The First Research

Robot Platforms

SLAM / Localization / Navigation Algorithms

  • DynaVINS: A Visual-Inertial SLAM for Dynamic Environments
  • AdaLIO: Adaptive LiDAR Inertial Odometry
  • STEPState Estimator for Legged Robots Using a Preintegrated Foot Velocity Factor
  • UV-SLAMUnconstrained Line-based SLAM Using Vanishing Points for Structural Mapping
  • ALVIOAdaptive Line Visual Inertial Odometry
  • HG-SLAM: Hierarchical Graph-based SLAM
  • G2P-SLAMGeneralized Grouping and Pruning-Based RGB-D SLAM Framework for Mobile Robots in Low-Dynamic Environments
  • GP-SLAMGrouping Nodes and Puning Constraints SLAM
  • DV-SLAMDual-sensor-based Vector-field SLAM
  • MU-SLAMMagnetic-field-based Underground SLAM
  • BRMLocalization: Building Ratio Map Localization for UAVs
  • NR-UIONLOS-Robust UWB-Inertial Odometry based on IMM and NLOS Factor Estimation
  • GP-ICPGround Plane ICP for Mobile Robots


 

  • Peacock Exploration: A Lightweight Exploration for UAV using Control-Efficient Trajectory
  • TRAVEL: Traversable Ground and Above-Ground Object Segmentation Using Graph Representation of 3D LiDAR Scans
  • MLCPPMulti-Layer Coverage Path Planner
  • eARC-Theta*extended Angular-Rate-Constrained Theta*

AI / ML Algorithms

  • DreamWaQ: Learning Robust Quadrupedal Locomotion With Implicit Terrain Imagination via Deep Reinforcement Learning
  • Struct-MDCMesh-Refined Unsupervised Depth Completion Leveraging Structural Regularities from Visual SLAM 
  • MSDPNMulti-Stage Depth Prediction Neural Network
  • Retro-RL: Reinforcing Nominal Controller with Deep Reinforcement Learning for Tilting-Rotor Drones
  • Patchwork: Concentric Zone-based Region-wise Ground Segmentation with Ground Likelihood Estimation Using a 3D LiDAR Sensor
  • ERASOR: Egocentric Ratio of Pseudo Occupancy-based Dynamic Object Removal for Static 3D Point Cloud Map Building
  • RONetRange-Only Network