This paper describes a rule base-Sugeno fuzzy hybrid controller for path planning of single as well as multiple humanoid robots in cluttered environments. Initially, sensor outputs regarding the obstacle distances are used as inputs to the rule base model, and turning angle is obtained as the output. The rule-based analysis is used for training the fuzzy controller with membership functions. The output from the rule base model along with other regular inputs is supplied to a Sugeno fuzzy model, and effective turning angle is obtained as the final output to avoid the obstacles present in the environment and navigate the humanoids safely to their target points. The proposed hybrid controller is tested on a V-REP simulation platform, and the simulation results are validated in an experimental set-up. To avoid the possibility of any inter-collision during navigation of multiple humanoids on a common platform, a Petri-net scheme is integrated along with the proposed hybrid model. Finally, the results obtained from simulation and experimental platforms are compared against each other with proper agreement and minimal percentage of deviations. To validate the proposed controller, it has also been tested against another existing navigational approach, and satisfactory performance enhancement has been observed.

中文翻译：

---

使用混合规则库-Sugeno 模糊控制器对多个类人机器人进行导航分析

本文描述了一种规则库-Sugeno 模糊混合控制器，用于在杂乱环境中对单个和多个仿人机器人进行路径规划。最初，有关障碍物距离的传感器输出用作规则库模型的输入，并获得转向角作为输出。基于规则的分析用于训练具有隶属函数的模糊控制器。规则库模型的输出与其他常规输入一起提供给 Sugeno 模糊模型，并获得有效的转向角作为最终输出，以避开环境中存在的障碍物并将类人机器人安全导航到目标点。所提出的混合控制器在 V-REP 仿真平台上进行了测试，并在实验装置中验证了仿真结果。为了避免在一个公共平台上多个类人机器人导航期间发生任何相互碰撞的可能性，Petri-net 方案与所提出的混合模型一起集成。最后，将从模拟和实验平台获得的结果相互比较，具有适当的一致性和最小的偏差百分比。为了验证所提出的控制器，它还针对另一种现有的导航方法进行了测试，并观察到了令人满意的性能增强。