Distributed Deep Reinforcement Learning based Indoor Visual Navigation

Hsu, Shih-Hsi; Chan, Shao-Hung; Wu, Ping-Tsang; Xiao, Kun; Fu, Li-Chen

doi:10.1109/iros.2018.8594352

Cited by 21 publications

(11 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Collaborative manipulation and multi-agent path planning are another two subproblems where machine learning could be used. Recent work utilized different types of machine learning such as Reinforcement learning are presented in [2,6,31,43,71,81].…”

Section: Discussion and Future Research Directionsmentioning

confidence: 99%

A survey on multi-robot coverage path planning for model reconstruction and mapping

Taha²,

et al. 2019

View full text Add to dashboard Cite

There has been an increasing interest in researching, developing and deploying multi-robot systems. This has been driven mainly by: the maturity of the practical deployment of a single-robot system and its ability to solve some of the most challenging tasks. Coverage path planning (CPP) is one of the active research topics that could benefit greatly from multi-robot systems. In this paper, we surveyed the research topics related to multi-robot CPP for the purpose of mapping and model reconstructions. We classified the topics into: viewpoints generation approaches; coverage planning strategies; coordination and decision-making processes; communication mechanism and mapping approaches. This paper provides a detailed analysis and comparison of the recent research work in this area, and concludes with a critical analysis of the field, and future research perspectives.

show abstract

Section: Discussion and Future Research Directionsmentioning

confidence: 99%

A survey on multi-robot coverage path planning for model reconstruction and mapping

Taha²,

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Gupta et al [10] investigated a mapping and planning navigation network based on visual data that encodes the robot's observations into a birds-eye view of the environment, which makes the method limited to known scenarios. Also the approach presented by Hsu et al [11] was developed for known environments. A CNN processes image data and generates discrete actions to move the robot towards a global goal pose.…”

Section: Related Workmentioning

confidence: 99%

Deep Reinforcement Learning for Navigation in Cluttered Environments

Seguchi¹,

Gesing²,

Bennewitz³

et al. 2020

Computer Science &Amp; Information Technology (CS &Amp; IT)

View full text Add to dashboard Cite

Collision-free motion is essential for mobile robots. Most approaches to collision-free and efficient navigation with wheeled robots require parameter tuning by experts to obtain good navigation behavior. In this paper, we aim at learning an optimal navigation policy by deep reinforcement learning to overcome this manual parameter tuning. Our approach uses proximal policy optimization to train the policy and achieve collision-free and goal-directed behavior. The output of the learned network are the robot's translational and angular velocities for the next time step. Our method combines path planning on a 2D grid with reinforcement learning and does not need any supervision. Our network is first trained in a simple environment and then transferred to scenarios of increasing complexity. We implemented our approach in C++ and Python for the Robot Operating System (ROS) and thoroughly tested it in several simulated as well as real-world experiments. The experiments illustrate that our trained policy can be applied to solve complex navigation tasks. Furthermore, we compare the performance of our learned controller to the popular dynamic window approach (DWA) of ROS. As the experimental results show, a robot controlled by our learned policy reaches the goal significantly faster compared to using the DWA by closely bypassing obstacles and thus saving time.

show abstract

“…In the realm of global planners, mapless navigation has drawn some attention. In [36] the global path planner focuses on the recognition of pre-trained landmarks for the global localization; even though there is no need for a map, the system requires a dataset with global coordinates of the landmarks. Differently in [37], the authors modify A * path planning to make the search more efficient in large graph structures.…”

Section: A Related Workmentioning

confidence: 99%

Temporal Graph Traversals Using Reinforcement Learning With Proximal Policy Optimization

2020

View full text Add to dashboard Cite

Graphs in real-world applications are dynamic both in terms of structures and inputs. Information discovery in such networks, which present dense and deeply connected patterns locally and sparsity globally can be time consuming and computationally costly. In this paper we address the shortest path query in spatio-temporal graphs which is a fundamental graph problem with numerous applications. In spatiotemporal graphs, shortest path query classical algorithms are insufficient or even flawed because information consistency can not be guaranteed between two timestamps and path recalculation is computationally costly. In this work, we address the complexity and dynamicity of the shortest path query in spatio-temporal graphs with a simple, yet effective model based on Reinforcement Learning with Proximal Policy Optimization. Our solution simplifies the problem by decomposing the spatio-temporal graph in two components: a static and a dynamic sub-graph. The static graph, known and immutable, is efficiently solved with A * algorithm. The sub-graphs interconnecting the static graph have unknown dynamics and we address such issue by estimating the unknown dynamic portion of the graph as a Markov Chain which correlates the observations of the agents in the environment and the path to be followed. We then derive an action policy through Proximal Policy Optimization to select the local optimal actions in the Markov Process that will lead to the shortest path, given the estimated system dynamics. We evaluate the system in a simulation environment constructed in Unity3D. In partially structured and unknown environments, with variable environment parameters we've obtained an efficiency 75% greater than the comparable deterministic solution.

show abstract

Distributed Deep Reinforcement Learning based Indoor Visual Navigation

Cited by 21 publications

References 2 publications

A survey on multi-robot coverage path planning for model reconstruction and mapping

A survey on multi-robot coverage path planning for model reconstruction and mapping

Deep Reinforcement Learning for Navigation in Cluttered Environments

Temporal Graph Traversals Using Reinforcement Learning With Proximal Policy Optimization

Contact Info

Product

Resources

About