Henrik I Christensen
Henrik I Christensen
Home
Posts
Projects
Courses
Students
Publications
Contact
CV
Light
Dark
Automatic
1
SemVecNet: Generalizable Vector Map Generation for Arbitrary Sensor Configurations
Vector maps are essential in autonomous driving for tasks like localization and planning, yet their creation and maintenance are notably costly. While recent advances in online vector map generation for autonomous vehicles are promising, current models lack adaptability to different sensor configurations. They tend to overfit to specific sensor poses, leading to decreased performance and higher retraining costs. This limitation hampers their practical use in real-world applications. In response to this challenge, we propose a modular pipeline for vector map generation with improved generalization to sensor configurations. The pipeline leverages probabilistic semantic mapping to generate a bird’s-eye-view (BEV) semantic map as an intermediate representation. This intermediate representation is then converted to a vector map using the MapTRv2 decoder. By adopting a BEV semantic map robust to different sensor configurations, our proposed approach significantly improves the generalization performance. We evaluate the model on datasets that are different from the training set including real-world data collected with our platform with different sensor configurations and show that the model generalizes significantly better than the state-of-the-art methods.
N. Ranganatha
,
H. Zhang
,
S. Vankatramani
,
J-Y. Liao and H.I. Christensen
Cite
Code
Project
Open X-Embodiment: Robot Learning Dataset
Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream …
Quan Vuong Et Al
PDF
Cite
Project
Household navigation and manipulation for everyday object rearrangement tasks
We consider the problem of building an assistive robotic system that can help humans in daily household cleanup tasks. Creating such an …
Shrutheesh R. Iyer
,
Anwesan Pal
,
Jiaming Hu
,
Akanimoh Adeleye
,
Aditya Aggarwal
,
Henrik I. Christensen
PDF
Cite
Code
Project
Video
DOI
3D Scene Graph Prediction on Point Clouds Using Knowledge Graphs
Yiding Qiu
,
Henrik I Christensen
Cite
A Real2Sim2Real Method for Robust Object Grasping with Neural Surface Reconstruction
Luobin Wang
,
Runlin Guo
,
Quan Vuong
,
Yuzhe Qin
,
Hao Su
,
Henrik I Christensen
Cite
Scaling up multi-agent patrolling in urban environments
Rohan Patil
,
Alexander Langley
,
Henrik I. Christensen
Cite
Place-And-Pick-Based Re-Grasping Using Unstable Placement
J. Hu
,
A. Adeleye
,
H. I. Christensen
Cite
Putting away the Groceries with Precise Semantic Placements
A. Adeleye
,
J. Hu
,
H. Christensen
Cite
Robust Human Identity Anonymization using Pose Estimation
H. Zhang
,
J.-Y. Liao
,
D. Paz
,
H. I. Christensen
Cite
Rotational Slippage Minimization in Object Manipulation
J. Hu
,
H. I. Christensen
Cite
Project
»
Cite
×