Figure 2 - uploaded by Joseph Jones
Content may be subject to copyright.
Rug Warrior was an early floor-cleaning robot. It possessed a simple carpet sweeping mechanism for cleaning, a full coverage bump sensor to allow escape from collisions, and drive wheel-mounted shaft encoders that enabled the robot to follow a simple cleaning pattern. A behavior-based program running on a low-cost microprocessor controlled the robot.
Source publication
Consumer robotics has achieved its first significant commercial success with the arrival of the iRobot Roomba Robotic Floorvac. Roomba has succeeded in the marketplace where other robots failed or feared to tread. Like many good products, Roomba has been rewarded for putting customer's interests first. Roomba accomplishes a task customers care abou...
Context in source publication
Context 1
... own efforts in the AI Olympics resulted in the floor- sweeping robot, Rug Warrior, shown in Figure 2. Although Rug Warrior lacked the robustness and reliability necessary for a consumer product, it provided a promising demonstra- tion that a small, uncomplicated device might be able to clean ...
Citations
... Once position of the person is estimated accurately, it's time to plan the path for DARwIn-OP to reach the person. For this purpose, the proposed architecture relies on the LiDAR based mapping by a two-wheeled differential drive smart home appliance Roomba [15]. Out of many accurate ways exist, this paper uses Cartographer SLAM [16] to build the indoor environment map in ROS. ...
... Mobile robots play a key role in industrial (e.g., warehouse robots in logistics [1]) and domestic (e.g., service robots for household [2]) automation. Due to their simplicity, high maneuverability and ease of control and maintenance, differential drive robots that can be modelled as a simple kinematic unicycle become a standard choice as a mobile robot base for many such application settings [3]. ...
... The unicycle forward motion control u y in (2) asymptotically brings all unicycle poses px, θq in R 2ˆr´π , πq to any given goal position y P R 2 , i.e., the closed-loop unicycle trajectory pxptq, θptqq satisfies lim tÑ8 xptq " y. ...
... Lemma 2 (Euclidean Distance to Goal) Under the unicycle forward motion control u y in (2), the Euclidean distance }x´y} of any unicycle pose px, θq P R 2ˆr´π , πq to any given goal position y P R 2 is decreasing over time, i.e., ...
As a simple and robust mobile robot base, differential drive robots that can be modelled as a kinematic unicycle find significant applications in logistics and service robotics in both industrial and domestic settings. Safe robot navigation around obstacles is an essential skill for such unicycle robots to perform diverse useful tasks in complex cluttered environments, especially around people and other robots. In this paper, as a more accurate alternative to the standard circular Lyapunov level sets, we introduce novel conic feedback motion prediction methods for bounding the close-loop motion trajectory of the kinematic unicycle robot model under a standard unicycle motion control approach. We present an application of unicycle feedback motion prediction for safe robot navigation using a reference governor, where the safety of the unicycle motion is continuously monitored based on the predicted robot motion. We investigate the role of motion prediction on robot behaviour in numerical simulations and conclude that accurate feedback motion prediction is key for safe and fast robot navigation.
... It will lead to more successful applications of insect-inspired AI to complex, real-world tasks. Of course, there are already such applications, with as most compelling example the Roomba robotic vacuum cleaner, which performed a biology-inspired random walk to cover the floor of a room [170]. We hope that advances in insect-inspired navigation will allow for more complex and spatially extended tasks, and stimulate the production and availability of sensing and computing hardware specifically tailored to the autonomous navigation of small robots. ...
Autonomous robots are expected to perform a wide range of sophisticated tasks in complex, unknown environments. However, available onboard computing capabilities and algorithms represent a considerable obstacle to reaching higher levels of autonomy, especially as robots get smaller and the end of Moore's law approaches. Here, we argue that inspiration from insect intelligence is a promising alternative to classic methods in robotics for the artificial intelligence (AI) needed for the autonomy of small, mobile robots. The advantage of insect intelligence stems from its resource efficiency (or parsimony) especially in terms of power and mass. First, we discuss the main aspects of insect intelligence underlying this parsimony: embodiment, sensory-motor coordination, and swarming. Then, we take stock of where insect-inspired AI stands as an alternative to other approaches to important robotic tasks such as navigation and identify open challenges on the road to its more widespread adoption. Last, we reflect on the types of processors that are suitable for implementing insect-inspired AI, from more traditional ones such as microcontrollers and field-programmable gate arrays to unconventional neuromorphic processors. We argue that even for neuromorphic processors, one should not simply apply existing AI algorithms but exploit insights from natural insect intelligence to get maximally efficient AI for robot autonomy.
... Developments of cleaning robots in diverse cleaning applications such as floor cleaning [5], wall cleaning [6], window cleaning [7], staircase cleaning [8], and garden cleaning [9] can be observed. Among these applications, many consumer products targeted for floor cleaning have been developed since floor cleaning is more often essential [10]. This paper proposes the concept "design by robot," which enables a floor cleaning robot to suggest modification for the workspace to improve area coverage performance. ...
... This approach was adopted because the robot was not deployed together with humans, therefore the only option was to implement an indirect intervention. A non-healthcare example of this type of indirect support is the iRobot Roomba [44], a robotic vacuum cleaner, which uses a low-tech implementation to facilitate human life by removing the effort to perform a very specific task. Examples of more direct support are smart walkers. ...
Over the last two decades, several deployments of robots for in-house assistance of older adults have been trialled. However, these solutions are mostly prototypes and remain unused in real-life scenarios. In this work, we review the historical and current landscape of the field, to try and understand why robots have yet to succeed as personal assistants in daily life. Our analysis focuses on two complementary aspects: the capabilities of the physical platform and the logic of the deployment. The former analysis shows regularities in hardware configurations and functionalities, leading to the definition of a set of six application-level capabilities ( exploration , identification , remote control , communication , manipulation , and digital situatedness ). The latter focuses on the impact of robots on the daily life of users and categorises the deployment of robots for healthcare interventions using three types of services: support , mitigation , and response . Our investigation reveals that the value of healthcare interventions is limited by a stagnation of functionalities and a disconnection between the robotic platform and the design of the intervention. To address this issue, we propose a novel co-design toolkit, which uses an ecological framework for robot interventions in the healthcare domain. Our approach connects robot capabilities with known geriatric factors, to create a holistic view encompassing both the physical platform and the logic of the deployment. As a case study-based validation, we discuss the use of the toolkit in the pre-design of the robotic platform for an pilot intervention, part of the EU large-scale pilot of the EU H2020 GATEKEEPER project.
... If you ask most people, robotics researchers included, to name a commercially successful consumer robot, it is likely that iRobot's automatic vacuum cleaner-the Roomba-will come to mind. In fact, the Roomba has been heralded in literature as one of the only consumer robot successes [12]. Other examples may take considerably more effort to recall, if they are recalled at all. ...
... While there is a modest body of research on home robots (their design, perception, and use), there is nearly no research on how these robots might be specifically designed, adopted, or analyzed from the perspective of consumer marketplace success. Two exceptions are work by Kwak et al. [14] and Jones [12]. Jones [12] illustrates how home robots should be simplified for consumers, foregoing non-essential elements, in order to reduce both cost and technical complexity. ...
... Two exceptions are work by Kwak et al. [14] and Jones [12]. Jones [12] illustrates how home robots should be simplified for consumers, foregoing non-essential elements, in order to reduce both cost and technical complexity. It also stresses that the application is the most important aspect to consider when designing home robots [12]. ...
Recent high-profile failures of domestic robotic products suggest more research is needed on factors that impact consumers’ willingness to purchase robots, and the success rates of the consumer robotics industry compared with other innovative technologies. Using data from two crowdfunding sites (Kickstarter and Indiegogo), we summarize the applications, forms, prices, contexts of use, target populations, and sociality of potential consumer and home robots. We then use statistical analysis, predictive modeling, and word co-occurrence to determine which characteristics are associated with increased product support by early market consumers, finding that health and fitness, security and monitoring, and general education applications, cartoon-like and animal-like robot forms, and single user group robots have significantly more backers. We also find that social robots have a mean of 1.2–3.2 times as many backers as non-social robots and that every twofold increase in price results in a 20% decrease in financial supporters. Product reviews from these sites are additionally used to identify product features consumers found important. Finally, analyses of the failure rates of social and home robots find that these products are not failing more frequently than other innovative products overall. This research is among the first to study factors influencing consumers’ purchasing behavior of home robots, and to use data mining methods to gain insights into home and consumer robot design.
... It however is used to model differential wheeled vehicles which move in two dimensions with two coaxial independently driven wheels. This encompasses systems such as the popular Roomba vacuum cleaning robot [11], Segway self-balancing transporter [12], Pioneer 3-DX (Adept Technology, Amherst, NH), etc. It is also used to represent the kinematics of a simple car [13]. ...
Point-to-point path planning for a kinematic model of a differential-drive wheeled mobile robot (WMR) with the goal of minimizing input energy is the focus of this work. An optimal control problem is formulated to determine the necessary conditions for optimality and the resulting two point boundary value problem is solved in closed form using Jacobi elliptic functions. The resulting nonlinear programming problem is solved for two variables and the results are compared to the traditional shooting method to illustrate that the Jacobi elliptic functions parameterize the exact profile of the optimal trajectory. A set of terminal constraints which lie on a circle in the first quadrant are used to generate a set of optimal solutions. It is noted that for maneuvers where the angle of the vector connecting the initial and terminal point is greater than a threshold, which is a function of the radius of the terminal constraint circle, the robot initially moves into the third quadrant before terminating in the first quadrant. The minimum energy solution is compared to two other optimal control formulations: (1) an extension of the Dubins vehicle model where the constant linear velocity of the robot is optimized for and (2) a simple turn and move solution, both of whose optimal paths lie entirely in the first quadrant. Experimental results are used to validate the optimal trajectories of the differential-drive robot.
... It was not until 20 years after the first mobile robots emerged in the decade of 1940 [9], that Shakey, a general-purpose mobile robot, capable of reasoning about its own actions, was built [10]. Since then, many mobile robots have been developed for a wide variety of applications [11][12][13][14]. ...
Simultaneous localization and mapping responds to the problem of building a map of the environment without any prior information and based on the data obtained from one or more sensors. In most situations, the robot is driven by a human operator, but some systems are capable of navigating autonomously while mapping, which is called native simultaneous localization and mapping. This strategy focuses on actively calculating the trajectories to explore the environment while building a map with a minimum error. In this paper, a comprehensive review of the research work developed in this field is provided, targeting the most relevant contributions in indoor mobile robotics.
... The technology employed in domestic cleaning robots has developed rapidly. The first Roomba was introduced in 2002, giving iRobot, its manufacturer, 16 years of experience in this application (Jones 2006). The obstacle avoidance function of the Roomba has progressed from front-end collision detection to using a 360°infrared camera for determining the distance to obstacles (the Roomba 960). ...
The cleaning of large-scale indoor public spaces is currently performed by workers driving cleaning machines. However, labor shortages are becoming more acute, resulting in human labor being substituted with robotics solutions for the cleaning of large public facilities (e.g., airport terminals, stations, and underground commercial streets). With the rapid development of sensing and automation technologies, various types of large-scale cleaning robots have been proposed. However, due to difficulty in precise indoor positioning, cleaning along a preplanned path is still challenging for robots. Therefore, this study proposes a cleaning robot that maps large indoor spaces using laser scanning and can avoid obstacles. The chassis of the robot has two independent primary wheels and two auxiliary wheels as power and support; direct current (DC) is employed to power the vacuum cleaner and the robot’s drive motor, to prevent power loss due to DC–alternating current conversion. An indoor facility undergoes three-dimensional laser scanning, and the cleaning space is then mapped through matrix graphics; subsequently, a path is planned using the boustrophedon method. The distance to the wall, measured by the laser rangefinder, is employed as a reference for the correction of the robot’s movement. The powerful vacuum cleaner design of the proposed cleaning robot was experimentally confirmed as having the ability to suction trash. In addition, the proposed robot was shown to clearly identify obstacles through laser scanning and successfully avoid them during the cleaning process to complete the cleaning task along the preplanned cleaning route.
... Since the first mass-produced domestic robot Roomba became commercially available in 2002 [62], cleaning robots and robotic lawnmowers took over chores in many private households [60]. In professional settings, service robots relieve humans from mundane and repetitive tasks like industrial robots have for decades. ...
Roboter führen heutzutage hauptsächlich repetitive Aufgaben im industriellen Kontext aus und agieren in speziell auf sie zugeschnittenen Anlagen. Doch die Nachfrage nach flexiblen Servicerobotern, die in unmittelbarer Nähe zum Menschen eingesetzt werden können, steigt stetig. Dieser Trend geht mit einer Vielzahl von Herausforderungen einher. Einsatzgebiete, die auf den Menschen ausgerichtet sind, wie Wohnbereiche, Büros, Krankenhäuser oder Flughäfen, sind oft unstrukturiert und verändern sich mit der Zeit. Außerdem treffen Roboter in Wohnbereichen und öffentlichen Räumen auf eine Vielzahl von Menschen mit unterschiedlichen Bedürfnissen und Präferenzen. Die meisten dieser Menschen haben wenig Erfahrung mit Robotern. Zusätzlich müssen die Anschaffungs- und Wartungskosten von Servicerobotern um Größenordnungen niedriger sein als für Industrieroboter, um für einen großflächigen Einsatz wirtschaftlich zu sein. Diese Herausforderungen erfordern ein höheres Maß an Autonomie und Flexibilität und verlangen, dass Serviceroboter sich kontinuierlich an ihre Umgebung anpassen und auf die Menschen, mit denen sie interagieren, eingehen.
In dieser Doktorarbeit werden Perzeptionsmethoden und Ansätze des maschinellen Lernens für den Einsatz mobiler Roboter in auf Menschen ausgelegten Arbeitsbereichen vorgestellt. Zunächst präsentieren wir eine Bildverarbeitungsmethode zur Erkennung von Menschen, die diese zusätzlich anhand ihrer Mobilitätshilfen unterscheidet. Mithilfe der erweiterten Personenerkennung können Roboter individuelle Einschränkungen und Anforderungen von Menschen wahrnehmen und sie so bedürfnisgerecht unterstützen. Des Weiteren stellen wir ein Ganzkörpersensorikkonzept vor, mit dem mobile Roboter Kollisionen und Interaktionskräfte wahrnehmen können. Aufgrund der hohen Dynamik und fehlenden Struktur ihrer Arbeitsbereiche und einer typischerweise eingeschränkten Sensorabdeckung können viele mobile Serviceroboter Kollisionen und unbeabsichtigte Kontakte mit Hindernissen oder Personen nicht vollständig ausschließen. Unser Sensoraufbau basiert auf einem zentral montierten Kraft-Momenten-Sensor und ermöglicht es mobilen Robotern, solche Kontakte wahrzunehmen und angemessen auf sie zu reagieren, um Schäden zu vermeiden. Aufbauend auf dem Kraftwahrnehmungskonzept stellen wir einen lernbasierten Ansatz vor zur Vorhersage von Kollisionen in 2D-Umgebungskarten, die auf Daten planarer Laserscanner basieren. Unser Ansatz interpretiert unerwünschte Kollisionen als Trainingsbeispiele, sodass mobile Roboter mit der Zeit verbesserte Umgebungsmodelle erlernen können. Abschließend untersuchen wir, wie Menschen einem kraftnachgiebigen mobilen Roboter soziale Navigation beibringen können, indem sie ihn entlang ihrer gewünschten Trajektorien schieben. Basierend auf der Interaktion passt der Roboter seine Navigationsfunktion mithilfe von Inverse Reinforcement Learning an. Da kraftnachgiebige Steuerung auch für Laien einfach umzusetzen ist und kein externes Steuergerät benötigt wird, kann jeder in Reichweite des Roboters mit ihm interagieren.
Die vorgestellten Ansätze wurden in umfangreichen Experimenten mit besonderem Fokus auf realitätsnahe Szenarien evaluiert. Die Experimente zeigen, wie mobile Roboter, die die spezifischen Bedürfnisse und Anforderungen von Menschen wahrnehmen können, diese besser unterstützen können. Sie bestätigen weiterhin, dass mobile Roboter durch die gezeigten Ansätze bessere Umgebungsmodelle erlernen und auf die individuellen Vorlieben von Menschen eingehen können. Diese Arbeit ist somit ein wichtiger Schritt auf dem Weg zu flexiblen, autonomen Servicerobotern, die robust und zuverlässig in auf den Menschen ausgerichteten Arbeitsbereichen agieren können.
