Graph Neural Networks improve 3D object detection in LiDAR point clouds.
problem Challenges in processing LiDAR data due to its 3D geometry and massive volume.
method Proposes a Graph Neural Network (GNN) based framework for 3D object detection.
result GNNs successfully identify objects in 3D LiDAR point clouds.
Federated LIDAR aided beam selection reduces mmWave beam search overhead.
problem Efficient link configuration in mmWave communication systems with reduced beam search overhead.
method Federated learning of LIDAR data to train a shared neural network for beam selection.
result Proposed method significantly outperforms previous works in performance and complexity.
Paper classifies pedestrians and vehicles detected by LiDAR.
problem Classifying objects from LiDAR data for self-driving cars.
method Used LiDAR-based object detector and Neural Networks classifier.
result Real-time object detection for self-driving vehicles.
Adversarial objects can fool LiDAR-based autonomous driving systems.
problem Vulnerability of LiDAR-based autonomous driving systems to adversarial attacks.
method Optimization-based approach LiDAR-Adv to generate adversarial objects.
result LiDAR-based autonomous driving systems are vulnerable to adversarial attacks.
TensorMap uses tensor decompositions to create accurate topological maps from Lidar data.
problem Creating accurate topological maps from Lidar data in real-time.
method Orthogonal Tucker3 tensor decomposition.
result TensorMap accurately detects the vehicle's position in a graph-based map.
A CNN for lidar data improves understanding of moving vehicles.
problem Disambiguating the motion of vehicles from a single lidar sensor.
method Proposes a CNN architecture trained with pretext tasks including image data.
result CNN outperforms without image data at test time.
Improved road segmentation on low-res LIDAR data for autonomous vehicles.
problem Low-resolution LIDAR data affects road segmentation accuracy in autonomous vehicles.
method Subsampled LIDAR data transformation into feature maps, use local normal vector with spherical coordinates.
result Improves road segmentation accuracy on low-resolution LIDAR data.
Paper uses CNN to create realistic LiDAR data.
problem Creating high-resolution LiDAR data with missing points.
method Modified per-point loss and perceptual loss applied to generate realistic LiDAR data.
result Significant improvement in geometric and semantic accuracy over traditional methods.
FCN improves lidar cloud detection accuracy.
problem Segmenting lidar imagery into cloud locations.
method Semi-supervised learning with pre-training and fully supervised learning.
result FCN achieves higher cloud identification accuracy.
PointPainting fuses lidar and image data for better 3D object detection.
problem Lidar-only methods outperform fusion methods on 3D object detection benchmarks.
method Sequential fusion by projecting lidar points into image segmentation output and appending class scores.
result Significant improvements on state-of-the-art 3D object detection methods on KITTI and nuScenes datasets.
Industrial vehicle uses LiDAR and camera to detect and avoid restricted areas.
problem Avoiding collisions in industrial settings with automated vehicles.
method Combining LiDAR and camera data, using deep learning for projection, and model-predictive control.
result Reduces false positives in LiDAR detection of reflective beacons.
Improved 3D LiDAR data classification using product coefficients.
problem Enhancing accuracy in 3D LiDAR data classification.
method Introducing product coefficients derived from measure theory as additional features in the classification process, alongside PCA.
result Significant improvement in classification accuracy with product coefficients.
This study examines LiDAR spoofing attacks on autonomous vehicle perception.
problem Security vulnerabilities in LiDAR-based perception systems in autonomous driving.
method Formulated as an optimization problem, designed input perturbation and objective functions, combined optimization and global sampling.
result Attack success rates improved to around 75% through strategic input perturbation.
Study improves semantic segmentation of LiDAR point clouds for autonomous vehicles.
problem Semantic understanding of 3D LiDAR data for autonomous vehicles.
method Image-based semantic segmentation architectures, network size optimization, improved point cloud projection, soft Dice loss, reduced weight-sharing convolution.
result 3.2% increase in mIoU segmentation performance with 42% reduction in inference time.
Waymo Open Dataset provides a large, diverse, and synchronized LiDAR and camera dataset for autonomous driving research.
problem Limited diversity and scale in existing self-driving datasets hinder real-world problem alignment.
method Developed a new large-scale, high-quality, diverse dataset with synchronized LiDAR and camera data.
result The dataset is 15x more diverse than the largest existing dataset based on a proposed diversity metric.
DALES offers a large annotated aerial LiDAR dataset for 3D deep learning.
problem Lack of large-scale annotated aerial LiDAR datasets for deep learning.
method Collection and annotation of over half a billion hand-labeled points from an ALS scanner.
result DALES is the most extensive publicly available ALS data set with improved resolution and coverage.
Review of image compressive sensing algorithms for beginners.
problem Efficiently processing images with limited data.
method Comprehensive review of Total variation methods and other algorithms.
result Standardized comparison of algorithms for compressive sensing applications.
Voxel-FPN detects 3D objects from point clouds using raw LIDAR data.
problem 3D object detection in point cloud data for autonomous driving.
method Bottom-up voxel extraction and top-down feature fusion.
result Voxel-FPN outperforms baselines on the KITTI-3D benchmark.
CARML uses meta-learning to avoid obstacles in 2D vehicle navigation.
problem Collision avoidance in 2D vehicle navigation.
method Model-Agnostic Meta-Learning for multi-objective reinforcement learning.
result CARML outperforms a baseline TD3 solution in obstacle avoidance.
Expands sparse disparity cues from LiDAR to improve stereo matching performance.
problem Improving stereo estimation performance with limited dense data.
method Proposes a sparsity expansion technique to enhance local features from sparse disparity cues.
result Significantly boosts stereo algorithms with sparse cues, outperforming previous methods.
nuScenes dataset includes multimodal sensor data for autonomous vehicle training.
problem Training robust detection and tracking methods for autonomous vehicles.
method Presented the first multimodal dataset with 6 cameras, 5 radars, and 1 lidar, 360-degree field of view.
result 7x more annotations and 100x more images than KITTI dataset.
Proposes a new convolutional neural network for non-grid data.
problem Limited applicability of standard CNNs to non-grid structured data.
method Introduces Parametric Continuous Convolution (PCC) with learnable kernel functions.
result Significant improvement in point cloud segmentation and lidar motion estimation.
Study uses satellite and lidar data to map forest height and biomass in France.
problem Mapping forest resources and carbon in large areas.
method Machine learning approach using Sentinel-1, Sentinel-2, ALOS-2, and GEDI Lidar data.
result High-resolution maps of forest height and biomass produced with good accuracy.
A deep learning model improves pedestrian tracking accuracy.
problem Pedestrian tracking accuracy is low, especially with inertial measurement unit.
method Deep learning model using IMU and LIDAR data, attention mechanism.
result Preliminary results show improved accuracy.
3D object detection improved using energy-based models.
problem Accurate 3D object detection in cluttered environments from sparse LiDAR data.
method Designing a differentiable pooling operator for 3D bounding boxes integrated into a state-of-the-art 3D object detector.
result Our approach consistently outperforms the SA-SSD baseline across all 3DOD metrics on the KITTI dataset.
PRECOG predicts future interactions between AVs and other drivers.
problem Autonomous vehicles need to predict human drivers' intentions for safe road behavior.
method Probabilistic forecasting model trained on real and simulated data.
result Our model predicts future interactions more accurately than existing methods.
MFM improves generative model interpolations by learning approximate geodesics on data manifolds.
problem Straight interpolations fail to capture dynamics on data manifolds.
method Metric Flow Matching (MFM) learns approximate geodesics by minimizing kinetic energy of a data-induced Riemannian metric.
result MFM outperforms Euclidean baselines, achieving SOTA on single-cell trajectory prediction.
This paper solves the normalizability crisis in sequential inference by introducing bounded information geometry.
problem Structural failure in standard sequential inference architectures when dealing with extreme outliers.
method Non-parametric field actions and bounded information geometry to truncate infinite tails of spatial distributions.
result Empirical benchmarks across three domains show robust estimation without infinite-tailed distributional assumptions.
STM maps improve terrain perception for autonomous robots.
problem Perception of terrain for autonomous robots in general environments.
method Stochastic triangular mesh (STM) technique for 2.5-D surface mapping.
result STM maps are more accurate than standard elevation maps.
PointPillars improves object detection speed and accuracy in point clouds.
problem Encoding point clouds for efficient object detection.
method PointPillars uses PointNets to learn pillar representations of point clouds, combined with a lean downstream network.
result PointPillars outperforms previous encoders in both speed and accuracy.
The article develops a mathematical theory for uniformly distributing points on surfaces.
problem Creating representative point clouds on surfaces and higher-dimensional manifolds.
method Using Cauchy Crofton formula and its generalizations from Integral Geometry.
result A rigorous mathematical theory for point clouds on various manifolds.
A 1D-fully convolutional network classifies 3D point clouds efficiently.
problem Efficiently classifying 3D point clouds with reliable features.
method Directly consumes terrain-normalized points and spectral data, implicitly learning contextual features.
result Ranked second in ISPRS 3D Semantic Labeling Contest with 81.6% overall accuracy.
This research detects and identifies human-made objects in 3D point clouds using novel methods.
problem Detect and identify human-made objects in 3D point clouds.
method Ground filtering, local information extraction, clustering using Marked Point Fields (MPFs) and Hessian matrix.
result The proposed method outperforms previous techniques in detecting human-made objects.
Paper introduces deep learning for radar processing.
problem Lack of labeled radar data and need for expensive calibration.
method Uses deep learning on radar complex data, trains on calibration data, introduces radar augmentation.
result Superior performance on radar 4D detection task compared to classical methods.
New CNN approach reduces overconfidence in object classification predictions.
problem Overconfident predictions from deep models, especially SoftMax layer.
method Introduces CNN probabilistic approach using Logit layer for Bayesian inference.
result Proposed approach shows promising performance compared to SoftMax.
A new CNN method for point cloud data.
problem Processing 3D point cloud data efficiently.
method Creating a mapping of nearest neighbors and applying weights to spatial relationships.
result Achieves a CNN-like architecture for point clouds without extensive feature engineering.
DeepMoTIon mimics human navigation in crowds for safe robot movement.
problem Safe navigation of robots in human environments.
method Trains a neural network on pedestrian data to predict human velocity and navigate safely.
result DeepMoTIon outperforms other methods in human imitation and safety compliance.
Novel AI-IMU method accurately estimates vehicle position and orientation.
problem Accurate dead-reckoning for wheeled vehicles using only IMU.
method Kalman filter and deep neural networks for noise adaptation.
result Average 1.10% translational error, competitive with LiDAR or stereo vision methods.
Deep RL learns driving decisions from compact scene descriptions.
problem Learning consistent driving behavior from varying environments.
method Compact semantic state representation for reinforcement learning.
result Agent adapts behavior online without re-training.
Method infers depth from sparse points and camera motion.
problem Depth inference from limited sparse data.
method Constructs a planar scaffolding and uses predictive cross-modal criterion.
result State-of-the-art performance on depth completion benchmark.
LEAK learns from mistakes to improve point cloud segmentation.
problem Improving point cloud semantic segmentation performance.
method Coarse-to-fine clustering, class-conditional prototypical feature alignment, fairness weighting.
result State-of-the-art performances on different architectures, datasets, and tasks.
Adaptive Quantization Modules enable online continual compression of non-i.i.d data streams.
problem Learning to compress and store a dataset from a non-i.i.d data stream, only observing each sample once.
method Discrete auto-encoders and Adaptive Quantization Modules (AQM) to control compression ability.
result Significant gains on continual learning benchmarks with AQM replacing episodic memory.
A new method steers Gaussian distributions with minimal effort.
problem Steering high-dimensional Gaussian distributions efficiently.
method Sliced feedback controller using one-dimensional projections and averaging.
result The method steers Gaussian distributions to targets efficiently.
End-to-end autonomous driving perception learns latent features for better performance.
problem Current autonomous driving systems are complex and require human engineering.
method Sequential latent representation learning for end-to-end perception.
result End-to-end perception model solves detection, tracking, localization, and mapping problems.
A novel multi-stage clustering framework improves radar data processing for autonomous vehicles.
problem High sparsity and low dimensionality of radar data makes clustering challenging.
method First, filter out static background data. Then, apply a two-stage clustering approach: 1) low-dimensional clustering, 2) feature extraction from clusters.
result Clear benefits of the first two methods and cluster merging process under specific circumstances.
We apply variational inference to learn vehicle trajectory parameters from noisy data.
problem Learning parameters for vehicle trajectory estimation from noisy measurements.
method Gaussian variational inference with parameter learning in a motion and sensor model context.
result High-quality state estimates achieved even with outliers and false loop closures.
Paper develops a scalable distributed inference algorithm for sensor networks.
problem Efficient inference in intelligent sensor networks for location, tracking, and mapping.
method Distributed variational inference algorithm for continuous variables and large-scale data.
result Derives a separable lower bound for distributed variational inference with one-hop communication.
New algorithm preserves transport maps for better diffusion model training.
problem Training diffusion models with task-specific optimality structures.
method Generalized Schrödinger Bridge Matching (GSBM), inspired by conditional stochastic optimal control.
result GSBM better preserves transport maps, enabling stable convergence and improved scalability.