基于行为检测的机器人安全保护方法

Method for Ensuring Safety of Robot Based on Behavior Detection

机器人是一类典型的信息物理融合系统,由软件控制的机器人行为存在多种形式的安全问题。为了避免这些问题,提出一种基于行为检测的机器人安全保护方法。行为检测是指通过检测机器人执行行为之前和之后的状态,判断机器行为是否安全。该方法针对硬件限制、稳定性和碰撞冲突3个方面的行为安全问题,支持机器人执行行为之前对其进行建模和检测,提出碰撞冲突检测算法ACD。基于AOP技术实现该安全保护方法。基于NAO机器人开展了若干场景的实验,结果表明该方法可有效检测出危害机器人安全的行为并及时做出相应动作补偿。

Robot is a typical cyber-physical system and its behaviors that are driven and controlled by software are high- ly related with safety. In order to ensure the safety of robot behaviors, this paper proposed a security protection method based on behavior detection that enables robot to detect its behaviors ~ safety before their executions. Three kinds of safety issues were considered, including hardware constraints, stability and collision confliction. The corresponding algo- rithm called ACD algorithm for collision confliction detection was proposed. Implementation framework for the method was proposed on the basis of AOP technology. We made some experiments with NAO robots. The results indicate that the method can effectively detect harmful behaviors and adjust motions in compensation for behaviors.