An Upper Confidence Bound for Simultaneous Exploration and Exploitation in Heterogeneous Multi-Robot Systems

Lee, Ki Myung Brian; Kong, Felix H.; Cannizzaro, Ricardo; Palmer, Jennifer L.; Johnson, D.L.; Yoo, Chanyeol

doi:10.1109/icra48506.2021.9560822

Cited by 8 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing approaches to multi-sensor problems involve optimizing for coverage objectives only (Cao et al 2021), creating separate viewpoints for exploration and coverage (Best et al 2018a; Vidal et al 2020; Petrlik et al 2023), or combining exploration and coverage into a single objective (Lee et al 2021c; Liu et al 2021; Sukkar et al 2019; Corah and Michael 2021). We opt for an approach that creates separate viewpoints for exploration and coverage, as we found that viewpoints that favor coverage are most beneficial, but there are specific scenarios where exploration viewpoints are necessary.…”

Section: Related Workmentioning

confidence: 99%

Multi-robot, multi-sensor exploration of multifarious environments with full mission aerial autonomy

Best,

Garg,

Keller

et al. 2023

The International Journal of Robotics Research

View full text Add to dashboard Cite

We present a coordinated autonomy pipeline for multi-sensor exploration of confined environments. We simultaneously address four broad challenges that are typically overlooked in prior work: (a) make effective use of both range and vision sensing modalities, (b) perform this exploration across a wide range of environments, (c) be resilient to adverse events, and (d) execute this onboard teams of physical robots. Our solution centers around a behavior tree architecture, which adaptively switches between various behaviors involving coordinated exploration and responding to adverse events. Our exploration strategy exploits the benefits of both visual and range sensors with a generalized frontier-based exploration algorithm and an OpenVDB-based map processing pipeline. Our local planner utilizes a dynamically feasible trajectory library and a GPU-based Euclidean distance transform map to allow fast and safe navigation through both tight doorways and expansive spaces. The autonomy pipeline is evaluated with an extensive set of field experiments, with teams of up to three robots that fly up to 3 m/s and distances exceeding 1 km in confined spaces. We provide a summary of various field experiments and detail resilient behaviors that arose: maneuvering narrow doorways, adapting to unexpected environment changes, and emergency landing. Experiments are also detailed from the DARPA Subterranean Challenge, where our proposed autonomy pipeline contributed to us winning the “Most Sectors Explored” award. We provide an extended discussion of lessons learned, release software as open source, and present a video that illustrates our extensive field trials.

show abstract

Section: Related Workmentioning

confidence: 99%

Multi-robot, multi-sensor exploration of multifarious environments with full mission aerial autonomy

Best,

Garg,

Keller

et al. 2023

The International Journal of Robotics Research

View full text Add to dashboard Cite

show abstract

“…This can be determined by adjusting the constant C p of the exploration item that determines the importance of strategic exploration. As the UCT iterations grow to infinity, the probability of choosing a suboptimal action at the root node converges to zero at a polynomial rate [35][36][37][38].…”

Section: Upper Confidence Bound Applied To Treementioning

confidence: 99%

NFSP-PLT: Solving Games with a Weighted NFSP-PER-Based Method

Li,

Qi,

Zhang

et al. 2023

Electronics

View full text Add to dashboard Cite

Nash equilibrium strategy is a typical goal when solving two-player imperfect-information games (IIGs). Neural fictitious self-play (NFSP) is a popular method to find the Nash equilibrium in IIGs, which is the first end-to-end method used to compute the Nash equilibrium strategy. However, the training of NFSP requires a large number of sample data and the interactive cost of obtaining such data is often very high. Realizing the efficient training of network under limited samples is an urgent problem. In this paper, we first proposed a new NFSP-based method, NFSP with prioritized experience replay (NFSP-PER), to improve the sample training efficiency. Then, a weighted NFSP-PER with learning time (NFSP-PLT) was proposed to control the utilization degree of priority-weighted samples. Furthermore, based on the NFSP-PLT, an adaptive upper-confidence-bound applied to tree (UCT) is used to solve the optimal response strategy, which makes the solving strategy more accurate. Extensive experimental results show that the proposed NFSP-PLT effectively improves the sample learning efficiency compared with the existing works.

show abstract

“…While single-robot strategies can be extended to multiagent setups by partitioning the area of interest according to the number of robots [7], this does not ensure efficient collaboration between them or resilience to single-robot failures. With the objective of addressing this limitation, cooperative frontier-based approaches have been proposed in centralized [2], [8], [21] and decentralized [10], [22] fashions. Centralised methods feature a hub or ground station where a global multi-robot plan is first computed, and then communicated to the agents.…”

Section: Related Workmentioning

confidence: 99%

Decentralised Multi-Robot Exploration Using Monte Carlo Tree Search

Bone,

Bartolomei,

Kennel-Maushart

et al. 2023

2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Autonomous robotic systems are useful in automating tasks such as inspection and surveying of unknown areas, where speed is often an important factor. In order to effectively reduce the time required to complete missions, an efficient exploration and coordination strategy is needed. In this spirit, this work proposes an approach based on the Monte Carlo Tree Search (MCTS) algorithm to guide robots during exploration missions. Our method first expands a search tree of possible actions from the robot's position towards unknown regions, and then selects the sequence of movements that best drive the exploration process forward with respect to a given reward function. The proposed approach, which is able to balance short-and long-term decision-making, is then extended to accommodate the presence of multiple robots, in a bid to push the efficiency of exploration further. Our method allows for the coordination of the robots' movements in a decentralized manner, relying on point-to-point communication. This results in an efficient strategy, which we refer to as Decentralized Monte Carlo Exploration (DMCE). The experimental results demonstrate that our pipeline outperforms a greedy exploration approach, as well as state-of-the-art planners, with up to 30% reduction in exploration times in a series of real-world maps.

show abstract

An Upper Confidence Bound for Simultaneous Exploration and Exploitation in Heterogeneous Multi-Robot Systems

Cited by 8 publications

References 25 publications

Multi-robot, multi-sensor exploration of multifarious environments with full mission aerial autonomy

Multi-robot, multi-sensor exploration of multifarious environments with full mission aerial autonomy

NFSP-PLT: Solving Games with a Weighted NFSP-PER-Based Method

Decentralised Multi-Robot Exploration Using Monte Carlo Tree Search

Contact Info

Product

Resources

About