ICRA 2015 论文列表

We present a framework for integrating two layers of map which are often required for fully automated operation: metric and semantic. Metric maps are likely to improve with subsequent visitations to the same place, while semantic maps can comprise both permanent and fluctuating features of the environment. However, it is not clear from the state of the art how to update the semantic layer as the metric map evolves. The strengths of our method are threefold: the framework allows for the unsupervised evolution of both maps as the environment is revisited by the robot; it uses vision-only sensors, making it appropriate for production cars; and the human labelling effort is minimised as far as possible while maintaining high fidelity. We evaluate this on two different car parks with a fully automated car, performing repeated automated parking manoeuvres to demonstrate the robustness of the system.

For reliable and fault tolerant operation of cognitive factories, we introduce an algorithm to monitor plan executions. According to this algorithm, when some changes or discrepancies are detected, appropriate decisions are given based on the causes of these changes or discrepancies. To identify these causes (e.g., broken robots or robot components), we introduce a novel diagnostic reasoning method which synergistically integrates hypothetical reasoning, geometric reasoning, and learning from earlier experiences. Based on these causes, if necessary, new hybrid plans (task plans integrated with feasibility checks) are computed to reach the manufacturing goals by allowing repairs of robots/components. The results of our experiments over reasonably-sized cognitive factory scenarios show the usefulness of (i) diagnostic reasoning for execution monitoring, (ii) allowing repair actions during replanning, and (iii) learning from experiences. We provide a video of dynamic simulation of our execution monitoring algorithm with Kuka youBots and a Nao humanoid robot as the supplementary material.

This paper examines an integrated path planning and power management problem for a solar-powered unmanned ground vehicle (UGV). The proposed method seeks to minimize the travel time of the UGV through an area with a known energy density by designing an optimal path and allocating the vehicle's power among its electrical components, while the UGV operates under strict power constraints and harvests ambient environmental energy along the designed path. A scalar field is first established to evaluate the solar radiation density at discrete locations. A modified Particle Swarm Optimization method is applied to search for a minimal time path wherein the energy gathered is equal to or greater than the energy expended. The proposed modeling and optimization strategy is verified through computer simulation and experimental demonstration.

This paper proposes an experimental study of slipping avoidance algorithms based on force/tactile perception data. The claim is that contact force measurements alone or tactile data alone are not sufficient for an effective slipping avoidance strategy in real world conditions. Integrated force/tactile sensors able to provide measurements of both the contact force vector and spatially distributed tactile maps are the key enabling technology for efficient slipping avoidance control algorithms that can actually work with real world objects under no restricting assumption on the contact geometry or with unknown physical properties of the objects. The paper proposes a new slipping avoidance control scheme, which usefully exploits an integrated force/tactile sensor mounted on the parallel gripper of a Kuka youBot. The results show how the strategy successfully allows the robot to safely manipulate real-world objects, both rigid and compliant, in various friction conditions of their surface, both stable and slippery.

A wide variety of strategies have been developed for assisting human locomotion using powered exoskeletons. Although these strategies differ in their aims as well as the control methods employed, they have the implicit property of causing a virtual modification of the dynamic response of the human limb. We use this property of the exoskeletons action to formulate a unified control design framework called Integral Admittance Shaping, which designs exoskeleton controllers capable of producing the desired dynamic response for the assisted limb. In this framework, a virtual increase in the admittance of the limb is produced by coupling it to an exoskeleton that exhibits active behavior. Specifically, our framework shapes the magnitude profile of the integral admittance (i.e. torque-to-angle relationship) of the coupled human-exoskeleton system, such that the desired assistance is achieved. This framework also ensures that the coupled stability and passivity are guaranteed. This paper presents a formulation of Integral Admittance Shaping for single degree-of-freedom (1-DOF) exoskeleton devices. We also present experimental results on a modified version of Honda's Stride Management Assist (SMA) device that successfully demonstrate motion amplification of the assisted hip joint during walking.

This paper reports motion control of living insect legs by electrically stimulating multiple leg muscles under pre-programmed sequential schedule. A living beetle (Coleopteran, Mecynorrhina torquata) was employed as the insect platform. Firstly, we investigated the sequence of leg motions (walking gait) of free-walking beetles to preliminarily understand which motions (leg muscles) are being activated at which timings and for how long. Each beetle leg has three degrees of freedom (DoFs), namely protraction/retraction, levation/depression, and extension/flexion. We then anatomically mapped out and located the leg muscle groups corresponding to each DoF to determine the stimulation sites (electrode implantation sites) for activating our desired leg motions. Silver thin wires were implanted into the muscles and the other ends of the wires were connected to output sites controlled by a microcontroller which allows for the pre-programmed sequential electrical stimulation. Based on the leg motion sequence in the free walking beetles, two types of walking gaits control, namely tripod and galloping were successfully demonstrated. The step frequency, which corresponds to walking speed, is user-adjustable by changing the duration of each stimulation sequence.

Passivity has been a major criterion on designing a stable haptic interface due to many advantages. However, passivity has been suffering from its intrinsic conservatism since it only represents a small set of the whole stable region. Therefore, there was always limitation to increase the performance due to the small design margin from the passivity criterion. In most of the cases, stability and performance has trade-off relationship. In this paper, we propose a less conservative control approach for stable haptic interaction based on Input to State Stable (ISS) criterion. The proposed approach is inspired from the analogy between virtual environments and systems with hysteresis nonlinearities. A system with hysteresis nonlinearity has sector bounded property, which allows us to guarantee that only a finite amount of energy can be extracted from the system, which leads the system to be dissipative [1] and also the states to be bounded by a function of the input [2]. Since the finite amount of energy is allowed to be extracted from the system, the proposed ISS approach has less conservative constraint compared with passivity-based approaches. Moreover, the proposed approach has a simple structure and does not use any system parameters which make it suitable for practical implementations. Experimental evaluation validates the effectiveness of the proposed approach.

While techniques exist for the rapid prototyping of mechanical and electrical components separately, this paper describes a method where commercial Additive Manufacturing (AM) techniques can be used to concurrently construct the mechanical structure and electronic circuits in a robotic or mechatronic system. The technique involves printing hollow channels within parts that are then filled with a low melting point liquid metal alloy that solidifies upon cooling to form electrical traces. This method is compatible with most conventional fused deposition modeling and stereolithography machines, and requires no modification to an existing printer, though the technique could easily be incorporated into multi-material machines. Three primary considerations are explored using the a commercial fused deposition manufacturing (FDM) process as a testbed: material and manufacturing process parameters, simplified injection fluid mechanics, and automatic part generation using standard printed circuit board software tools. As demonstration of the ability to embed circuit in RP parts, a differential-drive robot is printed, populated with discrete electronic components, and injected to create a fully functional robot.

Pose graph optimization is the non-convex optimization problem underlying pose-based Simultaneous Localization and Mapping (SLAM). If robot orientations were known, pose graph optimization would be a linear least-squares problem, whose solution can be computed efficiently and reliably. Since rotations are the actual reason why SLAM is a difficult problem, in this work we survey techniques for 3D rotation estimation. Rotation estimation has a rich history in three scientific communities: robotics, computer vision, and control theory. We review relevant contributions across these communities, assess their practical use in the SLAM domain, and benchmark their performance on representative SLAM problems (Fig. 1). We show that the use of rotation estimation to bootstrap iterative pose graph solvers entails significant boost in convergence speed and robustness.

Robotic prostheses can improve walking performance for amputees, but prescription of these devices has been hindered by their high cost and uncertainty about the degree to which individuals will benefit. The typical prescription process cannot well predict how an individual will respond to a device they have never used because it bases decisions on subjective assessment of an individual's current activity level. We propose a new approach in which individuals ‘test drive’ candidate devices using a prosthesis emulator while their walking performance is quantitatively assessed and results are distilled to inform prescription. In this system, prosthesis behavior is controlled by software rather than mechanical implementation, so users can quickly experience a broad range of devices. To test the viability of the approach, we developed a prototype emulator and assessment protocol, leveraging hardware and methods we previously developed for basic science experiments. We demonstrated emulations across the spectrum of commercially available prostheses, including traditional (e.g. SACH), dynamic-elastic (e.g. FlexFoot), and powered robotic (e.g. BiOM® T2) prostheses. Emulations exhibited low error with respect to reference data and provided subjectively convincing representations of each device. We demonstrated an assessment protocol that differentiated device classes for each individual based on quantitative performance metrics, providing feedback that could be used to make objective, personalized device prescriptions.

We develop a computationally efficient control policy for active perception that incorporates explicit models of sensing and mobility to build 3D maps with ground and aerial robots. Like previous work, our policy maximizes an information-theoretic objective function between the discrete occupancy belief distribution (e.g., voxel grid) and future measurements that can be made by mobile sensors. However, our work is unique in three ways. First, we show that by using Cauchy-Schwarz Quadratic Mutual Information (CSQMI), we get significant gains in efficiency. Second, while most previous methods adopt a myopic, gradient-following approach that yields poor convergence properties, our algorithm searches over a set of paths and is less susceptible to local minima. In doing so, we explicitly incorporate models of sensors, and model the dependence (and independence) of measurements over multiple time steps in a path. Third, because we consider models of sensing and mobility, our method naturally applies to both ground and aerial vehicles. The paper describes the basic models, the problem formulation and the algorithm, and demonstrates applications via simulation and experimentation.

In this paper, we present an information-based approach to select a reduced number of landmarks and poses for a robot to localize itself and simultaneously build an accurate map. We develop an information theoretic algorithm to efficiently reduce the number of landmarks and poses in a SLAM estimate without compromising the accuracy of the estimated trajectory. We also propose an incremental version of the reduction algorithm which can be used in SLAM framework resulting in information based reduced landmark SLAM. The results of reduced landmark based SLAM algorithm are shown on Victoria park dataset and a Synthetic dataset and are compared with standard graph SLAM (SAM [6]) algorithm. We demonstrate a reduction of 40-50% in the number of landmarks and around 55% in the number of poses with minimal estimation error as compared to standard SLAM algorithm.

Classically robot force control passes through joint torques measurement or estimation. Within this context, classical torque sensing technologies rely on current sensing on motor windings and on torsion sensing on motor shaft. An alternative approach was recently proposed in [1] and combines whole-body distributed 6-axis force/torque (F/T) sensors, gyroscopes, accelerometers and tactile sensors (i.e. artificial skin). A further advantage of this method is that it simultaneously estimates (internal) joint torques and (external) contact forces with no need of joint redesign. As a drawback, the method relies on a model of the robot dynamics, as it consists on reordering the classical recursive Newton-Euler algorithm (RNEA). In this paper we consider the problem of the parametric identification of the robot dynamic model from embedded F/T sensors. We extend recent results on parametric identification [2] by considering an arbitrary reordering of the classical RNEA. The theoretical framework is validated on the iCub humanoid, which is equipped with both 6-axis F/T sensors and joint torque sensors. We estimated the system inertial parameters using only one F/T sensor. We used the obtained parameters to estimate the joint torques (as proposed in [1]) and compared the results with direct joint torque measurements, used in this context only as a ground truth.

Home automation is now implemented in many retirement homes in order to improve elderly's autonomy and safety. Smart homes allow to monitor the activities of elderly persons using information coming from different sensors. The ADL (Activities of Daily Living) are used to evaluate the ability of a person to perform on their own a selection of the activities which are essential for independent living in everyday life. The ADL are then used to detect deviations in a person's behaviour. Indoor localization based on the fusion of heterogeneous data from different sensors, is then essential for ADL characterization. For this purpose, a robust data fusion method is presented in this work through a multi-modal analysis to monitor the activities of elderly people (immobility, walking, etc) in a smart home. The paper describes the installation of sensors in a Living Lab and the preliminary experimental results using a set of Pyroelectric Infra Red (PIR) sensors, Radio Frequency Identification (RFID) distance measurement and the outcome of a noise analysis. Within a set-membership framework, our algorithm for robust localization employs a multi-modal data fusion approach dealing with faulty measurements.

We present an incremental method for motion generation in environments with unpredictably moving and initially unknown obstacles. The key to the method is its incremental nature: it locally augments and adapts global motion plans in response to changes in the environment, even if they significantly change the connectivity of the world. The restriction to local changes to a global plan results from the fact that in mobile manipulation, robots can ultimately only rely on their on-board sensors to perceive changes in the world. The proposed method addresses three sub-problems of motion generation with three algorithmic components. The first component reactively adapts plans in response to small, continuous changes. The second augments the plan locally in response to connectivity changes. And the third extracts a global, goal-directed motion from the representation maintained by the first two components. In an experimental evaluation of this method, we show a real-world mobile manipulator executing a whole-body motion task in an initially unknown environment, while incrementally maintaining a plan using only on-board sensors.

In this paper, we propose a unified approach to teach and iteratively refine both end-effector and null-space movements. Hence, the robot can be taught to make use of all its degrees-of-freedom (DoF) to adapt its behavior to new dynamic scenarios. In order to achieve this goal we propose an incremental learning approach in a framework of kinesthetic teaching based on a multi-priority kinematic controller, the so-called Task Transition Control (TTC). The learning algorithm is responsible for skill acquisition and their incremental update. On the real-time level, end-effector and null-space motion primitives, as well as the physical guidance are considered as prioritized tasks. The transitions among these tasks and their insertion and removal are managed by the TTC according to the specified transition parameters. This allows to introduce a customized task which guarantees a proper and smooth response to the applied external forces during the kinesthetic teaching. Experimental results on a 7 DoF KUKA lightweight manipulator show the effectiveness of the proposed approach.

Our abilities in scene understanding, which allow us to perceive the 3D structure of our surroundings and intuitively recognise the objects we see, are things that we largely take for granted, but for robots, the task of understanding large scenes quickly remains extremely challenging. Recently, scene understanding approaches based on 3D reconstruction and semantic segmentation have become popular, but existing methods either do not scale, fail outdoors, provide only sparse reconstructions or are rather slow. In this paper, we build on a recent hash-based technique for large-scale fusion and an efficient mean-field inference algorithm for densely-connected CRFs to present what to our knowledge is the first system that can perform dense, large-scale, outdoor semantic reconstruction of a scene in (near) real time. We also present a ‘semantic fusion’ approach that allows us to handle dynamic objects more effectively than previous approaches. We demonstrate the effectiveness of our approach on the KITTI dataset, and provide qualitative and quantitative results showing high-quality dense reconstruction and labelling of a number of scenes.

Rescue missions require both speed to meet strict time constraints and maximum use of resources. This study presents a Task Swap Allocation (TSA) algorithm that increases vehicle allocation with respect to the state-of-the-art consensus-based bundle algorithm and one of its extensions, while meeting time constraints. The novel idea is to enable an online reconfiguration of task allocation among distributed and networked vehicles. The proposed strategy reallocates tasks among vehicles to create feasible spaces for unallocated tasks, thereby optimizing the total number of allocated tasks. The algorithm is shown to be efficient with respect to previous methods because changes are made to a task list only once a suitable space in a schedule has been identified. Furthermore, the proposed TSA can be employed as an extension for other distributed task allocation algorithms with similar constraints to improve performance by escaping local optima and by reacting to dynamic environments.