fred159 Goto Github PK

hdl_graph_slam

3D LIDAR-based Graph SLAM

husky

Common packages for the Clearpath Husky

jetson-inference

Guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.

kitti2bag

Convert KITTI dataset to ROS bag file the easy way!

lee-slam-source

SLAM 开发学习资源与经验分享

librealsense

Intel® RealSense™ SDK

lidar2rosbag_kitti

A simple way to convert KITTI LiDAR data to rosbag.

loam_velodyne

Laser Odometry and Mapping (Loam) is a realtime method for state estimation and mapping using a 3D lidar.

matlab-projects

Various MATLAB projects

mind-map-github

My open mind map

moveit_tutorials

A sphinx-based centralized documentation repo for MoveIt

my-udacity-project1-lane_extraction

Udacity project1 -Finding Lane Lines on the Road

my-udacity-project2-traffic-sign-recognition

German Traffic Sign Recognition

my-udacity-project3-clone-driving-behavior

Udacity selfdriving car project 3-behavior cloning using deep learning.

my-udacity-project4-advanced-lane-finding

my-udacity-project5-vehicle-detection-and-tracking

openpilot

openpilot is an open source driver assistance system. openpilot performs the functions of Automated Lane Centering and Adaptive Cruise Control for over 150 supported car makes and models.

probabilistic_robotics

solution of exercises of the book "probabilistic robotics"

pykitti

Python tools for working with KITTI data.

realsense

Intel(R) RealSense(TM) ROS Wrapper for D400 series and SR300 Camera

resources

Some resources from internet that is opened.

robond-deeprl-project

robond-kinematics-project

robond-kinematics-project-1

Pick and Place project for RoboND Term 1

robond-rover-project

Project repository for the Unity rover search and sample return project.

robond-slamlab

Solution for the SLAM Lab

robotics-p4-pid_controller

robotics-term2-p1-robot-inference

Object detection is a priority task that helps manipulator and ground vehicle to complete their missions. Object detection should provide object position and object class for implementing specify operation. Especially, when a robot want to do a operation with a tool, robot needs to know what the kind of the tool is. So an automated tool recognition solution is needed. In this paper, a method based on convolutional neural network is presented. Using supervised learning on the NVIDIA deep learning platform which name is DIGITS. The hardware to gathering the data is a depth camera d435 from INTEL. The common deep learning layer structure used in this paper is ’GoogLeNet’ and ’Alexnet’. With the GPU acceleration parallel computing service which is provided from Udacity reduces a lot of time. With this method, algorithm can gives a reliable recognition result with only RGB input. The result is only verified in single picture level.

robotics-term2-p4-arm-reinforcement-learning

Robotics term2 project4 arm reinforcement learning project

roboticsnd-follow-me-deeplearning