rongrong1314's starred repositories
spinningup
An educational resource to help anyone learn deep reinforcement learning.
PathPlanning
Common used path planning algorithms with animations.
traversability_mapping
Bayesian Generalized Kernel Inference for Terrain Traversability Mapping
ros_autonomous_slam
ROS package which uses the Navigation Stack to autonomously explore an unknown environment with help of GMAPPING and constructs a map of the explored environment. Finally, a path planning algorithm from the Navigation stack is used in the newly generated map to reach the goal. The Gazebo simulator is used for the simulation of the Turtlebot3 Waffle Pi robot. Various algorithms have been integrated for Autonomously exploring the region and constructing the map with help of the 360-degree Lidar sensor. Different environments can be swapped within launch files to generate a map of the environment.
RelationalGraphLearning
[IROS20] Relational graph learning for crowd navigation
RL-Coverage-Planner
A Reinforcement Learning (RL) agent for Coverage Path Planning.
ergodic_exploration
Robot agnostic information theoretic exploration strategy
Autonomous-Systems
Navigation, State estimation (KF & EKF) and SLAM.
sample-efficient-bayesian-rl
Source for the sample efficient tabular RL submission to the 2019 NIPS workshop on Biological and Artificial RL
GNN-MCTS-TSP
A Graph Neural Network Assisted Monte Carlo Tree Search Approach to Traveling Salesman Problem
uuv_Matlab
This directory simulates UUV dynamics and control purely in the Matlab programming language.
rl_nav
This is the accompannying code for the paper "SLAM-Safe Planner: Preventing Monocular SLAM Failure using Reinforcement Learning" and "Data driven strategies for Active Monocular SLAM using Inverse Reinforcement Learning" To run the code, download this repository and a modified version of PTAM from https://github.com/souljaboy764/ethzasl_ptam/ to your catkin workspace and compile it. For running the agent on maps: In the turtlebot_gazebo.launch change the argument "world_file" to the corresponding map world file (map1.world, map2.world, map3.world, corridor.world or rooms.world) and set the corresponding initial positions in joystick.launch Open 4 new terminals Terminal 1: roslaunch rl_nav turtlebot_gazebo.launch Terminal 2: roslaunch ptam ptam.launch Terminal 3: roslaunch rl_nav joystick.launch Terminal 4: rosrun rviz rviz -d `rospack find rl_nav`/ptam.rviz Press the "start" button on the xbox joystick or publish a message of type "std_msgs/Empty" to /rl/init Once PTAM is initialized, give an intermediate point using the "2D Pose Estimate" button in rviz and give the goal location using "2D Nav Goal" For traning the agent, In the turtlebot_gazebo.launch change the argument "world_file" to training.world Open 3 new terminals Terminal 1: roslaunch rl_nav turtlebot_gazebo.launch Terminal 2: roslaunch ptam ptam.launch Terminal 3: roslaunch rl_nav train.launch Press the "start" button on the xbox joystick or publish a message of type "std_msgs/Empty" to /rl/init Once PTAM is initialized, press the "A" button on the xbox controller to start training. For testing the agent on steps to breakage, In the turtlebot_gazebo.launch change the argument "world_file" to training.world Open 3 new terminals Terminal 1: roslaunch rl_nav turtlebot_gazebo.launch Terminal 2: roslaunch ptam ptam.launch Terminal 3: roslaunch rl_nav test.launch Press the "start" button on the xbox joystick or publish a message of type "std_msgs/Empty" to /rl/init Once PTAM is initialized, press the "A" button on the xbox controller to start testing. For running the IRL agent, just change the weights in qMatData.txt to the weights in qMatData_SGD.txt and run any of the above. For training the IRL agent, run IRLAgent.py with the data from https://www.dropbox.com/s/qnp8rs92kbmqz1e/qTrain.txt?dl=0 in the same folder as IRLAgent.py, which will save the final Q values in qRegressor.pkl
iwagpr2017-model
This model was created using gprMax. It is a 3D, near-surface example of a fictional but realistic landmine detection environment.
Informative-Path-Planning
The Informative Path Planning problem is to find some path that maximizes information gain subject to a set of constraints. In this project we are trying to learn some arbitrary 2D field (a temperature or topography map).
Empowerment-driven-Exploration
Tensorflow implementation for Empowerment driven Exploration using Mutual Information Estimation
Applied-Linear-Systems-AUV-Project-Part-1
1st Part of Semester long AUV Controls Project
automapping_matlab
Part of BSc thesis. Autonomous exploration and mapping using built-in MATLAB's toolboxes.
desistek_saga
Vehicle model description and configuration files for the Desistek SAGA ROV underwater vehicle.
xgb_vegetation_mapping
Accurate mapping of vegetation is a premise for conserving, managing, and sustainably using vegetation resources, especially at conditions of intensive human activities and accelerating global changes. However, it is still challenging today to produce high-resolution multiclass vegetation map in high accuracy, due to the incapacity of traditional mapping technology in distinguishing mosaic vegetation classes with subtle differences and the paucity of fieldwork data. This study, using extensive features and abundant vegetation survey data, created a workflow by adopting a promising classifier, eXtreme Gradient Boosting (XGBoost), to produce accurate vegetation maps of two strikingly different cases: Dzungarian Basin in China and New Zealand. For Dzungarian Basin, a vegetation map with 7 vegetation types, 17 subtypes, and 43 associations was produced, with an overall accuracy of 0.907, 0.801, and 0.748, respectively. For New Zealand, a map of 10 habitats and a map of 41 vegetation classes were produced, at an overall accuracy of 0.946, 0.703, respectively. The workflow incorporating simplified field survey procedures outperformed conventional field surveying and remote sensing based methods in terms of accuracy as well as efficiency. Besides, it opens the possibility of building large-scale, high-resolution, and timely vegetation monitoring platforms for most terrestrial ecosystems worldwide with the aid of Google Earth Engine and citizen science programs.
AutonomousMobileRobotics
University of Lincoln Autonomous Mobile Robotics Submission
RL-Project
This is reinforcement learning project entitled Autonomous Exploration Under Uncertainty via Deep Reinforcement Learning on Graphs
OceanMesh2D
A fast two-dimensional triangular mesh generator written in MATLAB designed specifically for coastal models that solve shallow-water equations.
iros-2019-workshop
Website for iros workshop on sampling robots