The <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" altimg="si9.gif" display="inline" overflow="scroll"><mml:mi>Q</mml:mi></mml:math>-learning obstacle avoidance algorithm based on EKF-SLAM for NAO autonomous walking under unknown environments

Wen, Shuhuan; Chen, Xiao; Ma, Chunli; Lam, Hak‐Keung; Hua, Shaoyang

doi:10.1016/j.robot.2015.04.003

Cited by 46 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RL has been used for navigation robot research [8,9]. In the RoboCup Standard Platform League (SPL), Kenzo Lobos-Tsunekawa et al [8] implemented a mapless visual navigation system in which robots used RL-generated paths without map information.…”

Section: Previous Workmentioning

confidence: 99%

“…Reinforcement learning (RL) [1][2][3][4][5], an artificial intelligence technique, is commonly applied in robot action learning. Several prior studies on RL have been conducted to develop behavior-imitation robots [6,7] and robot navigation [8,9]. As AI robots undertake human tasks, individuals have more time for leisure and self-development; as a result, many people require robots to work instead of humans.…”

Section: Introductionmentioning

confidence: 99%

“…Daily human tasks are divided into those that can be completed alone and those requiring cooperation between two or more people, such as moving an object. In most previous studies using RL, robots perform tasks on their own on behalf of humans [8][9][10][11][12][13][14][15][16][17]. Various human-robot interaction (HRI) technologies [18][19][20][21][22][23][24][25][26][27] are being studied, but most of them focus on research for robots to engage in conversation with humans [18][19][20][21][22][23] or utilize human feedback for robot learning [26,27] rather than collaborating with humans to perform tasks.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Table-Balancing Cooperative Robot Based on Deep Reinforcement Learning

Kim

Kang

2023

Sensors

View full text Add to dashboard Cite

Reinforcement learning is one of the artificial intelligence methods that enable robots to judge and operate situations on their own by learning to perform tasks. Previous reinforcement learning research has mainly focused on tasks performed by individual robots; however, everyday tasks, such as balancing tables, often require cooperation between two individuals to avoid injury when moving. In this research, we propose a deep reinforcement learning-based technique for robots to perform a table-balancing task in cooperation with a human. The cooperative robot proposed in this paper recognizes human behavior to balance the table. This recognition is achieved by utilizing the robot’s camera to take an image of the state of the table, then the table-balance action is performed afterward. Deep Q-network (DQN) is a deep reinforcement learning technology applied to cooperative robots. As a result of learning table balancing, on average, the cooperative robot showed a 90% optimal policy convergence rate in 20 runs of training with optimal hyperparameters applied to DQN-based techniques. In the H/W experiment, the trained DQN-based robot achieved an operation precision of 90%, thus verifying its excellent performance.

show abstract

Section: Previous Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Table-Balancing Cooperative Robot Based on Deep Reinforcement Learning

Kim

Kang

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…During the training process, depending on the small or large environment, the training time and the number of episodes will be different. Traditional Q-Learning [41] 60.0 198.4 s SARSA [42] 75.0 223.9 s Large (11 × 33) Traditional Q-Learning [41] 235.0 1.45 h SARSA [42] 275.0 57.23 min…”

Section: Reward Of Obstacle Romentioning

confidence: 99%

A Semi-Automatic Wheelchair with Navigation Based on Virtual-Real 2D Grid Maps and EEG Signals

Ngo¹,

Hải²

2022

Applied Sciences

View full text Add to dashboard Cite

A semi-automatic wheelchair allows disabled people to possibly control in an indoor environment with obstacles and targets. The paper proposes an EEG-based control system for the wheelchair based on a grid map designed to allow disabled people to reach any preset destination. In particular, the grid map is constructed by dividing it into grid cells that may contain free spaces or obstacles. The map with the grid cells is simulated to find the optimal paths to the target positions using a Deep Q-Networks (DQNs) model with the Parametric Rectified Linear Unit (PReLU) activation function, in which a novel algorithm for finding the optimal path planning by converting wheelchair actions is applied using the output parameters of the DQNs. For the wheelchair movement in one real indoor environment corresponding to the virtual 2D grid map, the initial position of the wheelchair will be determined based on natural landmarks and a graphical user interface designed for on-screen display can support disabled people in selecting the desired destination from a list of predefined locations using Electroencephalogram (EEG) signals by blinking eyes. Therefore, one user can easily and safely control the wheelchair using an EEG system to reach the desired target when the wheelchair position and destination are determined in the indoor environment. As a result, a grid map was developed and experiments for the semi-automatic wheelchair control were performed in real indoor environments to illustrate the effectiveness of the proposed method. In addition, the system is a platform to develop different types of controls depending on the types of user disabilities and different environmental maps built.

show abstract

“…It is also one of the important conditions for mobile robot to realize autonomous navigation. The existing SLAM algorithm is mainly applied to static environment (Wen et al, 2015). However, the real environment is complex and changeable, such as people walking, door switching, changes of lighting, etc.…”

Section: Introductionmentioning

confidence: 99%

Walking Human Detection Using Stereo Camera Based on Feature Classification Algorithm of Second Re-projection Error

et al. 2019

Self Cite

View full text Add to dashboard Cite

This paper presents a feature classification method based on vision sensor in dynamic environment. Aiming at the detected targets, a double-projection error based on orb and surf is proposed, which combines texture constraints and region constraints to achieve accurate feature classification in four different environments. For dynamic targets with different velocities, the proposed classification framework can effectively reduce the impact of large-area moving targets. The algorithm can classify static and dynamic feature objects and optimize the conversion relationship between frames only through visual sensors. The experimental results show that the proposed algorithm is superior to other algorithms in both static and dynamic environments.

show abstract

The Q-learning obstacle avoidance algorithm based on EKF-SLAM for NAO autonomous walking under unknown environments

Cited by 46 publications

References 7 publications

Table-Balancing Cooperative Robot Based on Deep Reinforcement Learning

Table-Balancing Cooperative Robot Based on Deep Reinforcement Learning

A Semi-Automatic Wheelchair with Navigation Based on Virtual-Real 2D Grid Maps and EEG Signals

Walking Human Detection Using Stereo Camera Based on Feature Classification Algorithm of Second Re-projection Error

Contact Info

Product

Resources

About