面向环境适应性的机器人服务策略生成方法

Environment-adaptive service strategy generation method for robot

为提高机器人在不同家庭环境下的服务任务执行能力,提出一种环境适应性服务策略生成方法,可生成以当前环境物品信息为主导的服务策略.首先,利用词频-逆文本频率(TF-IDF)算法构建服务指令集、关键字序列集与服务策略数据集;然后,对无规则自然语言指令进行语义解析与组块分析,分解映射至结构化服务指令以简化语义空间,获取对应待选关键字序列;最后,对包含当前家庭环境信息的Protégé本体知识库进行匹配、推理,获得服务关键字序列,引导经服务策略数据集微调的GPT-2模型生成适应性服务策略.实验结果表明:该方法能够提高服务策略生成的准确性,且最终生成的策略在具体家庭环境下具有更高的可行性.

In order to improve the service task execution ability of robots in different home environments,an environment-adaptive service strategy generation method was proposed,which could generate the service strategy based on the current environmental goods information. Firstly,term frequency-inverse document frequency(TF-IDF) algorithm was used to construct service instruction set,keyword sequence set and service strategy data set.Secondly,semantic parsing and block analysis were carried out for irregular natural language instructions,which were decomposed and mapped to structured service instructions to simplify the semantic space and obtain the corresponding keyword sequence to be selected. Finally,the Protégé ontology knowledge base containing the current family environment information was matched and inferred to obtain the service keyword sequence,and the GPT-2 model fine-tuned by the service strategy data set was guided to generate the adaptive service strategy.Experimental results show that this method can improve the accuracy of service strategy generation,and the final generated strategy is more feasible in a specific family environment.