TechTalks from event: Technical session talks from ICRA 2012

Conference registration code to access these videos can be accessed by visiting this link: PaperPlaza. Step-by-step to access these videos are here: step-by-step process .
Why some of the videos are missing? If you had provided your consent form for your video to be published and still it is missing, please contact

Humanoid Motion Planning and Control

  • Controlling the Planar Motion of a Heavy Object by Pushing with a Humanoid Robot Using Dual-Arm Force Control Authors: Nozawa, Shunichi; Kakiuchi, Yohei; Okada, Kei; Inaba, Masayuki
    Pushing heavy and large objects in a plane requires generating correct operational forces that compensate for unpredictable ground-object friction forces. This is a challenge because the reaction forces from the heavy object can easily cause a humanoid robot to slip at its feet or lose balance and fall down. Although previous research has addressed humanoid robot balancing problems to prevent falling down while pushing an object, there has been little discussion about the problem of avoiding slipping due to the reaction forces from the object. We extend a full-body balancing controller by simultaneously controlling the reaction forces of both hands using dual-arm force control. The main contribution of this paper is a method to calculate dual-arm reference forces considering the moments around the vertical axis of the humanoid robot and objects. This method involves estimating friction forces based on force measurements and controlling reaction forces to follow the reference forces. We show experimental results on the HRP-2 humanoid robot pushing a 90[kg] wheelchair.
  • Hopping at the Resonance Frequency: A Pattern Generation Technique for Bipedal Robots with Elastic Joints Authors: Ugurlu, Barkan; Saglia, Jody Alessandro; Tsagarakis, Nikolaos; Caldwell, Darwin G.
    It is known that bipedal robots with passive compliant structures have obvious advantages over stiff robots, as they are able to handle the potential energy management. Therefore, this paper is aimed at presenting a jumping pattern generation method that takes advantage of this property via the utilization of the ankle joint resonance frequency, which is of special importance. To begin with, the resonance frequency is determined through a system identification procedure on our actual robot. Consequentially, the vertical component of the CoM is generated via a periodic function in which the resonance frequency is employed. The horizontal component of the CoM is obtained using the ZMP criterion to guarantee the dynamic balance. Having analytically generated the necessary elements of the CoM trajectory, joint motions are computed with the help of translational and angular momenta constraints. In order to validate the method, two legged jumping experiments are conducted on our actual compliant robot. In conclusion, we satisfactorily observed repetitive, continuous, and dynamically equilibrated jumping cycles with successful landing phases.
  • Humanoid Motion Optimization Via Nonlinear Dimension Reduction Authors: Kang, Hyuk; Park, Frank
    This paper examines the extent to which nonlinear dimension reduction techniques from machine learning can be exploited to determine dynamically optimal motions for high degree-of-freedom systems. Using the Gaussian Process Latent Variable Model (GPLVM) to learn the low-dimensional embedding, and a density function that provides a nonlinear mapping from the low-dimensional latent space to the full-dimensional pose space, we determine optimal motions by optimizing the latent space, and mapping the optimal trajectory in the latent space to the pose space. The notion of variance tubes are developed to ensure that kinematic constraints and other are appropriately satisfied without sacrificing naturalness or richness of the motions. Case studies of a 62-dof humanoid performing two sports motions---a golf swing and throwing a baseball---demonstrate that our method can be a highly effective, computationally efficient method for generating dynamically optimal motions.
  • A Neurorobotic Model of Bipedal Locomotion Based on Principles of Human Neuromuscular Architecture Authors: Klein, Theresa; Lewis, M. Anthony
    In this paper, we present a walking biped, based on principles of mammalian neuromuscular architecture. Walking in mammals is a fluid, dynamical interaction between a central pattern generator, the biomechanics of the body, the environment, and sensory feedback. Our robot is designed based on principles of human leg muscle architecture. We incorporate load detecting force sensors that model Golgi tendon organs in the muscles, as well as foot pressure and joint angle sensors. These sensory feedback sources model those available in the human body. The robot is controlled by a spiking neuron simulation that integrates centrally generated (CPG) with peripheral (reflexive) responses. Using recent understanding of the neurobiology of locomotion, we are able to generate an effective and stable walking pattern using interactions between the biomechanics, CPG, and reflexive responses. The CPG drives overall limb motion at the hips, while phase modulated reflexive responses adapt the pattern of the lower limb to the needs of the step cycle. Load detection by the force sensors in the limb generates propulsive stepping, and controls entrainment of the CPG through positive force feedback. These concepts are important ones for locomotion in mammals that should be considered by roboticists developing walking robots.
  • Walking Control of Fully Actuated Robots Based on the Bipedal SLIP Model Authors: Garofalo, Gianluca; Ott, Christian; Albu-Schäffer, Alin
    The goal of this paper is to generate and stabilize a periodic walking motion for a five degrees of freedom planar robot. First of all we will consider a biped version of the spring loaded inverted pendulum (SLIP), which shows openloop stable behavior. Then we will control the robot behavior as close as possible to the simple model. In this way we take advantage of the open-loop stability of the walking pattern related to the SLIP, and additional control actions are used to increase the robustness of the system and reject external disturbances. To this end an upper level controller will deal with the stabilization of the SLIP model, while a lower level controller will map the simple virtual model onto the real robot dynamics. Two different approaches are implemented for the lower level: in the first one, we aim at exactly reproducing the same acceleration that a SLIP would have when put in the same condition, while in the second one, we aim at a simpler control law without exactly reproducing the aforementioned acceleration. The latter case is equivalent to considering a SLIP with additional external disturbances, which have to be handled by the upper level controller. Both approaches can successfully reproduce a periodic walking pattern for the robot.
  • Muscle Force Transmission to Operational Space Accelerations During Elite Golf Swings Authors: Demircan, Emel; Besier, Thor F.; Khatib, Oussama
    The paper investigates the dynamic characteristics that shape human skills using the task-space methods found in robotics research. It is driven by the hypothesis that each subject's physiology can be reflected to the task dynamics using the operational space acceleration characteristics and that elite performers achieve the optimum transmission from their available muscle induced torque capacity to the desired task in goal oriented dynamic skills. The methodology is presented along with the full body human musculoskeletal model used for the task-based analyzes. The robotics approach for human motion characterization is demonstrated in the biomechanical analysis of an elite golf swing. This approach allows us to trace the acceleration capacities in a given subject's task space. The results of the motion characterization show that humans in fact follow a path of trajectory in line with the maximum available operational space accelerations benefiting from their physiology shaped by the combination of the force generating capacities of the muscles as well as by the joint and limb mechanics.


  • A Game Theoretical Approach to Finding Optimal Strategies for Pursuit Evasion in Grid Environments Authors: Amigoni, Francesco; Basilico, Nicola
    Pursuit evasion problems, in which evading targets must be cleared from an environment, are encountered in surveillance and search and rescue applications. Several works have addressed variants of this problem in order to study strategies for the pursuers. As a common trait, many of these works present results in the general form: given some assumptions on the environment, on the pursuers, and on the evaders, upper and lower bounds are calculated for the time needed for (the probability of, the resources needed for, ...) clearing the environment. The question ''what is the optimal strategy for a given pursuer in a given environment to clear a given evader?'' is left largely open. In this paper, we propose a game theoretical framework that contributes in finding an answer to the above question in a version of the pursuit evasion problem in which the evader enters and exits a grid environment and the pursuer has to intercept it along its path. We adopt a criterion for optimality related to the probability of capture. We experimentally evaluate the proposed approach in simulated settings and we provide some hints to generalize the framework to other versions of the pursuit evasion problem.
  • Online Patrolling Using Hierarchical Spatial Representations Authors: Basilico, Nicola; Carpin, Stefano
    Unmanned Aerial Vehicles (UAVs) can be an effective technology for security applications involving patrolling and search missions. Defining online patrolling strategies for UAVs presents challenges related both to classical patrolling, as periodic monitoring of the environment, and to search, as accurate localization and identification of the mission-related activities. In this paper, we deal with this problem considering probabilistic intrusions and a variable resolution sensing model that naturally applies to the domain of UAVs. We present three online single--robot patrolling strategies exploiting a variable resolution paradigm to represent the environment that has recently shown promising results for search problems. The approach uses a hierarchical representation based on probabilistic quadtrees that allows UAVs to tradeoff sensing accuracy with sensing area. The model is extended by adding stochastic arrivals of intruders in space and time. Obtained results validate this approach for online patrolling against approaches based on uniform grids.
  • Laser-Based Intelligent Surveillance and Abnormality Detection in Extremely Crowded Scenarios Authors: Song, Xuan; Shao, Xiaowei; Zhang, Quanshi; Shibasaki, Ryosuke; Zhao, Huijing; Zha, Hongbin
    Abnormal activity detection plays a crucial role in surveillance applications, and a surveillance system that can perform robustly in the extremely crowded area has become an urgent need for public security. In this paper, we propose a novel laser-based system which can simultaneously perform the tracking, semantic scene learning and abnormality detection in the large and crowded environment. In our system, a novel abnormality detection model is proposed, and it considers and combines various factors that will influence human activity. Moreover, this model intensively investigate the relationship between pedestrians' social behaviors and their walking scenarios. We successfully applied the proposed system to the JR subway station of Tokyo, which can cover a 60*35m area, robustly track more than 180 targets at the same time and simultaneously perform the online semantic scene learning and abnormality detection with no human intervention.
  • Strong Shadow Removal Via Patch-Based Shadow Edge Detection Authors: Wu, Qi
    Detecting objects in shadows is a challenging task in computer vision. For example, in clear path detection application, strong shadows on the road confound the detection of the boundary between clear path and obstacles, making clear path detection algorithms less robust. Shadow removal, relies on the classification of edges as shadow edges or non-shadow edges. We present an algorithm to detect strong shadow edges, which enables us to remove shadows. By analyzing the patch-based characteristics of shadow edges and non-shadow edges (e.g., object edges), the proposed detector can discriminate strong shadow edges from other edges in images by learning the distinguishing characteristics. In addition, spatial smoothing is used to further improve shadow edge detection. Numerical experiments show convincing results that shadows on the road are either removed or attenuated with few visual artifacts, which benefits the clear path detection. In addition, we show that the proposed method outperforms the state-of-art algorithms in different conditions.
  • Integrated Probabilistic Generative Model for Detecting Smoke on Visual Images Authors: Vidal-Calleja, Teresa A.; Agamennoni, Gabriel
    Early fire detection is crucial to minimise damage and save lives. Video surveillance smoke detectors do not suffer from transport delays and can cover large areas. The smoke detection on images is, however, a difficult problem due the variability of smoke density, lighting conditions, background clutter, and unstable patterns. In order to solve this problem, we propose a novel unsupervised object classifier. Single visual features are classified using a model that simultaneously creates a codebook and categorises the smoke using a bag-of-words paradigm based on LDA model. Our algorithm can also tell the amount of smoke present on the image. Multiple image sequences from different cameras are used to show the viability of the proposed approach. Our experiments show that the model generalises well for different cameras, perspectives and scales.
  • Localization in Indoor Environments by Querying Omnidirectional Visual Maps Using Perspective Images Authors: Pedro, Vítor Manuel; Lourenço, Miguel; Barreto, João P.
    This article addresses the problem of image-based localization in a indoor environment. The localization is achieved by querying a database of omnidirectional images that constitutes a detailed visual map of the building where the robot operates. Omnidirectional cameras have the advantage, when compared to standard perspectives, of capturing in a single frame the entire visual content of a room. This, not only speeds up the process of acquiring data for creating the map, but also favors scalability by significantly decreasing the size of the database. The problem is that omnidirectional images have strong non-linear distortion, which leads to poor retrieval results when the query images are standard perspectives. This paper reports for the first time thorough experiments in using perspectives to index a database of para-catadioptric images for the purpose of robot localization. We propose modifications to the SIFT algorithm that significantly improve point matching between the two types of images with positive impact in the recognition based in visual words. We also compare the classical bags-of-words against the recent framework of visual-phrases, showing that the latter outperforms the former.

Environment Mapping

  • A Dependable Perception-Decision-Execution Cycle for Autonomous Robots Authors: Gspandl, Stephan; Podesser, Siegfried; Reip, Michael; Steinbauer, Gerald; Wolfram, Máté
    The tasks robots are employed to achieve are becoming increasingly complex, demanding for dependable operation, especially if robots and humans share common space. Unfortunately, for these robots non-determinism is a severe challenge. Malfunctioning hardware, inaccurate sensors, exogenous events and incomplete knowledge lead to inconsistencies in the robot’s belief about the world. Thus, a robot has to cope efficiently with such adversities while sensing its surroundings, deciding what to do next, and executing its decisions. In this paper, we present such a dependable perception-decision-execution cycle. It employs a belief management system that performs history-based diagnosis in the high-level control module. The belief management enables robots to detect these inconsistencies and thus operate successfully in non-deterministic environments. The main contributions of this paper are a robot design extending the high-level control IndiGolog by a belief management allowing to deal with a large variety of faults in a unique way, together with an evaluation on a real robot system.
  • Efficient Change Detection in 3D Environment for Autonomous Surveillance Robots based on Implicit Volume Authors: Wilson Vieira, Antonio; Drews Jr, Paulo; Campos, Mario Montenegro
    The ability to detect changes in the environment is an essential trait for robots commissioned to work in several applications. In surveillance, for instance, a robot needs to detect meaningful changes in the environment which is achieved by comparing current sensory data with previously acquired information from the environment. The large amount of sensory data, which are often complex and very noisy, explains the inherent difficulty of this task. As an attempt to tackle this hard problem, we present an efficient method to automatically segment 3D data, corrupted with noise and outliers, into an implicit volume bounded by a surface. The method makes it possible to efficiently apply Boolean operations to 3D data in order to detect changes and to update existing maps. We show that our approach is powerful, albeit simple, with linear time complexity. The method has been validated through several trials using mobile robots operating in real environments and their performance was compared to another state-of-art algorithm. Experimental results demonstrate the performance of the proposed method, both in accuracy and computational cost.
  • Stochastic Source Seeking in Complex Environments Authors: Atanasov, Nikolay; Le Ny, Jerome; Michael, Nathan; Pappas, George J.
    The objective of source seeking problems is to determine the minimum of an unknown signal field, which represents a physical quantity of interest, such as heat, chemical concentration, or sound. This paper proposes a strategy for source seeking in a noisy signal field using a mobile robot and based on a stochastic gradient descent algorithm. Our scheme does not require a prior map of the environment or a model of the signal field and is simple enough to be implemented on platforms with limited computational power. We discuss the asymptotic convergence guarantees of algorithm and give specific guidelines for its application to mobile robots in unknown indoor environments with obstacles. Both simulations and real-world experiments were carried out to evaluate the performance of our approach. The results suggest that the algorithm has good finite time performance in complex environments.
  • Robust Sound Localization for Various Platform of Robots Using TDOA Map Adaptation Authors: Shen, Guanghu, Guanghu; Hwang, Dohyung; Nguyen, Quang; Choi, Jongsuk
    In realistic environments, mismatches between the calculated angle-TDOA map with its real exact values are the major reason of performance degradation in sound localization. Usually, those mismatches come from some certain configuration errors or deviations caused by the change of environments. To reduce those mismatches, in this paper we proposed an angle-TDOA map adaptation method, which can achieve the robust sound localization in various robot platforms (i.e., various types of microphone array configuration). Especially, the proposed method is possible to easily apply to the sound localization system by using only several sound sources which generated from some known directions. As a result, the proposed method not only showed a good localization performance, and the program running time is also very short.