This paper presents elastodynamic modeling and analysis for a five-axis lightweight robotic arm. Natural frequencies are derived and visualized within the dexterous workspace to show the overall performances and compare them to the frequencies when the robotics is with payload. The comparison shows that the payload has a relatively small influence to the first- and second-order frequencies. Sensitivity analysis is conducted, and the system's frequency is more sensitive to the second joint stiffness than the others. Moreover, observations from the displacement response analysis reveal that the robotics produces linear elastic displacements of the same level between the loaded and unloaded working modes but larger rotational deflections under the loaded working condition. The main contribution of this work lies in that a systematic approach of elastodynamic analysis for serial robotic manipulators is formulated, where the arm gravity and external load are taken into account to investigate the dynamic behaviors of the robotic arms, i.e., frequencies, sensitivity analysis, and displacement responses, under the loaded mode.

Autonomous mobile robotic agents are increasingly present in highly dynamic environments, thus making the planning and execution of their tasks challenging. Task planning is vital in directing the actions of a robotic agent in domains where a causal chain could lock the agent into a dead-end state. This paper proposes a framework that integrates a domain ontology (home environment ontology) with a task planner (ROSPlan) to translate the objectives coming from a given agent (robot or human) into executable actions by a robotic agent.

In this paper, sliding mode control is combined with the classical simultaneous localization and mapping (SLAM) method. This combination can overcome the problem of bounded uncertainties in SLAM. With the help of genetic algorithm, our novel path planning method shows many advantages compared with other popular methods.

Rail track is a critical component of rail systems. Accidents or interruptions caused by rail track anomalies usually possess severe outcomes. Therefore, rail track condition monitoring is an important task. Over the past decade, deep learning techniques have been rapidly developed and deployed. In the paper, we review the existing literature on applying deep learning to rail track condition monitoring. Potential challenges and opportunities are discussed for the research community to decide on possible directions. Two application cases are presented to illustrate the implementation of deep learning to rail track condition monitoring in practice before we conclude the paper.