Highd Dataset
PulseAugur coverage of Highd Dataset — every cluster mentioning Highd Dataset across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New X-TRACK variants enhance autonomous driving trajectory prediction with uncertainty modeling
Researchers have developed new uncertainty-aware extensions for the X-TRACK framework, specifically X-TRACK-DE and X-TRACK-MCD, to improve trajectory prediction for autonomous driving. These methods explicitly model and…
-
New method generates extreme scenarios for autonomous vehicle testing
Researchers have developed a novel method for generating challenging scenarios for autonomous vehicle (AV) testing. This approach quantifies the extremity of a scenario by its percentile within the conditional distribut…
-
New AI model SSP-DMGTimeNet improves vehicle platoon trajectory prediction
Researchers have developed SSP-DMGTimeNet, a novel physics-constrained learning framework designed to improve spatiotemporal trajectory prediction for vehicle platoons. This model integrates multi-scale temporal represe…
-
New DNC-IMM method enhances lane-change intention recognition for autonomous driving
Researchers have developed a new method called Dual Neural-Calibrated Interacting Multiple Model (DNC-IMM) for recognizing lane-change intentions in autonomous driving systems. This approach uses a neural network to ada…
-
New research explores reinforcement learning advancements across multiple domains · 10 sources tracked
Multiple research papers published on arXiv explore advancements in reinforcement learning (RL) and its applications. One study focuses on improving the interpretability of RL policies through decision-tree pruning, dem…
-
New framework predicts multi-vehicle lane changes using dynamic scene graphs
Researchers have developed a new framework called DSiGAT, which uses a dynamic scene graph attention mechanism to predict the lane-change intentions and future trajectories of multiple interacting vehicles. This approac…
-
New module enhances autonomous driving trajectory prediction with dynamic risk analysis
Researchers have developed a new module for autonomous driving systems that dynamically profiles risk horizons in trajectory prediction. This module uses a continuous potential field model to assess the spatial-temporal…
-
AI predicts lane changes using physics-informed temporal fusion
Researchers have developed a new framework for predicting lane-change intentions in autonomous driving systems. This approach, termed Evolutionary Physics-Informed Temporal Fusion, integrates temporal descriptors derive…
-
New X-TRACK model uses xLSTM and physics for realistic vehicle trajectory prediction
Researchers have developed X-TRACK, a novel trajectory prediction model for autonomous driving that leverages the extended Long Short-Term Memory (xLSTM) architecture. This new model explicitly incorporates vehicle moti…