bhushankorpe / Obstacle-dodging-car-using-Q-learning
In this project, the robot car presents a behavioral approach to collision avoidance, where a mobile robot needs to avoid collisions with stationary obstacles and the wall enclosing its environment. The robot uses Reinforcement Learning technique to learn actions corresponding to states in which the robot is. The states are defined based on the …
☆12Updated 7 years ago
Related projects ⓘ
Alternatives and complementary repositories for Obstacle-dodging-car-using-Q-learning
- [ICRA2020] Path Planning in Dynamic Environments using Generative RNNs and Monte Carlo Tree Search☆26Updated 2 years ago
- Multi-Robot Collision Avoidance using Reinforcement Learning☆13Updated 6 years ago
- Planner for Markov Decision Processes with Temporal Goals☆20Updated 2 years ago
- Motion planning environment for Sampling-based Planners☆30Updated 10 months ago
- Implementation of Artificial Potential Field (Reactive Method of Motion Planing)☆59Updated 7 years ago
- Socially normative mobile robot navigation☆27Updated 8 years ago
- Learning human-aware robot navigation behavior from demonstrations via Maximum Entropy Inverse Reinforcement Learning.☆42Updated 4 years ago
- Implementation of an iterative linear quadratic regular (iLQR) on inverted pendulum, box quadratic programming (box-QP) is used to deal w…☆10Updated 6 years ago
- Master Thesis - Transfer Learning for Mapless Quadrotor Navigation Using Recurrent Neural Network☆16Updated 3 years ago
- ☆15Updated 3 years ago
- Using RL based controller for steering function of RRT. And a network learns to perform motion planning☆29Updated 4 years ago
- Python demo for the paper "Pareto Monte Carlo Tree Search for Multi-Objective Informative Planning".☆28Updated 2 years ago
- We use reachability to ensure the safety of a decision agent acting on a dynamic system in real-time. We compute the Forward Reachable Se…☆31Updated 3 years ago
- Quadrotor control using deep reinforcement learning☆15Updated 6 years ago
- Simultaneous task allocation and motion scheduling (STAAMS) solver based on constraint programming and optimization, implemented for the …☆17Updated 5 years ago
- ☆30Updated 3 years ago
- Reactive crowd simulator used in the IROS 2020 paper: "L2B: Learning to Balance the Safety-Efficiency Trade-off in Interactive Crowd-awar…☆20Updated 3 years ago
- ☆10Updated 3 years ago
- Implementation of RRT, RRT-connect, RRT*, and PRM in c++☆9Updated 7 years ago
- Simulation of multi-robot path tracking in Gazebo☆19Updated 5 years ago
- Using ROS to connect Stage simulator with Google DeepMind (DQN) project for Deep Reinforcement Learning in Robotic !☆27Updated 7 years ago
- This is an unofficial python implement of nonlinear model predictive control with control Lyapunov functions and control barrier function…☆30Updated 3 years ago
- Repository containing RL environment, model and trainer for GNN demo for ICRA 2022 paper "A Framework for Real-World Multi-Robot Systems\…☆33Updated 2 years ago
- Belief Space Motion Planning Using iLQG☆32Updated 7 years ago
- 学习一些经典的motion_planning方法以及学界motion_planning的新进展☆17Updated 5 years ago
- Reinforcement Learning-based Mobile Robot Navigation☆25Updated 7 years ago
- This is a library for some of sampling-based motion planning algorithms implemented in MATLAB.☆35Updated 5 years ago
- This repository contains the code for our paper on Dynamic Mirror Descent based MPC for Model-Free RL☆22Updated 2 years ago
- Code for path planning in dynamic environments with adaptive dimensionality☆28Updated 3 years ago
- Thrid-party safety-gym safe exploration environments for autonomous driving. Also environment used for IROS 2021 paper: Model-based Const…☆29Updated 3 years ago