Efficiency-Driven Adaptive Task Planning for Household Robot Based on Hierarchical Item-Environment Cognition

Task planning focused on household robots represents a conventional yet complex research domain, necessitating the development of task plans that enable robots to execute unfamiliar household services. This area has garnered significant research interest due to its extensive applications in robotics, particularly concerning household robots. Nevertheless, the majority of task planning methodologies exhibit suboptimal performance regarding the success and efficiency of completing household tasks, primarily due to a lack of cognitive capacity of household items and home environments. To address these challenges, we propose an efficiency-driven adaptive task planning approach based on hierarchical item-environment cognition. Initially, we establish a multiple semantic attribute-based priori knowledge (MSAPK) framework to facilitate the attributive representation of household items. Utilizing MSAPK, we develop a long short-term memory (LSTM) based item cognition model that assigns relevant attributes and substitutes to specified household items, thereby enhancing the cognitive capabilities of household robots at the attribute level. Subsequently, we construct an environment cognition model that delineates the relationships between household items and room types, enabling household robots to locate target items more efficiently. Through hierarchical item-environment cognition, we introduce a strategy for adaptive task planning, empowering household robots to execute household tasks with both flexibility and efficiency. The generated plans are evaluated in both virtual and real-world experiments, with promising results affirming the effectiveness of our proposed methodology.

I. Introduction

Household robots play an essential role in the everyday lives of individuals, fulfilling the demand for high-quality services across various household tasks in response to escalating material and lifestyle requirements. Robot task planning is a vital mechanism for skill acquisition in robots, encompassing cognitive science [1], [2], artificial intelligence [3], [4], [5], robotic navigation [6], [7], [8], and other interdisciplinary fields. This technology is fundamental in directing robots to execute household services [9], [10]. Task planning can be categorized into high-level and low-level planning based on the representation of generated plans. High-level planning generates sequences of semantic actions [27], [54]. For instance, in the task of sending water, the high-level semantic actions include Grab, Place, and Open. Conversely, low-level planning focuses on the motor control of robots, addressing aspects, such as joint angles [50], travel distance and direction [46], [49], and arm positioning. It should be noted that the task planning discussed in this article pertains to high-level planning, represented as a sequence of semantic actions.