Voronoi-Based Multi-Robot Autonomous Exploration in Unknown Environments via Deep Reinforcement Learning

@article{Hu2020VoronoiBasedMA,
  title={Voronoi-Based Multi-Robot Autonomous Exploration in Unknown Environments via Deep Reinforcement Learning},
  author={Junyan Hu and Hanlin Niu and Joaqu{\'i}n Carrasco and Barry Lennox and Farshad Arvin},
  journal={IEEE Transactions on Vehicular Technology},
  year={2020},
  volume={69},
  pages={14413-14423}
}
Autonomous exploration is an important application of multi-vehicle systems, where a team of networked robots are coordinated to explore an unknown environment collaboratively. This technique has earned significant research interest due to its usefulness in search and rescue, fault detection and monitoring, localization and mapping, etc. In this paper, a novel cooperative exploration strategy is proposed for multiple mobile robots, which reduces the overall task completion time and energy costs… 
Decentralized trajectory optimization for multi-agent exploration
TLDR
A decentralized ergodic multi-agent trajectory planning algorithm featuring limited communication constraints is proposed, which allows a much more efficient exploration in terms of completion task time and control energy distribution by leveraging collaboration among agents.
Decentralized Trajectory Optimization for Multi-Agent Ergodic Exploration
TLDR
A decentralized ergodic multi-agent trajectory planning algorithm featuring limited communication constraints is proposed, which allows a much more efficient exploration in terms of completion task time and control energy distribution by leveraging collaboration among agents.
Intelligent Exploration Approaches Based on Utility Functions Optimization for Multi-Agent Environment Applications
TLDR
It is proposed to compare the fitting of the market utility function using neural networks and optimize this function using genetic algorithms to avoid heavy computation in the Non-Polynomial (NP: nondeterministic polynomial time) path-planning problem.
A Decentralized Cluster Formation Containment Framework for Multirobot Systems
TLDR
A unified cluster formation containment coordination framework for networked robots that can be decomposed into two layers containing the leaders and the followers is developed.
Federated Reinforcement Learning for Collective Navigation of Robotic Swarms
TLDR
The experimental results from the collective learning scenario showed that the proposed FL-based strategy dramatically reduced the number of communication by minimum 1600 times and even increased the success rate of navigation with the trained controller by 2.8 times compared to the baseline strategies that share a central server.
Group Coordinated Control of Networked Mobile Robots With Applications to Object Transportation
TLDR
A ‘continuous’ cooperative control protocol is proposed to overcome the chattering phenomenon often caused by a discontinuous control action during hardware implementation, and the closed-loop stability of the overall networked MRS is guaranteed via the Lyapunov theory and boundary-layer techniques.
Universal Artificial Pheromone Framework with Deep Reinforcement Learning for Robotic Systems
TLDR
The feasibility of using the proposed PhERS (Pheromone for Every RobotS) framework designed to increase versatility in a robotic scenario is demonstrated, showing that DRLbased controller outperforms the baseline hand-tuned controller in a dynamic environment.
A Soar-Based Space Exploration Algorithm for Mobile Robots
TLDR
This paper models the space exploration problem of mobile robots based on the decision-making process of the cognitive architecture of Soar, and three space exploration heuristic algorithms are further proposed based on this model to improve the exploration speed of the robot.
A Fully Controllable Agent in the Path Planning using Goal-Conditioned Reinforcement Learning
  • G. Lee
  • Computer Science
    ArXiv
  • 2022
TLDR
A novel reinforcement learning framework for a fully controllable agent in the path planning is proposed, in which the agent’s behavior and sub-goals are trained on the goal-conditioned RL and the reward shaping is presented to shorten the number of steps for the agent to reach the goal.
Collaborative multi-agents in dynamic industrial internet of things using deep reinforcement learning
TLDR
A model to tackle the problem of scalability in DRL algorithms in transportation domain uses generative adversarial imitation learning and behavior cloning, combined with a proximal policy optimization algorithm, for training multiple agents in a dynamic environment.
...
...

References

SHOWING 1-10 OF 37 REFERENCES
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.
Deep Reinforcement Learning Robot for Search and Rescue Applications: Exploration in Unknown Cluttered Environments
TLDR
This letter presents the first use of deep learning to address the robot exploration task in USAR applications, and uniquely combine the traditional approach of frontier-based exploration with deep reinforcement learning to allow a robot to autonomously explore unknown cluttered environments.
Bayesian Reinforcement Learning for Multi-Robot Decentralized Patrolling in Uncertain Environments
TLDR
A scalable decentralized online learning and planning algorithm is proposed by extending the Monte Carlo tree search method, which computes patrols that are bounded optimal and is able to achieve high performance in typical decentralized patrolling scenarios.
Coordinated multi-robot exploration
TLDR
This paper presents an approach for the coordination of multiple robots, which simultaneously takes into account the cost of reaching a target point and its utility and describes how this algorithm can be extended to situations in which the communication range of the robots is limited.
Deep Reinforcement Learning Supervised Autonomous Exploration in Office Environments
TLDR
An algorithm is presented that utilizes deep reinforcement learning (DRL) to learn exploration knowledge over office blueprints, which enables the agent to predict a long-term visiting order for unexplored subregions and an exploration architecture that integrates a DRL model, a next-best-view (NBV) selection approach and a structural integrity measurement to further improve the exploration performance.
Autonomous Robotic Exploration by Incremental Road Map Construction
TLDR
An efficient path planning framework is introduced to reduce the path length and exploration time and a target selection mechanism helps the robot determine the next best target to explore and the proposed trajectory optimization algorithm helps in reducing the path cost.
Deep reinforcement learning with successor features for navigation across similar environments
TLDR
This paper proposes a successor-feature-based deep reinforcement learning algorithm that can learn to transfer knowledge from previously mastered navigation tasks to new problem instances and substantially decreases the required learning time after the first task instance has been solved.
Virtual-to-real deep reinforcement learning: Continuous control of mobile robots for mapless navigation
TLDR
It is shown that, through an asynchronous deep reinforcement learning method, a mapless motion planner can be trained end-to-end without any manually designed features and prior demonstrations.
The Sensor-based Random Graph Method for Cooperative Robot Exploration
TLDR
A roadmap of the explored area, with the associate safe region, is built in the form of a sensor-based random graph (SRG) by a team of mobile robots equipped with range finders by using a randomized local planner that automatically realizes a tradeoff between information gain and navigation cost.
Efficient Autonomous Exploration Planning of Large-Scale 3-D Environments
TLDR
This letter presents a method that combines both approaches, with FEP as a global exploration planner and RH-NBVP for local exploration, and presents techniques to estimate potential information gain faster, to cache previously estimated gains and to exploit these to efficiently estimate new queries.
...
...