Refining Co-operative Competition of Robocup Soccer with Reinforcement Learning

Wang, Zhengqiao; Zeng, Yufan; Yuan, Yue; Guo, Yating

doi:10.1109/dsc50466.2020.00049

Cited by 3 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, when the weight of the heavy object carried is too large, a single humanoid robot carries a heavy object will fail to complete the work successfully and even may fall down and damage the joints. And in the fields such as rescue tasks (Hong et al, 2018 ), logistics handling cooperation (Straßmann et al, 2019 ), and sports competition (Wang Z. et al, 2020 ), broad applications are expected on humanoid robots. Therefore, the problem of multi-humanoid robot cooperation has gradually become a hot topic in the field of robotics.…”

Section: Introductionmentioning

confidence: 99%

Humanoid Robot Cooperative Motion Control Based on Optimal Parameterization

Zhong

Zheng

et al. 2021

Front. Neurorobot.

View full text Add to dashboard Cite

The implementation of low-energy cooperative movements is one of the key technologies for the complex control of the movements of humanoid robots. A control method based on optimal parameters is adopted to optimize the energy consumption of the cooperative movements of two humanoid robots. A dynamic model that satisfies the cooperative movements is established, and the motion trajectory of two humanoid robots in the process of cooperative manipulation of objects is planned. By adopting the control method with optimal parameters, the parameters optimization of the energy consumption index function is performed and the stability judgment index of the robot in the movement process is satisfied. Finally, the effectiveness of the method is verified by simulations and experimentations.

show abstract

Section: Introductionmentioning

confidence: 99%

Humanoid Robot Cooperative Motion Control Based on Optimal Parameterization

Zhong

Zheng

et al. 2021

Front. Neurorobot.

View full text Add to dashboard Cite

show abstract

Eligibility traces in an autonomous soccer robot with obstacle avoidance and navigation policy

Azarkasb,

Khasteh

2024

Applied Soft Computing

View full text Add to dashboard Cite

Strengthening Cooperative Consensus in Multi-Robot Confrontation

Xu,

Chen,

She

et al. 2024

ACM Trans. Intell. Syst. Technol.

View full text Add to dashboard Cite

Multi-agent reinforcement learning (MARL) has proven effective in training multi-robot confrontation, such as StarCraft and robot soccer games. However, the current joint action policies utilized in MARL have been unsuccessful in recognizing and preventing actions that often lead to failures on our side. This exacerbates the cooperation dilemma, ultimately resulting in our agents acting independently and being defeated individually by their opponents. To tackle this challenge, we propose a novel joint action policy, referred to as the consensus action policy (CAP). Specifically, CAP records the number of times each joint action has caused our side to fail in the past and computes a cooperation tendency, which is integrated with each agent’s Q-value and Nash bargaining solution to determine a joint action. The cooperation tendency promotes team cooperation by selecting joint actions that have a high tendency of cooperation and avoiding actions that may lead to team failure. Moreover, the proposed CAP policy can be extended to partially observable scenarios by combining it with Deep Q network (DQN) or actor-critic-based methods. We conducted extensive experiments to compare the proposed method with seven existing joint action policies, including four commonly used methods and three state-of-the-art (SOTA) methods, in terms of episode rewards, winning rates, and other metrics. Our results demonstrate that this approach holds great promise for multi-robot confrontation scenarios.

show abstract

Refining Co-operative Competition of Robocup Soccer with Reinforcement Learning

Cited by 3 publications

References 11 publications

Humanoid Robot Cooperative Motion Control Based on Optimal Parameterization

Humanoid Robot Cooperative Motion Control Based on Optimal Parameterization

Eligibility traces in an autonomous soccer robot with obstacle avoidance and navigation policy

Strengthening Cooperative Consensus in Multi-Robot Confrontation

Contact Info

Product

Resources

About