Argoverse 2
PulseAugur coverage of Argoverse 2 — every cluster mentioning Argoverse 2 across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
CorrelationFlow: Training-Free LiDAR Scene Flow Estimation Method Unveiled
Researchers have introduced CorrelationFlow, a novel training-free geometric approach for LiDAR scene flow estimation. This method diverges from current dominant architectures by utilizing connected-component labeling a…
-
New metrics evaluate 3D perception errors in autonomous driving
Researchers have developed new metrics to evaluate the criticality of 3D perception errors in autonomous driving systems. These metrics, False Speed Reduction (FSR) and Maximum Deceleration Rate (MDR), quantify the impa…
-
Geographic diversity in training data boosts AI driving model generalization
Researchers have found that geographic diversity in training data is more crucial than sheer volume for improving the cross-domain generalization of self-supervised latent world models used in autonomous driving. A stud…
-
LLM-powered agents automate biological trajectory analysis, new methods boost prediction accuracy · 6 sources tracked
Researchers have developed SpaCellAgent, a novel LLM-based multi-agent framework designed to automate trajectory inference and analysis in spatial and single-cell transcriptomics. This framework aims to reduce the manua…
-
MapDreamer generates lane-level maps from aerial images using diffusion models
Researchers have developed MapDreamer, a novel generative diffusion model capable of synthesizing lane-level vector maps directly from single aerial images. This model utilizes a compact latent representation for lane c…
-
New classifier identifies four distinct urban vehicle deceleration behaviors
Researchers have developed a new classifier to identify distinct modes of urban vehicle deceleration behavior. By analyzing over a thousand deceleration events from the Argoverse 2 dataset, they identified four stable m…
-
New framework decouples trajectory forecasting from benchmark metrics
Researchers have proposed a new framework for trajectory forecasting in autonomous driving that decouples the training objective from specific benchmark metrics. This approach, called Trajectory Distribution Evaluation …
-
New LAMP framework improves autonomous driving trajectory prediction
Researchers have developed LAMP (Lane-Aligned Motion Primitives), a new framework for trajectory prediction in autonomous driving. This system addresses a key limitation of current predictors by ensuring that predicted …
-
New ASP Method Computes Constrained Movement Trajectories
Researchers have developed a novel method for computing movement trajectories of objects in complex environments. This approach utilizes answer set programming (ASP) to generate constrained branching trajectory modes, w…
-
Class-Incremental Motion Forecasting for Autonomous Vehicles Unveiled
Researchers have introduced a novel approach to motion forecasting for autonomous vehicles called class-incremental motion forecasting. This method addresses the challenge of new object classes emerging over time and im…
-
New Neuro-Symbolic Framework Enhances Autonomous Vehicle Motion Prediction
Researchers have developed Trajectory Compliance-Shaping (TraCS), a novel neuro-symbolic framework designed to enhance motion prediction for autonomous navigation. This system integrates interpretable first-order logic …
-
MapRF uses NeRF-guided self-training for weakly supervised HD map construction
Researchers have developed MapRF, a novel framework for constructing high-definition (HD) maps for autonomous driving systems using only 2D image labels. This weakly supervised approach leverages Neural Radiance Fields …
-
Researchers develop new motion forecasting framework grounded in interpretable motion bank
Researchers have developed a new framework for motion forecasting that enhances interpretability by grounding predictions in a structured embedding space of physically realizable trajectories, termed a "motion bank." Th…
-
RetroMotion model forecasts agent motion with retrocausal transformers
Researchers have developed RetroMotion, a novel approach to motion forecasting for road users that decomposes complex joint trajectory predictions into simpler marginal and pairwise distributions. This method utilizes a…
-
New framework uses prior map data to improve camera-based 3D object detection
Researchers have developed a novel framework called DualViewMapDet for camera-only 3D object detection and tracking, particularly beneficial for autonomous driving systems that lack LiDAR sensors. This method leverages …
-
OpenVO framework enhances visual odometry with temporal awareness and geometric priors
Researchers have developed OpenVO, a new framework for open-world visual odometry that accounts for temporal dynamics and works with uncalibrated cameras. Unlike previous methods that assume fixed observation frequencie…