Sökning: id:"swepub:oai:DiVA.org:oru-88030" >
Localising Faster :
Localising Faster : Efficient and precise lidar-based robot localisation in large-scale environments
-
- Sun, L. (författare)
- Lincoln Centre for Autonomous Systems (L-CAS), University of Lincoln, UK
-
- Adolfsson, Daniel, 1992- (författare)
- Örebro universitet,Institutionen för naturvetenskap och teknik
-
- Magnusson, Martin, 1977- (författare)
- Örebro universitet,Institutionen för naturvetenskap och teknik
-
visa fler...
-
- Andreasson, Henrik, 1977- (författare)
- Örebro universitet,Institutionen för naturvetenskap och teknik
-
- Posner, I. (författare)
- University of Oxford, Oxford, UK
-
- Duckett, T. (författare)
- Lincoln Centre for Autonomous Systems (L-CAS), University of Lincoln, UK
-
visa färre...
-
(creator_code:org_t)
- IEEE, 2020
- 2020
- Engelska.
-
Ingår i: 2020 IEEE International Conference on Robotics and Automation (ICRA). - : IEEE. - 9781728173962 - 9781728173955 ; , s. 4386-4392
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- 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.
Ämnesord
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Robotteknik och automation (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Robotics (hsv//eng)
Nyckelord
- 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
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas