Figure 2 - uploaded by Éric Beaudry
Content may be subject to copyright.
Source publication
Integration of hardware, software and decisional components is fundamental in the design of advanced mobile robotic systems capable of performing challenging tasks in unstructured and unpredictable environments. We address such integration challenges following an iterative design strategy, centered on a decisional architecture based on the notion o...
Context in source publication
Context 1
... capabilities; 2 ) natural inter- action modalities in open settings; 3 ) adaptation to environmental changes for localization; and 4 ) monitoring / reporting decisions made by the robot [ 13, 30, 18, 29 ] . Trials conducted at the 2005 AAAI event helped establish new require- ments for providing meaningful and appropri- ate modalities for reporting and monitoring the robot’s states and experiences. When operating in open settings, interactions are rapid, diverse and context-related. Having an autonomous robot determining on its own when and what it has to do based on a variety of modalities ( time constraints, events occurring in the world, requests from users, etc. ) also makes it difficult to understand the robot’s behavior just by looking at it. Therefore, we concentrated our integration effort in 2006 to design a robot that can interact and explain, through speech and graphical displays, its decisions and its ex- periences as they occur ( for on-line and off-line diagnostics ) in open settings. This paper first presents the software / hardware components of our 2006 AAAI robot entry, its software and decisional architectures, the technical demon- stration made at the conference along with the interfaces developed for reporting the robot’s experiences. This outlines the progress made so far in addressing the integration challenge of designing autonomous robots. The paper then describes the design specification of our new advanced mobile robot platform, derived from what we have identified as critical elements in making autonomous systems operating in eve- ryday environments. Our 2006 AAAI robot entry, shown in Fig- ure 1, is a custom-built robot equipped with a SICK LMS200 laser range finder, a Sony SNC-RZ30N 25X pan-tilt-zoom color camera, a Crossbow IMU400CC inertial measurement unit, an array of eight microphones placed in the robot’s body, a touch screen interface, an audio system, one on-board computer and two laptop computers. The robot is equipped with a business card dispenser, which is part of the robot’s interaction modalities. A small cam- era ( not shown in the picture ) was added on the robot’s base to allow the robot to detect the pres- ence of electric outlets. The technique used is based on a cascade of boosted classifiers work- ing with Haar-like features [ 17 ] and a rule-based analysis of the images. Figure 2 illustrates the robot’s software architec- ture. It integrates Player for sensor and actuator abstraction layer [ 34 ] and CARMEN ( Carnegie Mellon Robot Navigation Toolkit ) for path plan- ning and localization [ 24 ] . Also integrated but not shown in the Figure is Stage / Gazebo for 1 2D and 3D simulators, and Pmap library for 2D mapping, all designed at the University of Southern California. RobotFlow and FlowDe- signer ( FD ) [ 8 ] are also used to implement the behavior-producing modules, the vision ...
Similar publications
Mobile service robots are recently gaining increased attention from industry as they are envisaged as a future market. Such robots need natural interaction capa-bilities to allow unexperienced users to make use of these robots in home and office environments. In order to enable the interaction between humans and a robot, the de-tection and tracking...
Using robots in the world is gaining a part in the discussion about technology, with several applications scenarios. Human-Robot Interaction (HRI) is crucial on the process of understanding and creating machines, which will communicate using voice as main factor. Speech communication is used to receive commands, actions and tasks, or to locate a us...
Integration of hardware, software and decisional components is fundamental in the design of advanced mobile robotic systems capable of performing challenging tasks in unstructured and unpredictable environments. We address such integration challenges following an iterative design strategy, centered on a decisional architecture based on the notion o...
Citations
... ROS4iOS [11] is also an environment integrating speech recognition (PocketSphinx [12]) and speaker identification (WISS [13]). What is missing from these implementations is the ability to manage dialogs, as demonstrated using the CSLU (Center for Spoken Language Understanding) toolkit [14], [15] integrated to the ManyEars [16] open source framework (also interfaced with ROS). -Using visualization modalities to represent live sound and speech interactions in simple and meaningful ways. ...
... -Using visualization modalities to represent live sound and speech interactions in simple and meaningful ways. The usual tools available for online or offline representations of sound sources represent their position over time [16], [6], with some also taking images when recording to provide additional contextual information [14]. Using a wide-angle camera, localization direction and intensity of sound sources can also be displayed in the image [6]. ...
Audition is a rich source of spatial, identity, linguistic and paralinguistic information. Processing all this information requires acquisition, processing and interpretation of sound sources, which are instantaneous, invisible and noisy signals. This can lead to different responses by the system in relation to the information perceived. This paper presents our first implementation of an integration framework for speech processing. Acquisition includes sound capture, sound source localization, tracking, separation and enhancement, and voice activity detection. Processing involves speech and emotion recognition. Interpretation consists of translating speech utterances into commands that can influence interaction through dialogue management and speech synthesis. The paper also describes two visualization interfaces, inspired by comic strips, to represent live vocal interactions in real life environments. These interfaces are used to demonstrate how the framework performs in live interactions and its use in a usability study.
... ROS4iOS [11] is also an environment integrating speech recognition (PocketSphinx [12]) and speaker identification (WISS [13]). What is missing from these implementations is the ability to manage dialogs, as demonstrated using the CSLU (Center for Spoken Language Understanding) toolkit [14], [15] integrated to the ManyEars [16] open source framework (also interfaced with ROS). -Using visualization modalities to represent live sound and speech interactions in simple and meaningful ways. ...
... -Using visualization modalities to represent live sound and speech interactions in simple and meaningful ways. The usual tools available for online or offline representations of sound sources represent their position over time [16], [6], with some also taking images when recording to provide additional contextual information [14]. Using a wide-angle camera, localization direction and intensity of sound sources can also be displayed in the image [6]. ...
Representing the location of sound sources may be helpful when teleoperating a mobile robot. To evaluate this modality, we conducted trials in which the graphical user interface (GUI) displays a blue right icon on the video stream where the sound is located. Results show that such visualization modality provides a clear benefit when a user has to distinguish between multiple sound sources.
... • Computer 2 runs the CSLU Toolkit for dialogue management. • Computer 3 hosts the decision-making processes of the robot, described in details in [20]. Figure 3 shows the Spartacus robot used in the trials. ...
To demonstrate the influence of an artificial audition system on speech recognition and dialogue management for a robot, this paper presents a case study involving soft coupling of ManyEars, a sound source localization, tracking and separation system, with the CSLU Dialogue Management system. Trials were conducted in a laboratory and a cafeteria. Results indicate that preprocessing of the audio signals by ManyEars improves speech recognition and dialogue management of the system, demonstrating the feasibility and the added flexibility provided by ManyEars for a robot to interact vocally with humans in a wide variety of contexts.
... We are currently investigating the use of the path planning packages found in the full ROS navigation stack. Future work will focus on incremental integration of higher level functions (e.g., SLAM, vision, artificial audition, autonomous decisional architecture) on an interactive humanoid robot [9]. ...
AZIMUT-3 is an omnidirectional non-holonomic (or pseudo-omnidirectional) robotic platform intended for safe human-robot interaction. In its wheeled configuration, shown in Fig. 1, AZIMUT-3 uses eight actuators for locomotion: four for propulsion and four for steering the wheels, which can rotate 180 degrees around their steering axis. Propulsion is done using standard DC brushless motors (Bayside K064050-3Y) with optical encoders (US Digital E4-300-157-HUB, 0.3 deg of resolution), capable of reaching 1.47 m/s. The platform uses steerable wheels motorized using differential elastic actuators (DEA), which provide compliance, safety and torque control capabilities. AZIMUT-3's hardware architecture consists of distributed modules for sensing and low-level control, communicating with each other through a 1 Mbps CAN bus. A Mini-ITX computer equipped with a 2.0 GHz Core 2 duo processor running Linux with real-time patches (RT-PREEMPT) is used on-board for high-level control modules. Nickel-metal hydride batteries provide power to the platform for up to 3 hours of autonomy. A passive vertical suspension mechanism (Rosta springs) is used to connect the wheels to AZIMUT-3's chassis, allowing them to keep contact with the ground on uneven surfaces. The platform has a 34 kg payload capacity and weights 35 kg.
... ture used to integrate all necessary decisional capabilities of an autonomous robot [8]. It was implemented on a Pioneer 2 robot entry in the 2000 AAAI Mobile Robot Challenge. A robot had to start at the entrance of the conference site, find the registration desk, register, perform volunteer duties (e.g., guard an area) and give a presentation [9]. [15]. Our 2006 implementation showed increased reliability and capabilities of MBA. Our planner is capable of dealing with temporal constraints violation, task cancellation, unknown waypoint that would occur in real-life settings and within a computational architecture using distributed modules (compared to architectures with one centralized ...
... To our knowledge though, none has yet been used to validate a specific high-level architecture. With Johnny-0 however , the objective is to build from our past experience with our previous high-level architectures (ISB – Intentional Selection of Behaviors [49], EMIB – Emotion, Motivation and Intentional Behaviors [8] , MBA – Motivated Behavioral Architecture [11, 12, 15]) and experiment with a novel conceptual framework named HBBA – Hybrid Behavior-Based Architecture . HBBA combines both hybrid and behavior-based paradigms.Figure 4 illustrates the architecture in which behaviors are the basic control components. ...
The field of robotics has made steady progress in the pursuit of bringing autonomous machines into real-life settings. Over
the last 3 years, we have seen omnidirectional humanoid platforms that now bring compliance, robustness and adaptiveness to
handle the unconstrained situations of the real world. However, today’s contributions mostly address only a portion of the
physical, cognitive or evaluative dimensions, which are all interdependent. This paper presents an overview of our attempt
to integrate as a whole all three dimensions into a robot named Johnny-0. We present Johnny-0’s distinct contributions in
simultaneously exploiting compliance at the locomotion level, in grounding reasoning and actions through behaviors, and in
considering all possible factors experimenting in the wildness of the real world.
Keywordsomnidirectionality-compliance-architecture-evaluation in the wild
