IROS 2017 论文列表

This paper presents the Pi-puck extension board - an interface between the e-puck robot platform and a Raspberry Pi single-board computer that enhances the processing power, memory capacity, and networking capabilities of the robot at a low cost. It allows high-level control algorithms, wireless communication, and computationally expensive operations such as real-time image processing to be handled by a Raspberry Pi, while the e-puck's microcontroller deals with low-level motor control and sensor interfacing. Although two similar extension boards for the e-puck robot platform already exist, they are now out-dated and expensive in comparison. Our open-source hardware design and supporting software infrastructure offer an inexpensive upgrade to the e-puck robot, transforming it into the Pi-puck - a modern and flexible new platform for mobile robotics research.

Planning kinodynamically feasible trajectories for autonomous vehicles is computationally expensive, especially when planning over long distances in unstructured environments. This paper presents a hierarchical planner, called the Maverick planner, which can find such trajectories efficiently. It comprises two parts: a waypoint planner that uses a simplified vehicle model and an RRT* planner that respects full kinodynamic constraints. The waypoint planner quickly finds a directed graph of waypoints from start to goal, which is then used to bias sampling and speed up computation in RRT*. The Maverick planner is capable of anytime planning and continuous replanning. It has been tested extensively in simulation and on real vehicles. When planning on a sensor-generated map of the SwRI test track it can find a feasible path over 0.5 km in under 16 ms, and refine that path to within 1% of the local optimum in 0.5 seconds.

Consider a setting where robots must visit sites represented as nodes in a graph, but each robot may fail when traversing an edge. The goal is to find a set of paths for a team of robots which maximizes the expected number of nodes collectively visited, while guaranteeing that the paths satisfy a notion of “independence” formalized by a matroid (e.g. limits on team size, number of visits to regions), and that the probabilities that each robot survives to its destination are above a given threshold. We call this problem the Matroid Team Surviving Orienteers (MTSO) problem, which has broad applications such as environmental monitoring in risky regions and search and rescue in dangerous conditions. We present the MTSO formally and detail numerous examples of matroids in a path planning context. We then propose an approximate greedy algorithm for selecting a feasible set of paths and prove that the value of the output is within a factor ps/ps + λ of the optimum, where ps is the per-robot survival probability threshold and 1/λ ≤ 1 is the approximation factor of an oracle routine for the well known orienteering problem. We demonstrate the efficiency of our approach by applying it to a scenario where a team of robots must gather information while avoiding pirates in the Coral Triangle.

Microrobots show great potential to realize a wide range of medical applications especially in a hard-to-reach region within human body. Among a diversity of medical applications, the microrobots are expected to efficiently perform tasks within the human body, but the existing electromagnetic coil systems such as Helmholtz coil, Maxwell coil, etc. do not compromise on the insertion of such a large volume of human parts. We aim to magnetically manipulate diverse microrobots in medical applications with respect to surgical or biopsy tasks within insiders of the human head such as to perform brachytherapy with the helical microswimmer, etc. For this reason, we proposed a novel, a magnetically actuated system called the HyBrid system with the conceptual design in capability of generating both uniform and gradient magnetic fields. The system consists of three different coil setups orthogonally arranged over a large workspace which is available to let the human head inserted into. The simulation results of the magnetic field generation expressed that its performance is suitable and feasible towards magnetically manipulation within the human head, and more efficient than 3D-Helmholtz coil system under the same conditions.

To address the requirement for autonomous moral decision making, we introduce a software library for modeling hybrid ethical reasoning agents (short: HERA). The goal of the HERA project is to provide theoretically well-founded and practically usable logic-based machine ethics tools for implementation in robots. The novelty is that HERA implements multiple ethical principles like utilitarianism, the principle of double effect, and a Pareto-inspired principle. These principles can be used to automatically assess moral situations represented in a format we call causal agency models. We discuss how to model moral situations using our approach, and how it can cope with uncertainty about moral values. Finally, we briefly outline the architecture of our robot IMMANUEL, which implements HERA and is able to explain ethical decisions to humans.

We investigate tethered flight of a small quadrotor robot in the context of creating stippled prints. At a low level, we use motion capture to measure the position of the robot and the canvas, and a robust control algorithm to command the robot to fly to different stipple positions to make contact with the canvas using an ink soaked sponge. With the objective of fully autonomous flight, we power our quadrotor using a wired tether. We compensate for the tether in our control of the robot by assuming a static catenary curve of fixed length between the robot and the power source, and model the forces and torques produced. We evaluate accuracy of hovering and flight on simple paths, and compare the results to untethered flight.

This paper presents a tentacle-based obstacle avoidance scheme for omnidirectional mobile robots that must satisfy visibility constraints during navigation. The navigation task consists of driving the robot towards a visual target in the presence of environment (static or moving) obstacles. The target is acquired by an on-board camera, while the obstacles surrounding the robot are sensed by laser range scanners. To perform such task, the robot must avoid the obstacles while maintaining the target in its field of view. The approach is validated in both simulated and real experiments.

Robotic teleoperation in cluttered environments is attracting increasing attention for its potential in hazardous scenarios, disaster response, and telemaintenance. Although haptic feedback has been proven effective in such applications, commercially-available grounded haptic interfaces still show significant limitations in terms of workspace, safety, transparency, and encumbrance. For this reason, we present a novel robotic teleoperation system with wearable haptic feedback for telemanipulation in cluttered environments. The slave system is composed of a soft robotic hand attached to a 6-axis force sensor, which is fixed to a 6-degrees-of-freedom robotic arm. The master system is composed of two wearable vibrotactile armbands and a Leap Motion. The armbands are worn on the upper arm and forearm, and convey information about collisions on the robotic arm and hand, respectively. The position of the manipulator and the grasping configuration of the robotic hand are controlled by the user's hand pose as tracked by the Leap Motion. To validate our approach, we carried out a human-subject telemanipulation experiment in a cluttered scenario. Twelve participants were asked to teleoperate the robot to grasp an object hidden between debris of various shapes and stiffnesses. Haptic feedback provided by our wearable devices significantly improved the performance of the considered telemanipulation tasks. All subjects but one preferred conditions with wearable haptic feedback.

Intraoperative 3D imaging has great potential for enhancing surgical visualization. This is especially so in ophthalmic surgery where live volumetric imaging from optical coherence tomography systems recently incorporated into surgical microscopes has freed surgeons from the otherwise universal top-down viewpoint. New viewpoints, however, disorient surgeons when directions of their hand motions and viewed tool motions do not align. We propose introducing a robotic surgery system to decouple surgeons' hands from their tools and ensure that viewed tool motions align in arbitrary viewpoints. We present a framework entitled Arbitrary Viewpoint Robotic Manipulation (AVRM) which governs how hand and tool motions should interact to minimize disorientation and thereby enable operations from desirable but previously untenable viewpoints. A crossover study in which 20 subjects completed mock surgical scenarios with an AVRM testbed system demonstrated that arbitrary viewpoints do not improve task performance unless automatic hand-tool misalignment correction is provided. When provided together with arbitrary viewpoints, automatic hand-tool misalignment correction reduces task completion time by 50% on average compared to a fixed top-down viewpoint.

Tele-operation in the presence of environmental constraints is a well-studied problem, where the difficulties of the transparency-stability trade-off have been elucidated by several important studies. While at the state-of-art, passivity-based stabilizers appear to provide the best insight and command over this problem, recent work by our group has proposed an alternative approach, which consists in measuring and replicating the master's limb endpoint impedance on the slave robot in real-time. Tele-impedance control offers advantages in certain conditions, e.g. where master-slave communications are low quality. However, force feedback remains necessary when visual feedback is impaired or transparency and telepresence in the remote environment is of major concern. In this paper, we propose a novel framework to achieve the Tele-Impedance with Force Feedback (TIFF) so as to have a seamless control scheme that subsumes the performance advantages of both, while still guaranteeing stability and transparency. Experimental results illustrate the potential of the proposed technique in addressing the drawbacks of the two concepts.

We present a task-oriented grasp model, that encodes grasps that are configurationally compatible with a given task. For instance, if the task is to pour liquid from a container, the model encodes grasps that leave the opening of the container unobstructed. The model consists of two independent agents: First, a geometric grasp model that computes, from a depth image, a distribution of 6D grasp poses for which the shape of the gripper matches the shape of the underlying surface. The model relies on a dictionary of geometric object parts annotated with workable gripper poses and preshape parameters. It is learned from experience via kinesthetic teaching. The second agent is a CNN-based semantic model that identifies grasp-suitable regions in a depth image: regions where a grasp will not impede the execution of the task. The semantic model allows us to encode relationships such as “grasp from the handle.” A key element of this work is to use a deep network to integrate contextual task cues, and defer the structured-output problem of gripper pose computation to an explicit (learned) geometric model. Jointly, these two models generate grasps that are mechanically fit, and that grip on the object in a way that enables the intended task.

An important question in imitation learning is how to generalize a learned motion to novel situations. The motion generalization depends on a set of features which can be represented as feature vectors spanning a feature space, called query space. The purpose of generalization is to find a mapping from this query space to the motion primitive space (MP space). In this paper, we address the problem of generalization of dynamic movement primitives (DMPs) to new queries by applying locally weighted regression (LWR) with radial basis functions (RBF). Since two DMPs differ only in their non-linear part, we transform the problem of DMP generalization to a regression analysis problem. We introduce a task-oriented regression algorithm with a cost function that takes task constraints into consideration and which relies on model switching to solve the problem of poor DMP generalization when using a single regression model for the entire query space. The evaluation shows that our algorithm outperforms related approaches in the literature in terms of generalization capabilities.

Machine learning algorithms can be expensive to deploy, in particular, those used in robotics applications that perform many variations of the same task. Solutions to one variation of a task may be found via Reinforcement Learning algorithms, and are typically modeled as a vector of N parameters encoding the robot's behavior policy. When N is large or executing robot trials is time-consuming, searching in the space of solutions becomes prohibitively expensive. In this paper, we introduce a method that allows robots to generalize behaviors by analyzing solutions to a small number of previously-trained related tasks. This allows for approximate policies for novel tasks to be rapidly estimated. We present a method that achieves this type of generalization by performing nonlinear regression directly on the policy manifold — i.e., the solution space spanned as we change the parameters describing tasks. Because tasks are typically described by few parameters, the corresponding policy manifold has few degrees of freedom, which leads to low-dimensional surfaces. We exploit this property to construct a function that maps task parameters to policy parameters (a parameterized skill). Our method uses manifold clustering techniques to deal with discontinuous manifolds, a challenging situation arising from physical obstacles or robot constraints. We evaluate our method on a set of robot manipulation tasks and show that it can efficiently estimate policies for novel tasks from a small number of training examples.

To satisfy the diversity of tactile patterns during Physical Human Robot Interaction(PHRI), this paper proposes a method to recognize human tactile motion using a spherical handle equipped with tactile sensors. The method first exploits convolutional neural networks as universal feature extractors, and then support vector machines are implemented for classifying the 16 kinds of motion in 4D space. Experimental results show the superiority of our approach against other methods, leading to classification rates over 91.19%.

Target registration error (TRE) is widely adopted to evaluate the accuracy of a paired-point rigid registration (PPRR). However, TRE is defined in such a way that target localization error (TLE) is not considered. In this paper, we first propose a new type of error that is referred to as total target registration error (TTRE). The statistical model of TTRE is derived that we take the TLE in two spaces to be registered into consideration. Results in the first simulation show that the developed model can accurately estimate the simulated TTRE root-mean-square (RMS) (RMS percent differences|| <; 1.5% ± 2%) in all test cases. When all elements of diagonal FLE and TLE covariance matrices are independently generated from a uniform distribution that spans from 0 to 1mm and the number of fiducials N ≥ 6, the mean and covariance matrix of TTRE are well modelled. We have also theoretically proved and validated through the second simulation that TTRE and fiducial registration error (FRE) are uncorrelated (correlation coefficient (CC) <; 0.1). Finally, TTRE and TRE were found to exhibit a low correlation (0.37 <; CC <; 0.46).

In this paper we study the problem of synthesizing correct-by-construction Behavior Trees (BTs) controlling agents in adversarial environments. The proposed approach combines the modularity and reactivity of BTs with the formal guarantees of Linear Temporal Logic (LTL) methods. Given a set of admissible environment specifications, an agent model in form of a Finite Transition System and the desired task in form of an LTL formula, we synthesize a BT in polynomial time, that is guaranteed to correctly execute the desired task. To illustrate the approach, we present three examples of increasing complexity.

This paper describes a simple control scheme for the two-legged dynamic climbing robot, the ParkourBot. Inspired by the swing leg retraction (SLR) method used on running robots, we propose to implement an SLR controller that does not require an actual apex crossing event as an initiator. The familiar SLR control for running is initiated when the center of mass (CoM) of the robot reaches the apex of its trajectory. Often, dynamic climbing gaits do not reach an apex. We therefore define an alternative initiator named, the virtual apex. We evaluate two simple models, the conservative spring loaded inverted pendulum (SLIP) model, and the more realistic non-conservative SLIP model. We show, in simulation, that using SLR we are able to stabilize and control the otherwise unstable conservative SLIP model. We also show, that using the SLR significantly increases the robustness of the non-conservative SLIP model. Finally, we validate our results through experiments on the ParkourBot climbing robot.

In travelling towards the oviducts, sperm cells undergo transitions between planar to helical flagellar propulsion by a beating tail based on the viscosity of the environment. In this work, we aim to model and mimic this behaviour in low Reynolds number fluids using externally actuated soft robotic sperms. We numerically investigate the effects of transition between planar to helical flagellar propulsion on the swimming characteristics of the robotic sperm using a model based on resistive-force theory to study the role of viscous forces on its flexible tail. Experimental results are obtained using robots that contain magnetic particles within the polymer matrix of its head and an ultra-thin flexible tail. The planar and helical flagellar propulsion are achieved using in-plane and out-of-plane uniform fields with sinusoidally varying components, respectively. We experimentally show that the swimming speed of the robotic sperm increases by a factor of 1.4 (fluid viscosity 5 Pa.s) when it undergoes a controlled transition between planar to helical flagellar propulsion, at relatively low actuation frequencies.

Teleoperation is the dominant form of dexterous robotic tasks in the field. However, there are many use cases in which direct teleoperation is not feasible such as disaster areas with poor communication as posed in the DARPA Robotics Challenge or robot operations on spacecraft far from Earth. Presented is a solution that combines the Affordance Template Framework for object interaction with TaskForce for supervisory control in order to accomplish high-level task objectives with basic autonomous behavior from the robot. This framework has allowed the robot to take corrective actions before requesting assistance from the user. This work is demonstrated with Robonaut 2 removing a Cargo Transfer Bag from a simulated logistics resupply vehicle for spaceflight using a single operator command. This was executed with 80% success with no human involvement and 95% success with limited human interaction. This technology sets the stage to do any number of high-level tasks using a similar framework, allowing the robot to accomplish tasks with minimal to no human interaction.