Corpus ID: 237563193

Decentralized Global Connectivity Maintenance for Multi-Robot Navigation: A Reinforcement Learning Approach

@article{Li2021DecentralizedGC,
  title={Decentralized Global Connectivity Maintenance for Multi-Robot Navigation: A Reinforcement Learning Approach},
  author={Minghao Li and Yingrui Jie and Yang Kong and Hui Cheng},
  journal={ArXiv},
  year={2021},
  volume={abs/2109.08536}
}
The problem of multi-robot navigation of connectivity maintenance is challenging in multi-robot applications. This work investigates how to navigate a multi-robot team in unknown environments while maintaining connectivity. We propose a reinforcement learning (RL) approach to develop a decentralized policy, which is shared among multiple robots. Given range sensor measurements and the positions of other robots, the policy aims to generate control commands for navigation and preserve the global… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 31 REFERENCES
Connectivity Guaranteed Multi-robot Navigation via Deep Reinforcement Learning
TLDR
A novel Deep Reinforcement Learning (DRL)-based approach is proposed to derive end-to-end policies for the multi-robot navigation problem to guarantee the connectivity during the navigation, and a constraint satisfying parametric function (CSPF) is suggested to represent the navigation policy. Expand
Cooperative Multi-Robot Navigation in Dynamic Environment with Deep Reinforcement Learning
TLDR
A cooperative approach to address the multi-robot navigation problem (MRNP) under dynamic environments using a deep reinforcement learning (DRL) framework, which can help multiple robots jointly achieve optimal paths despite a certain degree of obstacle complexities. Expand
A bounded controller for multirobot navigation while maintaining network connectivity in the presence of obstacles
TLDR
This challenging problem is addressed through the development of a novel controller that can guarantee that robots will approach their individual desired positions while maintaining existing network topology and avoiding obstacles. Expand
Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning
TLDR
This work presents a decentralized sensor-level collision avoidance policy for multi-robot systems, which directly maps raw sensor measurements to an agent's steering commands in terms of movement velocity and demonstrates that the learned policy can be well generalized to new scenarios that do not appear in the entire training period. Expand
Decentralized connectivity maintenance for cooperative control of mobile robotic systems
TLDR
This paper presents a completely decentralized control strategy for global connectivity maintenance of the communication graph that exploits decentralized estimation of the algebraic connectivity in the disk communication model. Expand
Bounded Control Law for Global Connectivity Maintenance in Cooperative Multirobot Systems
TLDR
This paper describes the effect of the connectivity control term on the achievement of the collective control objective by resorting to an input-to-state stability-like analysis and provides numerical and experimental results to corroborate the theoretical findings and assess the effectiveness of the proposed bounded connectivity maintenance control law. Expand
End-to-end Decentralized Multi-robot Navigation in Unknown Complex Environments via Deep Reinforcement Learning
TLDR
The proposed method can derive end-to-end policies, which map raw lidar measurements into velocity control commands of robots without the necessity of constructing obstacle maps, which verify the effectiveness of the proposed method. Expand
Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning
  • Michael Everett, Y. Chen, J. How
  • Computer Science, Engineering
  • 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2018
TLDR
This work extends the previous approach to develop an algorithm that learns collision avoidance among a variety of types of dynamic agents without assuming they follow any particular behavior rules, and introduces a strategy using LSTM that enables the algorithm to use observations of an arbitrary number of other agents, instead of previous methods that have a fixed observation size. Expand
Global connectivity control for spatially interacting multi-robot systems with unicycle kinematics
TLDR
This work extends a decision-based link maintenance framework to unicycle kinematics and discontinuous potential-based interaction, by exploiting techniques from nonsmooth analysis, and couple this extension with an existing connectivity estimation technique which yields an estimate with tunable precision in finite time. Expand
From perception to decision: A data-driven approach to end-to-end motion planning for autonomous ground robots
TLDR
This work presents the first approach that learns a target-oriented end-to-end navigation model for a robotic platform, and demonstrates that the learned navigation model is directly transferable to previously unseen virtual and, more interestingly, real-world environments. Expand
...
1
2
3
4
...