Turtlebot 3 as a Robotics Education Platform

Amsters, Robin; Slaets, Peter

doi:10.1007/978-3-030-26945-6_16

Cited by 75 publications

(38 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Turtlebot3-waffle [ 40 ] was used as a transporter robot, and the diameter of the robot was about 0.3 m. A gazebo with ROS noetic was used to constitute the simulation, which makes a physics model based on an open dynamics engine (ODE). We played Gazebo simulations about 70 times fast, and it took about 10 and 20 h to train 2000 (single robot) and 4000 (multi-robot) episodes, respectively; these total training numbers of episodes were experimentally determined because the average reward curve converged from those of episodes, as will be described in Figure 5 .…”

Section: Resultsmentioning

confidence: 99%

Cooperative Object Transportation Using Curriculum-Based Deep Reinforcement Learning

Eoh

Park

2021

Sensors

View full text Add to dashboard Cite

This paper presents a cooperative object transportation technique using deep reinforcement learning (DRL) based on curricula. Previous studies on object transportation highly depended on complex and intractable controls, such as grasping, pushing, and caging. Recently, DRL-based object transportation techniques have been proposed, which showed improved performance without precise controller design. However, DRL-based techniques not only take a long time to learn their policies but also sometimes fail to learn. It is difficult to learn the policy of DRL by random actions only. Therefore, we propose two curricula for the efficient learning of object transportation: region-growing and single- to multi-robot. During the learning process, the region-growing curriculum gradually extended to a region in which an object was initialized. This step-by-step learning raised the success probability of object transportation by restricting the working area. Multiple robots could easily learn a new policy by exploiting the pre-trained policy of a single robot. This single- to multi-robot curriculum can help robots to learn a transporting method with trial and error. Simulation results are presented to verify the proposed techniques.

show abstract

Section: Resultsmentioning

confidence: 99%

Cooperative Object Transportation Using Curriculum-Based Deep Reinforcement Learning

Eoh

Park

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Next, we conduct simulations on the Gazebo simulator (Koenig & Howard, 2004) using LOGO for way-point tracking by a robot in environments with and without obstacles, with the only reward being attainment of way points. Finally, we transfer the trained models to a real-world TurtleBot robot (Amsters & Slaets, 2019) to demonstrate LOGO in a realistic setting. In what follows, we present a summary of our experiments 1 and results.…”

Section: Methodsmentioning

confidence: 99%

Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration

Rengarajan¹,

Vaidya²,

Sarvesh³

et al. 2022

Preprint

View full text Add to dashboard Cite

A major challenge in real-world reinforcement learning (RL) is the sparsity of reward feedback. Often, what is available is an intuitive but sparse reward function that only indicates whether the task is completed partially or fully. However, the lack of carefully designed, fine grain feedback implies that most existing RL algorithms fail to learn an acceptable policy in a reasonable time frame. This is because of the large number of exploration actions that the policy has to perform before it gets any useful feedback that it can learn from. In this work, we address this challenging problem by developing an algorithm that exploits the offline demonstration data generated by a sub-optimal behavior policy for faster and efficient online RL in such sparse reward settings. The proposed algorithm, which we call the Learning Online with Guidance Offline (LOGO) algorithm, merges a policy improvement step with an additional policy guidance step by using the offline demonstration data. The key idea is that by obtaining guidance from -not imitating -the offline data, LOGO orients its policy in the manner of the sub-optimal policy, while yet being able to learn beyond and approach optimality. We provide a theoretical analysis of our algorithm, and provide a lower bound on the performance improvement in each learning episode. We also extend our algorithm to the even more challenging incomplete observation setting, where the demonstration data contains only a censored version of the true state observation. We demonstrate the superior performance of our algorithm over state-of-the-art approaches on a number of benchmark environments with sparse rewards and censored state. Further, we demonstrate the value of our approach via implementing LOGO on a mobile robot for trajectory tracking and obstacle avoidance, where it shows excellent performance.

show abstract

“…Ten markers were attached to a corridor at equal intervals of 180 cm. The wheeled mobile robot moved from marker 0 to 9 at a speed of 0.1 m/s [ 27 ]. The global position of the reference marker (marker 0) was set as 0, 0.…”

Section: Verification Of Proposed Methodsmentioning

confidence: 99%

Marker-Based Method for Recognition of Camera Position for Mobile Robots

Gwak

Yang

Park

et al. 2021

Sensors

View full text Add to dashboard Cite

Position recognition is one of the core technologies for driving a robot because of differences in environment and rapidly changing situations. This study proposes a strategy for estimating the position of a camera mounted on a mobile robot. The proposed strategy comprises three methods. The first is to directly acquire information (e.g., identification (ID), marker size and marker type) to recognize the position of the camera relative to the marker. The advantage of this marker system is that a combination of markers of different sizes or having different information may be used without having to update the internal parameters of the robot system even if the user frequently changes or adds to the marker’s identification information. In the second, two novel markers are proposed to consider the real environment in which real robots are applied: a nested marker and a hierarchical marker. These markers are proposed to improve the ability of the camera to recognize markers while the camera is moving on the mobile robot. The nested marker is effective for robots like drones, which land and take off vertically with respect to the ground. The hierarchical marker is suitable for robots that move horizontally with respect to the ground such as wheeled mobile robots. The third method is the calculation of the position of an added or moved marker based on a reference marker. This method automatically updates the positions of markers after considering the change in the driving area of the mobile robot. Finally, the proposed methods were validated through experiments.

show abstract

Turtlebot 3 as a Robotics Education Platform

Cited by 75 publications

References 5 publications

Cooperative Object Transportation Using Curriculum-Based Deep Reinforcement Learning

Cooperative Object Transportation Using Curriculum-Based Deep Reinforcement Learning

Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration

Marker-Based Method for Recognition of Camera Position for Mobile Robots

Contact Info

Product

Resources

About