18 papers
DiffuSearch: How Hybrid Trajectory Planning Benefits from Aligned Objectives in Diffusion and Action Space
Steffen Hagedorn, Aron Distelzweig, Alexandru P. Condurache
In trajectory planning for autonomous driving, hybrid planning architectures are often realized as a collection of disparate modules, each with its own objectives. This lack of a u…
Driving on Memory
Christian Löwens, Thorben Funke, Alexandru Paul Condurache
End-to-end autonomous driving models plan future trajectories from raw sensor input. While earlier driving benchmarks often measured deviation from the human trajectory, current be…
GhostPoint: Self-Supervised Representation Learning by Hallucinating Occluded LiDAR Structure
Mohamed Abdelsamad, Bin Yang, Michael Ulrich +4
3D object detection from LiDAR point clouds is a core problem in autonomous driving. Recent advances in self-supervised learning (SSL) enable scalable pretraining and transfers wel…
HASTE: A Framework for Training-Free, Dynamic, and Steerable Compression of Pre-Trained Convolutional Neural Networks
Lukas Meiner, Jens Mehnert, Alexandru Paul Condurache
Deploying large convolutional neural networks (CNNs) on resource-constrained devices is challenging due to their high computational cost. While dynamic execution methods are promis…
Collaborative Learning for Semi-Supervised LiDAR Semantic Segmentation
Bin Yang, Alexandru Paul Condurache
Annotating large-scale LiDAR point clouds for 3D semantic segmentation is costly and time-consuming, which motivates the use of semi-supervised learning (SemiSL). Standard LiDAR Se…
Towards Foundation Models for 3D Scene Understanding: Instance-Aware Self-Supervised Learning for Point Clouds
Bin Yang, Mohamed Abdelsamad, Miao Zhang +1
Recent advances in self-supervised learning (SSL) for point clouds have substantially improved 3D scene understanding without human annotations. Existing approaches emphasize seman…
SparseLaneSTP: Leveraging Spatio-Temporal Priors with Sparse Transformers for 3D Lane Detection
Maximilian Pittner, Joel Janai, Mario Faigle +1
3D lane detection has emerged as a critical challenge in autonomous driving, encompassing identification and localization of lane markings and the 3D road surface. Conventional 3D…
When Planners Meet Reality: How Learned, Reactive Traffic Agents Shift nuPlan Benchmarks
Steffen Hagedorn, Luka Donkov, Aron Distelzweig +1
Planner evaluation in closed-loop simulation often uses rule-based traffic agents, whose simplistic and passive behavior can hide planner deficiencies and bias rankings. Widely use…
PseudoMapTrainer: Learning Online Mapping without HD Maps
Christian Löwens, Thorben Funke, Jingchao Xie +1
Online mapping models show remarkable results in predicting vectorized maps from multi-view camera images only. However, all existing approaches still rely on ground-truth high-def…
Variance-Based Pruning for Accelerating and Compressing Trained Networks
Uranik Berisha, Jens Mehnert, Alexandru Paul Condurache
Increasingly expensive training of ever larger models such as Vision Transfomers motivate reusing the vast library of already trained state-of-the-art networks. However, their late…
Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks
Uranik Berisha, Jens Mehnert, Alexandru Paul Condurache
Vision Transformers have emerged as the state-of-the-art models in various Computer Vision tasks, but their high computational and resource demands pose significant challenges. Whi…
FA-KPConv: Introducing Euclidean Symmetries to KPConv via Frame Averaging
Ali Alawieh, Alexandru P. Condurache
We present Frame-Averaging Kernel-Point Convolution (FA-KPConv), a neural network architecture built on top of the well-known KPConv, a widely adopted backbone for 3D point cloud a…
PROM: Prioritize Reduction of Multiplications Over Lower Bit-Widths for Efficient CNNs
Lukas Meiner, Jens Mehnert, Alexandru Paul Condurache
Convolutional neural networks (CNNs) are crucial for computer vision tasks on resource-constrained devices. Quantization effectively compresses these models, reducing storage size…
Learning Through Retrospection: Improving Trajectory Prediction for Automated Driving with Error Feedback
Steffen Hagedorn, Aron Distelzweig, Marcel Hallgarten +1
In automated driving, predicting trajectories of surrounding vehicles supports reasoning about scene dynamics and enables safe planning for the ego vehicle. However, existing model…
FLARES: Fast and Accurate LiDAR Multi-Range Semantic Segmentation
Bin Yang, Alexandru Paul Condurache
3D scene understanding is a critical yet challenging task in autonomous driving due to the irregularity and sparsity of LiDAR data, as well as the computational demands of processi…
Unsupervised Point Cloud Registration with Self-Distillation
Christian Löwens, Thorben Funke, André Wagner +1
Rigid point cloud registration is a fundamental problem and highly relevant in robotics and autonomous driving. Nowadays deep learning methods can be trained to match a pair of poi…
LaneCPP: Continuous 3D Lane Detection using Physical Priors
Maximilian Pittner, Joel Janai, Alexandru P. Condurache
Monocular 3D lane detection has become a fundamental problem in the context of autonomous driving, which comprises the tasks of finding the road surface and locating lane markings.…
Pioneering SE(2)-Equivariant Trajectory Planning for Automated Driving
Steffen Hagedorn, Marcel Milich, Alexandru P. Condurache
Planning the trajectory of the controlled ego vehicle is a key challenge in automated driving. As for human drivers, predicting the motions of surrounding vehicles is important to…