Zobrazeno 1 - 10
of 630
pro vyhledávání: '"Kiran, A. Ravi"'
Autor:
Gosala, Nikhil, Petek, Kürsat, Kiran, B Ravi, Yogamani, Senthil, Drews-Jr, Paulo, Burgard, Wolfram, Valada, Abhinav
Semantic Bird's Eye View (BEV) maps offer a rich representation with strong occlusion reasoning for various decision making tasks in autonomous driving. However, most BEV mapping approaches employ a fully supervised learning paradigm that relies on l
Externí odkaz:
http://arxiv.org/abs/2405.18852
Autor:
Schramm, Jonas, Vödisch, Niclas, Petek, Kürsat, Kiran, B Ravi, Yogamani, Senthil, Burgard, Wolfram, Valada, Abhinav
Semantic scene segmentation from a bird's-eye-view (BEV) perspective plays a crucial role in facilitating planning and decision-making for mobile robots. Although recent vision-only methods have demonstrated notable advancements in performance, they
Externí odkaz:
http://arxiv.org/abs/2403.11761
Autonomous agents face the challenge of coordinating multiple tasks (perception, motion planning, controller) which are computationally expensive on a single onboard computer. To utilize the onboard processing capacity optimally, it is imperative to
Externí odkaz:
http://arxiv.org/abs/2305.04614
Publikováno v:
Management of Environmental Quality: An International Journal, 2024, Vol. 35, Issue 5, pp. 1048-1077.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/MEQ-10-2023-0338
Active Learning (AL) has remained relatively unexplored for LiDAR perception tasks in autonomous driving datasets. In this study we evaluate Bayesian active learning methods applied to the task of dataset distillation or core subset selection (subset
Externí odkaz:
http://arxiv.org/abs/2302.10679
Autonomous driving (AD) perception today relies heavily on deep learning based architectures requiring large scale annotated datasets with their associated costs for curation and annotation. The 3D semantic data are useful for core perception tasks s
Externí odkaz:
http://arxiv.org/abs/2302.08292
Publikováno v:
Management of Environmental Quality: An International Journal, 2023, Vol. 35, Issue 2, pp. 249-269.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/MEQ-08-2023-0247
Autor:
T, Sugirtha, M, Sridevi, Santhakumar, Khailash, Liu, Hao, Kiran, B Ravi, Gauthier, Thomas, Yogamani, Senthil
Modern object detection architectures are moving towards employing self-supervised learning (SSL) to improve performance detection with related pretext tasks. Pretext tasks for monocular 3D object detection have not yet been explored yet in literatur
Externí odkaz:
http://arxiv.org/abs/2206.12738
Annotating objects with 3D bounding boxes in LiDAR pointclouds is a costly human driven process in an autonomous driving perception system. In this paper, we present a method to semi-automatically annotate real-world pointclouds collected by deployme
Externí odkaz:
http://arxiv.org/abs/2202.02666
Autonomous driving (AD) datasets have progressively grown in size in the past few years to enable better deep representation learning. Active learning (AL) has re-gained attention recently to address reduction of annotation costs and dataset size. AL
Externí odkaz:
http://arxiv.org/abs/2202.02661