Researchers have introduced LCS-Net, a lightweight collaborative neural network that executes simultaneous real-time object detection and semantic segmentation for autonomous ...
Researchers developed ChatMPC, a simulation framework that translates natural language driving instructions into dynamic model predictive control parameters.
A new hybrid review and original research article in Discover Vehicles presents a unified AI framework for intelligent sustainable mobility, ...
Researchers developed a compact road-object detector coupling high-resolution feature alignment and quality-aware assignment to improve small-object detection accuracy on benchmark ...
Computer scientists propose a Digital Reality framework that uses parametric real-world models and sensor simulation to generate balanced synthetic training ...
Researchers developed a bird's-eye-view architecture combining collaborative distillation and multi-domain attention to improve multimodal 3D object detection in complex driving ...
A diagnostic evaluation of the frozen SparseDriveV2 planner reveals that safety failures under camera perturbations concentrate in narrow operational cells, ...
A transformer-based middle-fusion framework called T-3MS Fusion achieves 74.9% NDS and 72.8% mAP on nuScenes 3D object detection using a ...
A landmark head-to-head study finds that a YOLOv3 image detector outperforms point-cloud-native and modular machine learning methods for detecting moving ...
Machine learning models that power highly automated driving, medical systems, and aviation are only as good as the data and ...
A new conditional diffusion framework called CDJMP predicts multi-agent vehicle trajectories with state-of-the-art accuracy while cutting inference time to under ...
A CNN running on a host PC with Arduino-based servo actuation predicted steering angles with a validation MAE of 0.093 ...
Automated vehicles promise safer highways, but the hardest moments are often the simplest ones: a car ahead braking suddenly, a ...
A simulation study reports that a distributed imitation learning framework with adversarial perturbation training cut path tracking error to 0.18 ...
A new open access survey in Artificial Intelligence Review organises open-ended visual segmentation into three research directions and maps the ...
Researchers in Hefei have combined a compact Mie-scattering LiDAR with an autonomous electric vehicle to continuously profile aerosols in three ...
Researchers have developed tandem PbSe colloidal quantum-dot photodiodes that combine built-in visible-light suppression with nanosecond response, enabling centimeter-resolution 1550 nm ...
A conceptual study maps three complementary runtime monitors onto ISO 21448 safety activities for AI-based autonomous-driving perception systems, but does ...
GraphLane combined three-frame context, uncertainty-weighted graph reasoning and road-geometry constraints to improve lane-coordinate estimates in a CULane study, although its ...
A new RGB-depth salient object detection framework combines multi-level attention-based feature fusion with a WebP compression and denoising defense that ...
