By Topic

Robotics and Automation (ICRA), 2013 IEEE International Conference on

Date 6-10 May 2013

Filter Results

Displaying Results 1 - 25 of 873
  • Instantaneous control of a vertically hopping leg's total step-time

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (637 KB) |  | HTML iconHTML  

    The main contribution of this paper is a new step-time controller for a vertically hopping robot leg capable of meeting a demanded step-time instantaneously, meaning within a single hop. The ability to perform hops of an arbitrary and changing size accurately forms the motivation behind the work done here. This would allow control of a running robot's foot placement and thus fast traversal of terrain with limited safe foot placement spots. In this paper, the hopping controller is developed and validated using an articulated, hydraulically actuated leg from the HyQ robot which has been modified to include an elastic foot and constrained to hop vertically. It is shown that instantaneous control over the step-time can be achieved using only joint positions and ground contact senses. This was achieved with a simple feedforward lookup in combination with a proportional and integral action. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Minimalistic models of an energy efficient vertical hopping robot

    Page(s): 7 - 12
    Multimedia
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1638 KB) |  | HTML iconHTML  

    The use of free vibration in elastic structure can lead to energy efficient robot locomotion, since it significantly reduces the energy expenditure if properly designed and controlled. However, it is not well understood how to harness the dynamics of free vibration for the robot locomotion, because of the complex dynamics originated in discrete events and energy dissipation during locomotion. From this perspective, this paper explores three minimalistic models of free vibration that can characterize the basic principle of robot locomotion. Since the robot mainly exhibits vertical hopping, three one-dimensional models are examined that contain different configurations of simple spring-damper-mass components. The self-stability of these models are also investigated in simulation. The real-world and simulation experiments show that one of the models best characterizes the robot hopping, through analyzing the basic kinematics and negative works in actuation. Based on this model, the control parameters are analyzed for the energy efficient hopping. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A novel one-motor driven robot that jumps and walks

    Page(s): 13 - 19
    Multimedia
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2406 KB) |  | HTML iconHTML  

    This paper presents a 10 cm × 5 cm × 5 cm, 52 g one-motor driven robot. One DC motor with a driving gear drives two driven gears to implement the functions of jumping and walking. Two one-way bearings mounted on the inner races of the two driven gears are used to switch between jumping and walking when the motor rotates clockwise and anticlockwise respectively. The jumping energy is obtained by compressing and releasing two torsion springs using a cylindrical cam with quick return characteristics. Two disk cams drive two forelegs with elastic joints to step forward one after another to implement the walking locomotion pattern. Two connecting rods link the forelegs and the rear legs on the left and right sides of the robot to transmit motions from forelegs to rear legs. The jumping and walking performances of the robot are tested. Experimental results show that the proposed robot can jump more than 33 cm high at a takeoff angle of 71.2° and it can walk forward at 1.43 mm/s. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • STAR, a sprawl tuned autonomous robot

    Page(s): 20 - 25
    Multimedia
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1283 KB) |  | HTML iconHTML  

    This paper presents a six-legged, sprawl-tuned autonomous robot (STAR). This novel robot has a variable leg sprawl angle in the transverse plane to adapt its stiffness, height, and leg-to-surface contact angle. The sprawl angle can be varied from nearly positive 60 degrees to negative 90 degrees, enabling the robot to run in a planar configuration, upright, or inverted (see movie). STAR is fitted with spoke wheel-like legs which provide high electromechanical conversion efficiency and enable the robot to achieve legged performance over rough surfaces and obstacles, using a high sprawl angle, and nearly wheel-like performance over smooth surfaces for small sprawl angles. Our model and experiments show that the contact angle and normal contact forces are substantially reduced when the sprawl angle is low, and the velocity increases over smooth surfaces, with stable running at all velocities up to 5.2m/s and a Froude number of 9.8. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Flea inspired catapult mechanism with active energy storage and release for small scale jumping robot

    Page(s): 26 - 31
    Multimedia
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (845 KB) |  | HTML iconHTML  

    Fleas have a unique catapult mechanism with a special muscle configuration. Energy is stored in an elastic material, resilin, and the extensor muscle. Force is applied by the extensor muscle to generate a torque. Energy is released as a small triggering muscle reverses the direction of the aforementioned torque. A flea can jump 150 times its body length using this elastic catapult mechanism. In this paper, a flea-inspired catapult mechanism is presented. This mechanism can be categorized as an active storage and active release elastic catapult. Owing to its unique stiffness change characteristic, a shape-memory-alloy coil spring actuator enables the mimicking of the flea's catapult mechanism. Two types of flea-inspired jumping mechanisms were developed for verifying the feasibility of applying the concept to an efficient jumping robot. The first prototype has a flea-like appearance and the second is simplified to contain just the essential components of the flea-inspired catapult mechanism. The two prototypes are 20-mm- and 30-mm-long and can jump 64 cm and 120 cm, respectively. This unique catapult mechanism can be used not only for jumping robots but also for other small-sized robots to generate fast-releasing motion. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A nonlinear feedback controller for aerial self-righting by a tailed robot

    Page(s): 32 - 39
    Multimedia
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1962 KB) |  | HTML iconHTML  

    In this work, we propose a control scheme for attitude control of a falling, two link active tailed robot with only two degrees of freedom of actuation. We derive a simplified expression for the robot's angular momentum and invert this expression to solve for the shape velocities that drive the body's angular momentum to a desired value. By choosing a body angular velocity vector parallel to the axis of error rotation, the controller steers the robot towards its desired orientation. The proposed scheme is accomplished through feedback laws as opposed to feedforward trajectory generation, is fairly robust to model uncertainties, and is simple enough to implement on a miniature microcontroller. We verify our approach by implementing the controller on a small (175 g) robot platform, enabling rapid maneuvers approaching the spectacular capability of animals. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Probabilistic surface matching for bathymetry based SLAM

    Page(s): 40 - 45
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2164 KB) |  | HTML iconHTML  

    This paper describes a probabilistic surface matching method for pose-based bathymetry SLAM using a multibeam sonar profiler. The proposed algorithm compounds swath profiles of the seafloor with dead reckoning localization to build surface patches. Then, a probabilistic implementation of the ICP is used to deal with the uncertainty of the robot pose as well as the measured points in a two-stage process including point-to-point and point-to-plane metrics. A novel surface adaptation using octrees is proposed to have ICP-derived methods working in feature-poor or highly unstructured areas typical of bathymetric scenarios. Moreover, a heuristic based on the uncertainties of the surface points is used to improve the basic algorithm, decreasing the ICP complexity to O(n). The performance of the method is demonstrated with real data from a bathymetric survey. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust vision-aided navigation using Sliding-Window Factor graphs

    Page(s): 46 - 53
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2534 KB) |  | HTML iconHTML  

    This paper proposes a navigation algorithm that provides a low-latency solution while estimating the full nonlinear navigation state. Our approach uses Sliding-Window Factor Graphs, which extend existing incremental smoothing methods to operate on the subset of measurements and states that exist inside a sliding time window. We split the estimation into a fast short-term smoother, a slower but fully global smoother, and a shared map of 3D landmarks. A novel three-stage visual feature model is presented that takes advantage of both smoothers to optimize the 3D landmark map, while minimizing the computation required for processing tracked features in the short-term smoother. This three-stage model is formulated based on the maturity of the estimation of the 3D location of the underlying landmark in the map. Long-range associations are used as global measurements from matured landmarks in the short-term smoother and loop closure constraints in the long-term smoother. Experimental results demonstrate our approach provides highly-accurate solutions on large-scale real data sets using multiple sensors in GPS-denied settings. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Temporally scalable visual SLAM using a reduced pose graph

    Page(s): 54 - 61
    Multimedia
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1464 KB) |  | HTML iconHTML  

    In this paper, we demonstrate a system for temporally scalable visual SLAM using a reduced pose graph representation. Unlike previous visual SLAM approaches that maintain static keyframes, our approach uses new measurements to continually improve the map, yet achieves efficiency by avoiding adding redundant frames and not using marginalization to reduce the graph. To evaluate our approach, we present results using an online binocular visual SLAM system that uses place recognition for both robustness and multi-session operation. Additionally, to enable large-scale indoor mapping, our system automatically detects elevator rides based on accelerometer data. We demonstrate long-term mapping in a large multi-floor building, using approximately nine hours of data collected over the course of six months. Our results illustrate the capability of our visual SLAM system to map a large are over extended period of time. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust map optimization using dynamic covariance scaling

    Page(s): 62 - 69
    Multimedia
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1103 KB) |  | HTML iconHTML  

    Developing the perfect SLAM front-end that produces graphs which are free of outliers is generally impossible due to perceptual aliasing. Therefore, optimization back-ends need to be able to deal with outliers resulting from an imperfect front-end. In this paper, we introduce dynamic covariance scaling, a novel approach for effective optimization of constraint networks under the presence of outliers. The key idea is to use a robust function that generalizes classical gating and dynamically rejects outliers without compromising convergence speed. We implemented and thoroughly evaluated our method on publicly available datasets. Compared to recently published state-of-the-art methods, we obtain a substantial speed up without increasing the number of variables in the optimization process. Our method can be easily integrated in almost any SLAM back-end. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sparser Relative Bundle Adjustment (SRBA): Constant-time maintenance and local optimization of arbitrarily large maps

    Page(s): 70 - 77
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1523 KB) |  | HTML iconHTML  

    In this paper we defend the superior scalability of the Relative Bundle Adjustment (RBA) framework for tackling with the SLAM problem. Although such a statement was already done with the introduction of the sliding window (SW) solution to RBA [16], we claim that the map extension that can be maintained locally consistent for some fixed computational cost critically depends on the specific pattern in which new keyframes are connected to previous ones. By rethinking from scratch what we call loop closures in relative coordinates we will show the unexploited flexibility of the RBA framework, which allows us a continuum of strategies from pure relative BA to hybrid submapping with local maps. In this work we derive a systematic way of constructing the problem graph which lies close to submapping and which generates graphs that can be solved more efficiently than those built as previously reported in the literature. As a necessary tool we also present an algorithm for incrementally updating all the spanning-trees demanded by any efficient solution to RBA. Under weak assumptions on the map, and implemented on carefully designed data structures, it is demonstrated to run in bounded time, no matter how large the map becomes. We also present experiments with a synthetic dataset of 55K keyframes in a world of 4.3M landmarks. Our C++ implementation has been released as open source. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automated model approximation for robotic navigation with POMDPs

    Page(s): 78 - 84
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (867 KB) |  | HTML iconHTML  

    Partially-Observable Markov Decision Processes (POMDPs) are a problem class with significant applicability to robotics when considering the uncertainty present in the real world, however, they quickly become intractable for large state and action spaces. A method to create a less complex but accurate action model approximation is proposed and evaluated using a state-of-the-art POMDP solver. We apply this general and powerful formulation to a robotic navigation task under state and sensing uncertainty. Results show that this method can provide a useful action model that yields a policy with similar overall expected reward compared to the true action model, often with significant computational savings. In some cases, our reduced complexity model can solve problems where the true model is too complex to find a policy that accomplishes the task. We conclude that this technique of building problem-dependent approximations can provide significant computational advantages and can help expand the complexity of problems that can be considered using current POMDP techniques. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A dynamic Bayesian approach to real-time estimation and filtering in grasp acquisition

    Page(s): 85 - 92
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1292 KB) |  | HTML iconHTML  

    In this work, we develop a general solution to a broad class of grasping and manipulation problems that we term as C-SLAM for contact simultaneous localization and modeling, where the robots need to accurately track the motions of the contacted bodies and the locations of contacts, while simultaneously estimating important system parameters, such as body dimensions, masses and friction coefficients between contacting surfaces. Our solution framework is based on a dynamic Bayesian inference framework, and hence, we refer to it as Dynamic Bayesian C-SLAM (DBC-SLAM). DBC-SLAM combines an NCP-based dynamic model with the dynamic Bayesian network, and incorporates model parameter estimation as an intrinsic part of the overall inference procedure. We show two preliminary “proof-of-concept” examples that demonstrate the use of DBC-SLAM in robotic contact tasks. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust grip force estimation under electric feedback using muscle stiffness and electromyography for powered prosthetic hand

    Page(s): 93 - 98
    Multimedia
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (519 KB) |  | HTML iconHTML  

    Powered prosthetic hands are becoming increasingly functional through sensory feedback. However, when using electrical stimulation as sensory feedback for electromyographic (EMG) prosthetics, stimulation artifacts may cause EMG data noise. Electrical stimulation and EMG measurements are therefore performed using time-division methods in rehabilitation facilities. Under time-division methods, EMG levels cannot be acquired at the stimulation time. Highly functional prosthetic hands that can estimate grip force, however, use advanced signal processing and require detailed EMG information. EMG measuring cycle expansion may make grip force estimation unstable. We therefore developed a grip force estimation system using muscle stiffness and EMG as the estimation source signals. The estimation system consists of a muscle stiffness sensor, an EMG sensor and an estimation algorithm. We chose a tray holding task for the system evaluation. A weight is dropped on the tray and subjects are expected to control the tray's attitude. Grip force, EMG, and muscle stiffness are measured, and the measured and estimated grip forces are compared. The proposed algorithm estimates grip force with an error of just 18[N], which is 30% smaller than in EMG-only methods. The system response time is lower than human mechanical reaction time, validating the effectiveness of the proposed method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The next best touch for model-based localization

    Page(s): 99 - 106
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2268 KB) |  | HTML iconHTML  

    This paper introduces a tactile or contact method whereby an autonomous robot equipped with suitable sensors can choose the next sensing action involving touch in order to accurately localize an object in its environment. The method uses an information gain metric based on the uncertainty of the object's pose to determine the next best touching action. Intuitively, the optimal action is the one that is the most informative. The action is then carried out and the state of the object's pose is updated using an estimator. The method is further extended to choose the most informative action to simultaneously localize and estimate the object's model parameter or model class. Results are presented both in simulation and in experiment on the DARPA Autonomous Robotic Manipulation Software (ARM-S) robot. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A sensorimotor account of visual and tactile integration for object categorization and grasping

    Page(s): 107 - 112
    Multimedia
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1445 KB) |  | HTML iconHTML  

    The fusion of tactile and visual modalities is crucial for understanding objects and learning how to manipulate them. A common modus operandi in robotics is to deal with each of these modalities separately. We propose an integrated approach that associates to local visual features of an object, tactile feedback of the effector when touching that part of the object. Thus the agent learns to predict from a visual scene the shape/curvature properties of the object. The associated curvature properties are directly linked to grasp possibilities (as in approaches like [1] and [2]) but can also provide the agent with object categorization regarding the distribution of curvature classes. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Uncertainty aware grasping and tactile exploration

    Page(s): 113 - 119
    Multimedia
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (976 KB) |  | HTML iconHTML  

    The perception of the surrounding world depends on noisy sensors which introduce uncertainty. When we develop algorithms for grasping with robotic hands it is not enough to assume the best estimate of the environment - if there is a measure of uncertainty we need to account for it. This paper presents a control law which augments a grasp controller with the ability to prefer known or unseen regions of an object; this leads to the introduction of two motion primitives: an explorative and exploitative grasp. We integrate this control law in a framework for iterative grasping and implement a tactile exploration scenario. The experimental results confirm that using the notion of uncertainty in the control loop yields better models and does it faster than an uninformed controller. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dual arm estimation for coordinated bimanual manipulation

    Page(s): 120 - 125
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1667 KB) |  | HTML iconHTML  

    This paper develops an estimation framework for sensor-guided dual-arm manipulation of a rigid object. Using an unscented Kalman Filter (UKF), the approach combines both visual and kinesthetic information to track both the manipulators and object. From visual updates of the object and manipulators, and tactile updates, the method estimates both the robot's internal state and the object's pose. Nonlinear constraints are incorporated into the framework to deal with the an additional arm and ensure the state is consistent. Two frameworks are compared in which the first framework run two single arm filters in parallel and the second consists of the augment dual arm filter with nonlinear constraints. Experiments on a wheel changing task are demonstrated using the DARPA ARM-S system, consisting of dual Barrett- WAM manipulators. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Embedding high-level information into low level vision: Efficient object search in clutter

    Page(s): 126 - 132
    Multimedia
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2065 KB) |  | HTML iconHTML  

    The ability to search visually for objects of interest in cluttered environments is crucial for robots performing tasks in a multitude of environments. In this work, we propose a novel visual search algorithm that integrates high-level information of the target object - specifically its size and shape, with a recently introduced visual operator that rapidly clusters potential edges based on their coherence in belonging to a possible object. The output is a set of fixation points that indicate the potential location of the target object in the image. The proposed approach outperforms purely bottom-up approaches - saliency maps of Itti et al. [15], and kernel descriptors of Bo et al. [2], over two large datasets of objects in clutter collected using an RGB-Depth camera. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient temporal consistency for streaming video scene analysis

    Page(s): 133 - 139
    Multimedia
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1427 KB) |  | HTML iconHTML  

    We address the problem of image-based scene analysis from streaming video, as would be seen from a moving platform, in order to efficiently generate spatially and temporally consistent predictions of semantic categories over time. In contrast to previous techniques which typically address this problem in batch and/or through graphical models, we demonstrate that by learning visual similarities between pixels across frames, a simple filtering algorithfiltering algorithmm is able to achieve high performance predictions in an efficient and online/causal manner. Our technique is a meta-algorithm that can be efficiently wrapped around any scene analysis technique that produces a per-pixel semantic category distribution. We validate our approach over three different scene analysis techniques on three different datasets that contain different semantic object categories. Our experiments demonstrate that our approach is very efficient in practice and substantially improves the consistency of the predictions over time. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3D spatial relationships for improving object detection

    Page(s): 140 - 147
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1185 KB) |  | HTML iconHTML  

    This work demonstrates how 3D qualitative spatial relationships can be used to improve object detection by differentiating between true and false positive detections. Our method identifies the most likely subset of 3D detections using seven types of 3D relationships and adjusts detection confidence scores to improve the average precision. A model is learned using a structured support vector machine [1] from examples of 3D layouts of objects in offices and kitchens. We test our method on synthetic detections to determine how factors such as localization accuracy, number of detections and detection scores change the effectiveness of 3D spatial relationships for improving object detection rates. Finally, we describe a technique for generating 3D detections from 2D image-based object detections and demonstrate how our method improves the average precision of these 3D detections. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Geometric data abstraction using B-splines for range image segmentation

    Page(s): 148 - 153
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2007 KB) |  | HTML iconHTML  

    With the availability of cheap and powerful RGB-D sensors interest in 3D point cloud based methods has drastically increased. One common prerequisite of these methods is to abstract away from raw point cloud data, e.g. to planar patches, to reduce the amount of data and to handle noise and clutter. We present a novel method to abstract RGB-D sensor data to parametric surface models described by B-spline surfaces and associated boundaries. Data is first pre-segmented into smooth patches before B-spline surfaces are fitted. The best surface representations of these patches are selected in a merging procedure. Furthermore, we show how curve fitting estimates smooth boundaries and improves the given sensor information compared to hand-labelled ground truth annotation when using colour in addition to depth information. All parts of the framework are open-source1 and are evaluated on the object segmentation database (OSD) also available online, showing accuracy and usability of the proposed methods. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Clearing a pile of unknown objects using interactive perception

    Page(s): 154 - 161
    Multimedia
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3078 KB) |  | HTML iconHTML  

    We address the problem of clearing a pile of unknown objects using an autonomous interactive perception approach. Our robot hypothesizes the boundaries of objects in a pile of unknown objects (object segmentation) and verifies its hypotheses (object detection) using deliberate interactions. To guarantee the safety of the robot and the environment, we use compliant motion primitives for poking and grasping. Every verified segmentation hypothesis can be used to parameterize a compliant controller for manipulation or grasping. The robot alternates between poking actions to verify its segmentation and grasping actions to remove objects from the pile. We demonstrate our method with a robotic manipulator. We evaluate our approach with real-world experiments of clearing cluttered scenes composed of unknown objects. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pose estimation of rigid transparent objects in transparent clutter

    Page(s): 162 - 169
    Multimedia
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4097 KB) |  | HTML iconHTML  

    Transparent objects are ubiquitous in human environments but, due to their special interaction with light, very few vision methods exist to identify them. We propose a new algorithm for recognition and pose estimation of rigid transparent objects which can deal with overlapping instances and cluttered environments. Using an active depth sensor for segmentation of the objects and 2d edge analysis for pose estimation, we are able to provide accurate identification and position. The proposed method is evaluated on a Microsoft Kinect and also on a PR2 robot. Results show that the algorithm is robust and accurate enough for robotic grasping and that it can be used in practical applications like table cleaning. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Facial communicative signal interpretation in human-robot interaction by discriminative video subsequence selection

    Page(s): 170 - 177
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (482 KB) |  | HTML iconHTML  

    Facial communicative signals (FCSs) such as head gestures, eye gaze, and facial expressions can provide useful feedback in conversations between people and also in human-robot interaction. This paper presents a pattern recognition approach for the interpretation of FCSs in terms of valence, based on the selection of discriminative subsequences in video data. These subsequences capture important temporal dynamics and are used as prototypical reference subsequences in a classification procedure based on dynamic time warping and feature extraction with active appearance models. Using this valence classification, the robot can discriminate positive from negative interaction situations and react accordingly. The approach is evaluated on a database containing videos of people interacting with a robot by teaching the names of several objects to it. The verbal answer of the robot is expected to elicit the display of spontaneous FCSs by the human tutor, which were classified in this work. The achieved classification accuracies are comparable to the average human recognition performance and outperformed our previous results on this task. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.