Towards a hybrid software architecture and multi-agent approach for autonomous robot software

Abstract

To support robust plan execution of autonomous robots in dynamic environments, autonomous robot software should include adaptive and reactive capabilities to cope with the dynamics and uncertainties of the evolving states of real-world environments. However, conventional software architectures such as sense-model-plan-act and behaviour-based paradigms are inadequate for meeting the requirements. A lack of sensing during acting in the sense-model-plan-act paradigm makes the software slow to react to run-time contingencies, whereas the behaviour-based architectures typically fall short in planning of long-range steps and making optimized plan adaptations. This article proposes a hybrid software architecture that maintains both adaptivity and reactivity of robot behaviours in dynamic environments. To implement this architecture, we further present the multi-agent development framework known as AutoRobot, which views the robot software as a multi-agent system in which diverse agent roles collaborate to achieve software functionalities. To demonstrate the applicability and validity of our concrete framework and software architecture, we conduct an experiment to implement a typical case, for example, a robot that autonomously picks up and drops off dishes for remote guests, which requires the robot to plan and navigate in a highly dynamic environment and can adapt its behaviours to unexpected situations.

RETRACTED: A decentralized multi-agent control approach for robust robot plan execution

“…In the presence of such uncertainties, an autonomous robot system expects to carry out plans both robustly and adaptively to accomplish its assigned task, which requires the robot to continuously sense the situated environment, monitor the status of plan execution and adapt the plan in case of run-time emergencies. 3 The robustness of plan execution in open environments usually implies a tight integration of robot planning, sensing, acting and reasoning behaviours, which presents a greater challenge for effectively controlling a complex autonomous robot system. 4 More specifically, task planning and plan execution monitoring need to be incorporated into the robotic control process, which heavily relates to robotic planning for task achievement, plan failure detection and plan recovery.…”

“…This article proposes the adoption of an MAS to model and abstract an execution-monitoring procedure in a single, complex robotic system, which specifically focuses on the failure detection and isolation steps. In our previous work, 3 we addressed in part the issue of plan recovery when both reactively and adaptively coping with emergent situations in the presence of uncertainties and dynamics. In this article, the MAS views robot components as interacting agent entities and allows flexible and efficient coordination between robot sensors and actuators, which increases the run-time feedback for plan execution monitoring.…”

<i>AutoRobot</i>: A Multi-Agent Software Framework for Autonomous Robots

“…To discuss the strengths and weaknesses of our framework AutoRobot, we establish a conceptual framework to compare AutoRobot and the other software frameworks mentioned above [28]. In the context of a robotic software framework, here, a platform for the implementation of ARS via an integral and concrete production of software engineering methodologies, tools and libraries, we present three categories of criteria for comparison that cover support for ARS, software engineering characteristics and platform supports.…”

Concepts of a Modular System Architecture for Distributed Robotic Systems

“…Yang et al [18] outline a high-level software architecture. The robot's software architecture is distributed into a reactive layer, where sensing and acting with the environment is done on an adaptive layer.…”