Mobile Robots Autonomous Exploration with Reinforcement Learning

2020-12-14 · CUHK Course IERG5350 2020 12 · Haojie Shi, LI ANG

Reinforcement Learning, a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives while interacting with a complex and uncertain environment. And it has quite a few applications in playing game or controlling a robot after exploration and exploitation. Our project is aimed at designing an efficient robot autonomous exploration algorithm based on reinforcement learning. Our work is based on the HouseExpo dataset and we developed reinforcement learning algorithm on it, showing that the robot can efficiently explore uncertain environments with a smart behavior. Our work is based on Double DQN with proportional prioritization[7], and we improve the algorithm by encoding history observation, adding global explored map and designing external reward via Artificial Potential Field.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…

DQN A DQN, or Deep Q-Network, approximates a state-value function in a Q-Learning framework with a neural network. In the Atari…

Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…

Double Q-learning Double Q-learning is an off-policy reinforcement learning algorithm that utilises double estimation to counteract overestimation problems with traditional Q-learning. The…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Double DQN 설명 없음

Towards Cognitive Exploration through Deep Reinforcement Learning for Mobile Robots

2016-10-06 · Lei Tai, Ming Liu

Exploration in an unknown environment is the core functionality for mobile robots. Learning-based exploration methods, including convolutional neural networks, provide excellent strategies without human-designed logic fo…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Mobile Robots Exploration via Deep Reinforcement Learning

2020-12-14 · CUHK Course IERG5350 2020 12 · Han Ma, Peng Xu

n this paper, we try to solve the mobile robot exploration problem in a 2D indoor office environment by deep reinforcement learning. Finally, we find that PPO with Convolutional Neural Network (CNN) and Dense layers con…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Self-Learning Exploration and Mapping for Mobile Robots via Deep Reinforcement Learning

2019-01-06 · Fanfei Chen, Shi Bai, Tixiao Shan, Brendan Englot

Mapping and exploration of a priori unknown environments is a crucial capability for mobile robot autonomy. A state-of-the-art approach for mobile robots equipped with range sensors uses mutual information as the basis f…

Computational Efficiency Deep Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)+1

Curiosity-driven Exploration for Mapless Navigation with Deep Reinforcement Learning

2018-04-02 · Oleksii Zhelo, Jingwei Zhang, Lei Tai, Ming Liu 외

This paper investigates exploration strategies of Deep Reinforcement Learning (DRL) methods to learn navigation policies for mobile robots. In particular, we augment the normal external reward for training DRL algorithms…

Deep Reinforcement Learning Navigate reinforcement-learning Reinforcement Learning+1

Autonomous Legged Mobile Manipulation for Lunar Surface Operations via Constrained Reinforcement Learning

2025-10-14 · Alvaro Belmonte-Baeza, Miguel Cazorla, Gabriel J. García, Carlos J. Pérez-Del-Pulgar 외 arxiv

Robotics plays a pivotal role in planetary science and exploration, where autonomous and reliable systems are crucial due to the risks and challenges inherent to space environments. The establishment of permanent lunar b…

Reinforcement Learning Collision Avoidance Pose Tracking