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 support@techtalks.tv

AI Reasoning Methods

  • An Adaptive Nonparametric Particle Filter for State Estimation Authors: Wang, Yali; Chaib-draa, Brahim
    Particle filter is one of the most widely applied stochastic sampling tools for state estimation problems in practice. However, the proposal distribution in the traditional particle filter is the transition probability based on state equation, which would heavily affect estimation performance in that the samples are blindly drawn without considering the current observation information. Additionally, the fixed particle number in the typical particle filter would lead to wasteful computation, especially when the posterior distribution greatly varies over time. In this paper, an advanced adaptive nonparametric particle filter is proposed by incorporating gaussian process based proposal distribution into KLD-Sampling particle filter framework so that the high-qualified particles with adaptively KLD based quantity are drawn from the learned proposal with observation information at each time step to improve the approximation accuracy and efficiency. Our state estimation experiments on univariate nonstationary growth model and two-link robot arm show that the adaptive nonparametric particle filter outperforms the existing approaches with smaller size of particles.
  • Online Semantic Exploration of Indoor Maps Authors: Liu, Ziyuan; Chen, Dong; v. Wichert, Georg
    In this paper we propose a method to extract an abstracted floor plan from typical grid maps using Bayesian reasoning. The result of this procedure is a probabilistic generative model of the environment defined over abstract concepts. It is well suited for higher-level reasoning and communication purposes. We demonstrate the effectiveness of the approach through real-world experiments.
  • Game Solving for Industrial Automation and Control Authors: Cheng, Chih-Hong; Buckl, Christian; Knoll, Alois; Geisinger, Michael
    An ongoing effort within the community of verification and program analysis is to raise the level of abstraction in programming by automatic synthesis. In this paper, we demonstrate how our synthesis engine GAVS+ achieves this goal by automatically creating control code for the FESTO modular production system. The overall approach is model-driven: we reinterpret planning domain definition language (PDDL) (as a design contract) to model two-player games played between control and environment, such that users can describe (i) basic abilities of hardware components, including sensors (as environment moves) and actuators (as control moves), (ii) topologies how components are interconnected, and (iii) desired specification under a restricted class of linear temporal logic. The model is processed by our game-based synthesis engine, and from which intermediate code is generated. By mapping each behavioral-level action to a sequence of low-level PLC control commands, we transform the intermediate code to an executable program. The efficiency of our engine enables to synthesize every scenario presented in this paper within seconds. When the specification evolves, this implies a huge time-gain compared to manual code modification.
  • Learning Relational Affordance Models for Robots in Multi-Object Manipulation Tasks Authors: Moldovan, Bogdan; Moreno, Plinio; van Otterlo, Martijn; Santos-Victor, José; De Raedt, Luc
    Affordances define the action possibilities on an object in the environment and in robotics they play a role in basic cognitive capabilities. Previous works have focused on affordance models for just one object even though in many scenarios they are defined by configurations of multiple objects that interact with each other. We employ recent advances in statistical relational learning to learn affordance models in such cases. Our models generalize over objects and can deal effectively with uncertainty. Two-object interaction models are learned from robotic interaction with the objects in the world and employed in situations with arbitrary numbers of objects. We illustrate these ideas with experimental results of an action recognition task where a robot manipulates objects on a shelf.
  • Abstract Planning for Reactive Robots Authors: Joshi, Saket; Schermerhorn, Paul; Khardon, Roni; Scheutz, Matthias
    Hybrid reactive-deliberative architectures in robotics combine reactive sub-policies for fast action execution with goal sequencing and deliberation. The need for replanning, however, presents a challenge for reactivity and hinders the potential for guarantees about the plan quality. In this paper, we argue that one can integrate abstract planning provided by symbolic dynamic programming in first order logic into a reactive robotic architecture, and that such an integration is in fact natural and has advantages over traditional approaches. In particular, it allows the integrated system to spend off-line time planning for a policy, and then use the policy reactively in open worlds, in situations with unexpected outcomes, and even in new environments, all by simply reacting to a state change executing a new action proposed by the policy. We demonstrate the viability of the approach by integrating the FODD-Planner with the robotic DIARC architecture showing how an appropriate interface can be defined and that this integration can yield robust goal-based action execution on robots in open worlds.
  • Searching Objects in Large-Scale Indoor Environments: A Decision-Theoretic Approach Authors: Kunze, Lars; Beetz, Michael; Saito, Manabu; Azuma, Haseru; Okada, Kei; Inaba, Masayuki
    Many of today's mobile robots are supposed to perform everyday manipulation tasks autonomously. However, in large-scale environments, a task-related object might be out of the robot's reach. Hence, the robot first has to search for the object in its environment before it can perform the task. In this paper, we present a decision-theoretic approach for searching objects in large-scale environments using probabilistic environment models and utilities associated with object locations. We demonstrate the feasibility of our approach by integrating it into a robot system and by conducting experiments where the robot is supposed to search different objects with various strategies in the context of fetch-and-delivery tasks within a multi-level building.

Redundant robots

  • Motion Control of Redundant Robots under Joint Constraints: Saturation in the Null Space Authors: Flacco, Fabrizio; De Luca, Alessandro; Khatib, Oussama
    We present a novel efficient method addressing the inverse differential kinematics problem for redundant manipulators in the presence of different hard bounds (joint range, velocity, and acceleration limits) on the joint space motion. The proposed SNS (Saturation in the Null Space) iterative algorithm proceeds by successively discarding the use of joints that would exceed their motion bounds when using the minimum norm solution and reintroducing them at a saturated level by means of a projection in a suitable null space. The method is first defined at the velocity level and then moved to the acceleration level, so as to avoid joint velocity discontinuities due to the switching of saturated joints. Moreover, the algorithm includes an optimal task scaling in case the desired task trajectory is unfeasible under the given joint bounds. We also propose the integration of obstacle avoidance in the Cartesian space by properly modifying on line the joint bounds. Simulation and experimental results reported for the 7-dof lightweight KUKA LWR IV robot illustrate the properties and computational efficiency of the method.
  • Priority Oriented Adaptive Control of Kinematically Redundant Manipulators Authors: Sadeghian, Hamid; Keshmiri, Mehdi; Villani, Luigi; Siciliano, Bruno
    In this paper an adaptive multi-priority nonlinear control algorithm for a redundant manipulator system is developed based on the Lyapunov like approach. The method considers the parametric uncertainties in the system and defines a proper filtered error signal to achieve asymptotic stability and convergence in tracking error both for the main task and sub-tasks according to the allocated priority. The performance of the proposed method is studied by some numerical simulations.
  • Resolving the Redundancy of a Seven DOF Wearable Robotic System Based on Kinematic and Dynamic Constraint Authors: Kim, Hyunchul; Li, Zhi; Milutinovic, Dejan; Rosen, Jacob
    According to the seven degrees of freedom (DOFs) human arm model composed of the shoulder, elbow, and wrist joints, positioning of the wrist in space and orientating the palm is a task requiring only six DOFs. Due to this redundancy, a given task can be completed by multiple arm configurations, and there is no unique mathematical solution to the inverse kinematics. The redundancy of a wearable robotic system (exoskeleton) that interacts with the human is expected to be resolved in the same way as that of the human arm. A unique solution to the system's redundancy was introduced by combining both kinematic and dynamic criteria. The redundancy of the arm is expressed mathematically by defining the swivel angle: the rotation angle of the plane including the upper and lower arm around a virtual axis connecting the shoulder and wrist joints which are fixed in space. Two different swivel angles were generated based on kinematic and dynamic constraints. The kinematic criterion is to maximize the projection of the longest principle axis of the manipulability ellipsoid for the human arm on the vector connecting the wrist and the virtual target on the head region. The dynamic criterion is to minimize the mechanical work done in the joint space for each two consecutive points along the task space trajectory. These two criteria were then combined linearly with different weight factors for estimating the swivel angle. Post processing of experimental data collected with a motion capturing
  • Dual-Arm Redundancy Resolution Based on Null-Space Dynamically-Scaled Posture Optimization Authors: Zanchettin, Andrea Maria; Rocco, Paolo
    Dual-arm robotic systems have been intensively studied in the literature. However, in industrial robotics, the resolution of the kinematic redundancy allowed by the coordinated manipulation task is still an open issue. In fact, typical proprietary industrial robotic controllers do not allow the programmer to modify the inverse kinematics algorithm, and thus to solve redundancy following any specified criterion. In this paper a method to enforce an arbitrary redundancy resolution criterion on top of an industrial robot controller is discussed and applied to the execution of a coordinated manipulation task. The extra degrees of freedom are used to maximize the dynamic manipulability measure in order to reduce the needed torque. Simulations and experimental results achieved on an ABB IRC 5 industrial robot controller are presented.
  • Optimal Decentralized Gait Transitions for Snake Robots Authors: Droge, Greg; Egerstedt, Magnus
    Snake robots are controlled by implementing gaits inspired from their biological counterparts. However, transitioning between these gaits often produces undesired oscillations which cause net movements that are difficult to predict. In this paper we present a framework for implementing gaits which will allow for smooth transitions. We also present a method to determine the optimal time for each module of the snake to switch between gaits in a decentralized fashion. This will allow for each module to participate in minimizing a cost by communicating with a set of modules in a local neighborhood. Both of these developments will help to maintain desired properties of the gaits during transition.

High Level Robot Behaviors

  • Automated Feedback for Unachievable High-Level Robot Behaviors Authors: Raman, Vasumathi; Kress-Gazit, Hadas
    One of the main challenges in robotics is the generation of controllers for autonomous, high-level robot behaviors comprising a non-trivial sequence of actions. Recently, formal methods have emerged as a powerful tool for automatically generating autonomous robot controllers that guarantee desired behaviors expressed by a class of temporal logic specifications. However, when there is no controller that fulfills the specification, these approaches do not provide the user with a source of failure, making the troubleshooting of specifications an unstructured and time-consuming process. In this paper, we describe a procedure for analyzing an unsynthesizable specification to identify causes of failure. We also provide an interactive game for exploring possible causes of failure, in which the user attempts to fulfill the robot specification against an adversarial environment. Our approach is implemented within the LTLMoP toolkit for robot mission planning.
  • Backtracking Temporal Logic Synthesis for Uncertain Environments Authors: Livingston, Scott; Murray, Richard; Burdick, Joel
    This paper considers the problem of synthesizing correct-by-construction robotic controllers in environments with uncertain but fixed structure. "Environment" has two notions in this work: a map or "world" in which some controlled agent must operate and navigate (i.e., evolve in a configuration space with obstacles); and an adversarial player that selects continuous and discrete variables to try to make the agent fail (as in a game). Both the robot and the environment are subjected to behavioral specifications expressed as an assume-guarantee linear temporal logic (LTL) formula. We then consider how to efficiently modify the synthesized controller when the robot encounters unexpected changes in its environment. The crucial insight is that a portion of this problem takes place in a metric space, which provides a notion of nearness. Thus if a nominal plan fails, we need not resynthesize it entirely, but instead can "patch" it locally. We present an algorithm for doing this, prove soundness (correctness of output), and demonstrate it on an example gridworld.
  • On the Revision Problem of Specification Automata Authors: KIM, Kangjin; Fainekos, Georgios; Sankaranarayanan, Sriram
    One of the important challenges in robotics is the automatic synthesis of provably correct controllers from high level specifications. One class of such algorithms operates in two steps: (i) high level discrete controller synthesis and (ii) low level continuous controller synthesis. In this class of algorithms, when phase (i) fails, then it is desirable to provide feedback to the designer in the form of revised specifications that can be achieved by the system. In this paper, we address the minimal revision problem for specification automata. That is, we construct automata specifications that are as ``close" as possible to the initial user intent, by removing the minimum number of constraints from the specification that cannot be satisfied. We prove that the problem is computationally hard and we encode it as a satisfiability problem. Then, the minimal revision problem can be solved by utilizing efficient SAT solvers.
  • LTL Robot Motion Control Based on Automata Learning of Environmental Dynamics Authors: Chen, Yushan; Tumova, Jana; Belta, Calin
    We develop a technique to automatically generate a control policy for a robot moving in an environment that includes elements with partially unknown, changing behavior. The robot is required to achieve an optimal surveillance mission, in which a certain request needs to be serviced repeatedly, while the expected time in between consecutive services is minimized. We define a fragment of Linear Temporal Logic (LTL) to describe such a mission and formulate the problem as a temporal logic game. Our approach is based on two main ideas. First, we extend results in automata learning to detect patterns of the partially unknown behavior of the elements in the environment. Second, we employ an automata-theoretic method to generate the control policy. We show that the obtained control policy converges to an optimal one when the unknown behavior patterns are fully learned. We implemented the proposed computational framework in MATLAB. Illustrative case studies are included.
  • Towards Formal Synthesis of Reactive Controllers for Dexterous Robotic Manipulation Authors: Chinchali, Sandeep; Livingston, Scott; Topcu, Ufuk; Burdick, Joel; Murray, Richard
    In robotic finger gaiting, fingers continuously manipulate an object until joint limitations or mechanical limitations periodically force a switch of grasp. Current approaches to gait planning and control are slow, lack formal guarantees on correctness, and are generally not reactive to changes in object geometry. To address these issues, we apply advances in formal methods to model a gait subject to external perturbations as a two-player game between a finger controller and its adversarial environment. High-level specifications are expressed in linear temporal logic (LTL) and low-level control primitives are designed for continuous kinematics. Simulations of planar manipulation with our synthesized correct-by-construction gait controller demonstrate the benefits of this approach.
  • Sequential Composition of Robust Controller Specifications Authors: Le Ny, Jerome; Pappas, George J.
    We present a general notion of robust controller specification and a mechanism for sequentially composing them. These specifications form tubular abstractions of the trajectories of a system in different control modes, and are motivated by the techniques available for certifying the performance of low-level controllers. The notion of controller specification provides a rigorous interface for connecting a planner and lower-level controllers that are designed and refined independently. With this approach, the planning layer does not integrate the closed-loop system dynamics and does not require the knowledge of how the controllers operate, but relies only on the specifications of the output tracking performance achieved by these controllers. The control layer aims at satisfying specifications that account quantitatively for robustness to unmodeled dynamics and various sources of disturbance and sensor noise, so that this robustness does not need to be revalidated at the planning level. As an illustrative example, we describe a randomized planner that composes different controller specifications from a given database to guarantee that any corresponding sequence of control modes steers a robot to a given region while avoiding obstacles.