Robot Perception of Static and Dynamic Objects with an Autonomous Floor Scrubber

Abstract

This paper presents the perception system of a new professional cleaning robot for large public places. The proposed system is based on multiple sensors including 3D and 2D lidar, two RGB-D cameras and a stereo camera. The two lidars together with an RGB-D camera are used for dynamic object (human) detection and tracking, while the second RGB-D and stereo camera are used for detection of static objects (dirt and ground objects). A learning and reasoning module for spatial-temporal representation of the environment based on the perception pipeline is also introduced. Furthermore, a new dataset collected with the robot in several public places, including a supermarket, a warehouse and an airport, is released. Baseline results on this dataset for further research and comparison are provided. The proposed system has been fully implemented into the Robot Operating System (ROS) with high modularity, also publicly available to the community. KeywordsRobot perception • Human detection and tracking • Object and dirt detection • Spatial-temporal representation • Dataset • ROS

Design of the Integrated Cognitive Perception Model for Developing Situation-Awareness of an Autonomous Smart Agent

“…Evren Daglarli T patterns like objects, faces, and spoken words. Accomplishing higher-level cognitive abilities to effectively respond to multimodal perceptual stimuli, engage in pattern recognition, model attention, and exhibit environmental awareness presents a challenging task [1,19,20]. Developing perceptual models that represent the environment of an autonomous system, including spatial world models and the interaction of physical behavior models, is among the significant challenges faced [17][18][19][20].…”

“…HE ABILITY to engage with their environment through perception is vital not just for humans but also for autonomous systems equipped with intelligent agents. These abilities rely on representations of the world model in terms of spatial and temporal, as well as perceptual cognition, situation awareness and attentional capabilities [1]. In biological systems, the cortical and cerebral lobes of the human brain play a significant role in providing these functions and characteristics.…”

“…Hence, it is necessary for these systems to be endowed with a perceptual system resembling that of humans, enabling them to interpret and sustain representations of the world model. Furthermore, they should be able to assess human-machine interaction through shared attention within a collaborative workspace [1,14,15]. Spatial cognition involves being aware of one's environment, encompassing the perception of objects in terms of their spatial aspects such as positions, orientations, distances, and movements [1,[16][17][18].…”

“…Furthermore, they should be able to assess human-machine interaction through shared attention within a collaborative workspace [1,14,15]. Spatial cognition involves being aware of one's environment, encompassing the perception of objects in terms of their spatial aspects such as positions, orientations, distances, and movements [1,[16][17][18]. On the other hand, temporal cognition focuses on the intermediate processes that involve encoding non-spatial or temporal characteristics of objects, such as color and shape, as well as recognizing…”