当前位置: X-MOL 学术IEEE Robot. Automation Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A Shared Control Framework for Human-Multirobot Foraging With Brain-Computer Interface
IEEE Robotics and Automation Letters ( IF 4.6 ) Pub Date : 2021-07-20 , DOI: 10.1109/lra.2021.3092290
Wei Dai , Yaru Liu , Huimin Lu , Zhiqiang Zheng , Zongtan Zhou

With the rapid development of multi-robot systems (MRSs), they can be widely used to perform various tasks in typical environments. However, the inevitable disadvantages of onboard sensor errors, communication delays, and underspecified environmental factors seriously affect the operation of MRSs. Therefore, this letter considers a shared control framework suitable for human-multirobot foraging with a brain-computer interface (BCI) as a means of allowing a human operator to express opinions, permitting the robots to rely on human experience and knowledge to improve cooperation. An opinion dynamics model is used to find the consensus opinion of the MRS, which, however, is likely not accurate due to the biased nature of the available environmental information. When the human operator learns the opinion of the robots, he/she can then either accept it or reject it and express his/her own opinion via the BCI. Of course, this human judgment may also be incorrect, or the BCI may suffer from false detections. Thus, the MRS does not directly follow the human operator's opinion; instead, it is added to the opinion dynamics model as a new node to generate the final consensus opinion. Extensive simulation results show that the proposed framework can markedly improve the efficiency of foraging compared with robot-only or human-only performance and traditional human-robot interaction methods.

中文翻译:


脑机接口人机多机器人觅食共享控制框架



随着多机器人系统(MRS)的快速发展,它们可以广泛用于在典型环境中执行各种任务。然而,机载传感器错误、通信延迟和未指定的环境因素等不可避免的缺点严重影响了MRS的运行。因此,这封信考虑了一种适合人机多机器人觅食的共享控制框架,通过脑机接口(BCI)作为允许人类操作员表达意见的手段,允许机器人依靠人类的经验和知识来改善合作。意见动态模型用于寻找 MRS 的共识意见,但由于现有环境信息的偏差,该意见可能不准确。当人类操作员了解机器人的意见时,他/她可以接受或拒绝它,并通过 BCI 表达他/她自己的意见。当然,这种人为判断也可能是错误的,或者BCI可能会出现错误检测。因此,MRS并不直接遵循操作人员的意见;相反,它作为新节点添加到意见动态模型中以生成最终的共识意见。大量的仿真结果表明,与仅机器人或仅人类的性能以及传统的人机交互方法相比,所提出的框架可以显着提高觅食效率。
更新日期:2021-07-20
down
wechat
bug