🌐 Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

Any4D: Unified Feed-Forward Metric 4D Reconstruction

Shenzhen MSU-BIT University PolarBear Team's Sentry Navigation Sim2Real Package for RoboMaster2025. QQ group: 932119307

ROS2-Gazebo simulation package leveraging Mid360 and FASTLIO for navigation.

A curated list of resources relevant to wheel-based SLAM

Fusing GNSS and wheel measurements based on FAST-LIO and IKFOM

A simulation platform for versatile Embodied AI research and developments.

A unified inference and post-training framework for accelerated video generation.

DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Driving

WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous Driving

123D: A Library for Driving Datasets

[ICRA'25] DoorBot: Closed-Loop Task Planning and Manipulation for Door Opening in the Wild with Haptic Feedback

GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.

SAM 3D Objects

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamics

Gazebo Simulator for RoboMaster University

Based on ROS2 and PCL libraries, used to convert pcd point cloud files into raster maps for navigation

[IROS2022] Robust Real-time LiDAR-inertial Initialization Method.

Lidar Localization and Mapping

RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO and designed for fine-tuning.

An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control inputs.

Official implementation of Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling

[AAAI 2025] Offical implementation of "DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input"

This project includes both EKF and ESKF for IMU attitude estimation. Additionally, a Butterworth low-pass filter is provided for noise attenuation. The package is built for both ROS and ROS 2 systems

Code for QuantVGGT: Quantized Visual Geometry Grounded Transformer

Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images