Stars
SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving
A robust optimization-based asynchronous Multi-camera-IMU state estimator [ICRA 2024, Workshop on Future of Construction, Best Research Award]
[ICRA 2025] MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry
Discrete-Time Hybrid Automata Learning: Legged Locomotion Meets Skateboarding
[RSS 2025] AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control
Official implementation for the paper "Full-Order Sampling-Based MPC for Torque-Level Locomotion Control via Diffusion-Style Annealing". DIAL-MPC is a novel sampling-based MPC framework for legged …
[ICRA 2025 Best Paper Award Finalist] Ground-Optimized 4D Radar-Inertial Odometry via Continuous Velocity Integration using Gaussian Process
GaRLIO: Gravity enhanced Radar-LiDAR-Inertial Odometry [ICRA 2025]
OpenHelix: An Open-source Dual-System VLA Model for Robotic Manipulation
Official implementations from the paper "Informed, Constrained, Aligned: A Field Analysis on Degeneracy-aware Point Cloud Registration in the Wild"
Topological Semantic Graph Memory for Image Goal Navigation (CoRL 2022 oral)
SORT3D, an LLM-based object-centric grounding and indoor navigation system employing a spatial reasoning toolbox and state of the art 2D VLMs for perception.
RGB-Only Gaussian Splatting SLAM for Unbounded Outdoor Scenes (ICRA 2025)
[RA-L 2024] GaussianGrasper: 3D Language Gaussian Splatting for Open-vocabulary Robotic Grasping
Official repository of "Open-Vocabulary Online Semantic Mapping for SLAM"
This repository contains the code for the ICRA 2025 Paper "DeepVL: Dynamics and Inertial Measurements-based Deep Velocity Learning for Underwater Odometry".
[T-RO 24] Swarm-LIO2: Decentralized, Efficient LiDAR-inertial Odometry for UAV Swarms
Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots
Official repository for holistic fusion.
An Adaptive Exploration Strategy for Zero-Shot Object Navigation with Target-centric Semantic Fusion
RMPs on multi-resolution occupancy maps for efficient reactive collision avoidance
ICRA2025: OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding
Enhancing Autonomous Driving Systems with On-Board Deployed Large Language Models
A tightly coupled deep learning framework for GNSS
[CVPR 2024] Real-Time Open-Vocabulary Object Detection
A highly robust and accurate LiDAR-inertial odometry package
Dynamic Initialization for LiDAR-inertial SLAM
ROMAN is a view-invariant global localization method that maps open-set objects and uses the geometry, shape, and semantics of objects to find the transformation between a current pose and previous…