Browse curated autonomous driving papers on end-to-end driving, BEV perception, 3D object detection, motion prediction, path planning, ADAS, Tesla FSD, Waymo, and self-driving foundation models.
To address these limitations, we propose InVDriver, a novel vectorized query-based system that systematically models intra-instance spatial dependencies through masked self-attention layers, thereby enhancing planning accuracy and trajectory smoothness.
Engineering 6.5 · Research 8.0 · Business 6.0
This study presents a lightweight deep learning model developed for DPU-accelerated systems.
Engineering 5.5 · Research 7.0 · Business 6.5
To that end, we propose a learning-from-rendering rainy image synthesizer, which combines the benefits of the realism of rendering-based methods and the controllability of learning-based methods.
Engineering 7.0 · Research 7.0 · Business 5.5
Therefore, we propose OrchardDepth, which fills the gap in the estimation of the metric depth of the monocular camera in the orchard/vineyard environment.
Engineering 5.0 · Research 7.0 · Business 5.0
To address these challenges, we propose OG-Gaussian, a novel approach that replaces LiDAR point clouds with Occupancy Grids (OGs) generated from surround-view camera images using Occupancy Prediction Network (ONet).
Engineering 5.5 · Research 8.0 · Business 6.0
To address these challenges, we developed a ViT-based DRL model and evaluated its performance through extensive training in the MetaDrive simulator and testing in the high-fidelity AirSim simulator.
Engineering 5.0 · Research 7.0 · Business 5.0
We propose Sce2DriveX, a human-like chain-of-thought (CoT) driving reasoning MLLM framework, designed to achieve progressive learning from multi-view scene understanding to behavior analysis, motion planning, and vehicle control driving process.
Engineering 5.5 · Research 8.5 · Business 5.0
The ability to accurately predict future road conditions is essential for the advancement of autonomous driving systems.
Engineering 5.5 · Research 7.0 · Business 5.5
Camera and LiDAR sensors play a crucial role in vehicle perception systems, enabling accurate detection of obstacles and other vehicles in autonomous driving technologies.
Engineering 5.0 · Research 8.0 · Business 5.0
To overcome this challenge, we develop a virtual dataset, designated as the Intersection Dataset, which includes extensive annotations of vehicles and pedestrians in various traffic scenarios.
Engineering 5.0 · Research 7.0 · Business 5.0
Developing reliable autonomous systems requires road lane segmentation models that can mimic human perception without the associated errors.
Engineering 5.5 · Research 7.0 · Business 5.5
To address this challenge, we introduce SimBEV.
Engineering 5.0 · Research 7.0 · Business 5.0
This paper presents an evaluation method to compare colored point clouds, a common fused data type, among two LiDAR–camera fusion systems and a stereo camera setup.
Engineering 5.0 · Research 7.0 · Business 5.0
In this paper, we introduce LinkOcc, a sparse-queries approach incorporating an efficient temporal association mechanism for 3D semantic occupancy prediction.
Engineering 5.5 · Research 8.0 · Business 5.5
As autonomous driving technology progresses, LiDAR-based 3D object detection has emerged as a fundamental element of environmental perception systems.
Engineering 5.0 · Research 7.0 · Business 5.0
To address these, we propose the sparse temporal fusion network (STFNet), which leverages multiframe historical information to improve 3D object detection accuracy.
Engineering 5.5 · Research 8.0 · Business 5.0
In this paper, a curbed fake point collector (CFPC), which addresses the three issues caused by pseudo points, is proposed to support 3D object detection for autonomous vehicles.
Engineering 5.0 · Research 7.0 · Business 5.0
Then, we propose the dense fusion with multi-scale masked attention (DFMMA), using multi-scale feature masks from bird's-eye-view (BEV)-level multimodal features to improve performance for small object feature perception.
Engineering 5.0 · Research 7.0 · Business 5.0
To overcome the limitations of single-sensor perception, this paper proposes the BSM-NET method, a multi-bandwidth, multi-scale, multi-modal fusion approach for 4D radar and LiDAR.
Engineering 5.0 · Research 8.0 · Business 5.0
An autonomous driving research paper: AFLaneNet: an attention-fused instance segmentation network for real-time lane detection.
Engineering 5.0 · Research 7.0 · Business 5.0