TwistSLAM++: Fusing multiple modalities for accurate dynamic semantic SLAM - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

TwistSLAM++: Fusing multiple modalities for accurate dynamic semantic SLAM

Résumé

Most classical SLAM systems rely on the static scene assumption, which limits their applicability in real world scenarios. Recent SLAM frameworks have been proposed to simultaneously track the camera and moving objects. However they are often unable to estimate the canonical pose of the objects and exhibit a low object tracking accuracy. To solve this problem we propose TwistSLAM++, a semantic, dynamic, SLAM system that fuses stereo images and LiDAR information. Using semantic information, we track potentially moving objects and associate them to 3D object detections in LiDAR scans to obtain their pose and size. Then, we perform registration on consecutive object scans to refine object pose estimation. Finally, object scans are used to estimate the shape of the object and constrain map points to lie on the estimated surface within the bundle adjustment. We show on classical benchmarks that this fusion approach based on multimodal information improves the accuracy of object tracking.
Fichier principal
Vignette du fichier
root.pdf (1.06 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04158998 , version 1 (11-07-2023)

Licence

Paternité

Identifiants

Citer

Mathieu Gonzalez, Eric Marchand, Amine Kacete, Jérome Royan. TwistSLAM++: Fusing multiple modalities for accurate dynamic semantic SLAM. IROS 2023 - IEEE/RSJ International Conference on Intelligent Robots and Systems, Oct 2023, Detroit, MI, United States. pp.1-7. ⟨hal-04158998⟩
49 Consultations
24 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More