of nodes in a graph (a “pose

graph”). Two robot-pose nodes share an edge if an odometry

measurement is available between them, while a landmark

and a robot-pose node share an edge if the landmark was

observed from the corresponding robot pose. This pose graph

optimization formulation of SLAM traces back to Lu and

Milios [10]. In recent years, the state of the art [11], [12]

consists of iterative optimization methods (e.g., nonlinear

least squares via the Gauss-Newton algorithm) that achieve

excellent performance but depend heavily on linearization

of the sensing and motion models. This becomes a problem

when we consider including discrete observations, such as

detected object classes, in the sensing model.

One of the ﬁrst systems that used both spatial and semantic

representations was proposed by Galindo et al. [13]. A spatial

hierarchy contained camera images, local metric maps, and the

environment topology, while a semantic hierarchy represented

concepts and relations, which allowed room categories to be

inferred based on object detections. Many other approaches

[14]–[19] extract both metric and semantic information but

typically the two processes are carried out separately and

the results are merged afterwards. The lack of integration

between the metric and the semantic mapping does not allow

the object detection conﬁdence to inﬂuence the performance

of the metric optimization. Focusing on the localization

problem only, Atanasov et al. [20] incorporated semantic

observations in the metric optimization via a set-based Bayes

ﬁlter. The works that are closest to ours [21]–[24] consider

both localization and mapping and carry out metric and

semantic mapping jointly. SLAM++ [22] focuses on a real-

time implementation of joint 3-D object recognition and RGB-

D SLAM via pose graph optimization. A global optimization

for 3D reconstruction and semantic parsing has been proposed

by [25], which is the closest work in semantic/geometric joint

optmization. The main difference is that 3D space is voxelized

and landmarks and/or semantic labels are assigned to voxels

which are connected in a conditional random ﬁeld while

our approach allows the estimation of continuous pose of

objects. Bao et al. [21] incorporate camera parameters, object

geometry, and object classes into a structure from motion

problem, resulting in a detailed and accurate but large and

expensive optimization. A recent comprehensive survey of

semantic mapping can be found in [26].

本内容试读结束，登录后可阅读更多

下载后可阅读完整内容，剩余7页未读，立即下载

fordanpianji

粉丝: 1
资源: 4

会员权益专享

Probabilistic Data Association for Semantic SLAM

Math counts 2019 State Sprint Competition

The Probabilistic Data Association Filter

Robust On-line Beat Tracking with Kalman Filtering and probabilistic data association

JPDA算法与PDA算法

JPDA和PDA计算概率时的区别

slam入门建议怎么学

Perform probabilistic iterative improvement for one iteration

jpda算法matlab目标跟踪

PDA算法卡尔曼滤波

传统jpda算法模型流程图

已知多条不同路径上导波信号的损伤概率，用MATLAB写一段Reconstruction algorithm for probabilistic inspection of damage程序

. Consider the 4-queen problem with the initial configuration below. The features and evaluation function is defined similarly as in Exercise 3. Perform probabilistic iterative improvement for one iteration. Calculate the expected loss value of the successor.

请推荐一些slam学习的资料

概率数据关联pda matlab

概率数据关联算法 pda 程序

ecoc2020 tu1j-6 probabilistic and geometric shaping for next-generation 100g

topic modeling matlab

jpda粒子滤波算法

航迹关联pda算法基本原理视频

7_目标跟踪_jpda.zip

会员权益专享

最新资源