Motion prediction and trajectory forecasting for autonomous driving — predicting future positions of vehicles, pedestrians and cyclists in complex traffic scenarios.
In this work, we introduce a structured multi-level visual perturbation framework to analyze visual-behavior dependency in VLA-based driving models systematically.
Engineering 5.0 · Research 7.0 · Business 5.0
In this paper, we present SparseWorld, a lightweight world model that focuses on predicting only the critical layout of the scene, enabling efficient future forecasting for end-to-end driving systems.
Engineering 7.5 · Research 8.0 · Business 5.0
To address these challenges, this paper proposes an Improved Driving Risk Field-based Multi-objective Trajectory Optimization (IDRF-MTO) method.
Engineering 5.0 · Research 7.0 · Business 5.0
In this paper, we propose DiffRefiner, a novel two-stage trajectory prediction framework.
Engineering 5.0 · Research 8.0 · Business 5.0
An autonomous driving research paper: Gaussian-Based World Model: Gaussian Priors for Voxel-Based Occupancy Prediction and Future Motion Prediction.
Engineering 5.0 · Research 7.0 · Business 5.0
Autonomous driving technology is advancing quickly.
Engineering 5.5 · Research 7.0 · Business 5.5
In this paper, a novel lightweight bird’s-eye view (BEV) architecture is introduced, which fully utilizes the camera data and aims to improve the efficiency of perspective conversion and feature representation.
Engineering 6.0 · Research 8.0 · Business 5.0
Our method is integrated into a perspective-view detection model that consumes sensor data from multiple LiDARs, radars and cameras.
Engineering 5.0 · Research 8.0 · Business 5.0
This paper proposes BETAV, a novel framework that addresses the persistent challenges of low 3D perception accuracy and suboptimal trajectory smoothness in autonomous driving systems through unified BEV-Transformer encoding and Bézier-optimized planning.
Engineering 5.5 · Research 8.0 · Business 5.0
We propose a novel POD framework, the core idea of which is to generate a virtual future point using a ray casting mechanism, create virtual two-frame point clouds with the current and virtual future frames, and encode these two-frame voxel features with a sparse 4D encoder.
Engineering 5.0 · Research 8.0 · Business 5.0
To tackle this issue, we propose ORION, a hOlistic E2E autonomous dRiving framework by vIsion-language instructed actiON generation.
Engineering 5.5 · Research 8.5 · Business 5.0
This paper proposes a multimodal vehicle trajectory prediction model based on visual perception information (VP-MTP).
Engineering 5.5 · Research 7.0 · Business 6.0
The primary input for motion planning, which permits safe autonomous driving on public roads, is an accurate trajectory prediction of nearby road users.
Engineering 5.0 · Research 7.0 · Business 5.0
To this end, we propose a coarse-to-fine Transformer for multimodal trajectory prediction, i.e., Pioformer, which explicitly extracts the post-interaction features to enhance the prediction accuracy.
Engineering 5.0 · Research 7.0 · Business 5.0
In this paper, we present a purely vision-based transformer model for end-to-end automatic parking, trained using expert trajectories.
Engineering 5.5 · Research 8.0 · Business 5.0
Recent breakthroughs in autonomous driving have been propelled by advances in robust world modeling, fundamentally transforming how vehicles interpret dynamic scenes and execute safe decision-making.
Engineering 5.5 · Research 7.0 · Business 6.0
To overcome these limitations, we propose a scene-centric transformer architecture with a cluster-based training approach, capturing pedestrian dynamics through combined probability distributions.
Engineering 5.5 · Research 8.0 · Business 5.5
To address this limitation, this paper proposes a bidirectional interaction network (DyMap) that takes into account the bilateral constraints of the map on the agents and the impact of the agents on the map, using a unique bidirectional attention module.
Engineering 5.0 · Research 8.0 · Business 5.0
In this paper, we present a novel framework termed BEV-TP, a visual context-guided center-based transformer network for joint 3D perception and trajectory prediction.
Engineering 6.0 · Research 8.0 · Business 5.0
This paper presents Senna, an autonomous driving system combining an LVLM (Senna-VLM) with an end-to-end model (Senna-E2E).
Engineering 7.5 · Research 8.0 · Business 5.0