Localising Faster: Efficient and precise lidar-based robot localisation in large-scale environments

Sun, L.Lincoln Centre for Autonomous Systems (L-CAS), University of Lincoln, UK (författare)

Localising Faster : Efficient and precise lidar-based robot localisation in large-scale environments

Funding agency:UK Research & Innovation (UKRI)Engineering & Physical Sciences Research Council (EPSRC) EP/M019918/1
This paper proposes a novel approach for global localisation of mobile robots in large-scale environments. Our method leverages learning-based localisation and filtering-based localisation, to localise the robot efficiently and precisely through seeding Monte Carlo Localisation (MCL) with a deeplearned distribution. In particular, a fast localisation system rapidly estimates the 6-DOF pose through a deep-probabilistic model (Gaussian Process Regression with a deep kernel), then a precise recursive estimator refines the estimated robot pose according to the geometric alignment. More importantly, the Gaussian method (i.e. deep probabilistic localisation) and nonGaussian method (i.e. MCL) can be integrated naturally via importance sampling. Consequently, the two systems can be integrated seamlessly and mutually benefit from each other. To verify the proposed framework, we provide a case study in large-scale localisation with a 3D lidar sensor. Our experiments on the Michigan NCLT long-term dataset show that the proposed method is able to localise the robot in 1.94 s on average (median of 0.8 s) with precision 0.75 m in a largescale environment of approximately 0.5 km 2.

TEKNIK OCH TEKNOLOGIER Elektroteknik och elektronik Robotteknik och automation hsv//swe
ENGINEERING AND TECHNOLOGY Electrical Engineering, Electronic Engineering, Information Engineering Robotics hsv//eng
Gaussian processes
learning (artificial intelligence)
mobile robots
Monte Carlo methods
neural nets
optical radar
path planning
recursive estimation
robot vision
SLAM (robots)
precise lidar-based robot localisation
large-scale environments
global localisation
Monte Carlo Localisation
MCL
fast localisation system
deep-probabilistic model
Gaussian process regression
deep kernel
precise recursive estimator
Gaussian method
deep probabilistic localisation
large-scale localisation
largescale environment
time 0.8 s
size 0.75 m
Robots
Neural networks
Three-dimensional displays
Laser radar
Kernel
Computer Science
Datavetenskap

Adolfsson, Daniel,1992-Örebro universitet,Institutionen för naturvetenskap och teknik(Swepub:oru)dlao (författare)
Magnusson, Martin,1977-Örebro universitet,Institutionen för naturvetenskap och teknik(Swepub:oru)mnmn (författare)
Andreasson, Henrik,1977-Örebro universitet,Institutionen för naturvetenskap och teknik(Swepub:oru)hkan (författare)
Posner, I.University of Oxford, Oxford, UK (författare)
Duckett, T.Lincoln Centre for Autonomous Systems (L-CAS), University of Lincoln, UK (författare)
Lincoln Centre for Autonomous Systems (L-CAS), University of Lincoln, UKInstitutionen för naturvetenskap och teknik (creator_code:org_t)

Ingår i:2020 IEEE International Conference on Robotics and Automation (ICRA): IEEE, s. 4386-439297817281739629781728173955

Av författaren/redakt...: Sun, L.; Adolfsson, Danie ...; Magnusson, Marti ...; Andreasson, Henr ...; Posner, I.; Duckett, T.

Om ämnet

TEKNIK OCH TEKNOLOGIER: TEKNIK OCH TEKNO ...; och Elektroteknik oc ...; och Robotteknik och ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.