ICRA 2015 论文列表

In caging, an object is geometrically confined by position-controlled robots and never escapes from the constraint. Caging has some advantages over conventional grasping, and its applications have been performed not only in 2D but also in 3D scenes with various actual robots. However, the conditions of complete caging are not always satisfied due to limited robot configuration. This paper studies partial caging, in which an object is incompletely confined by robots or obstacles and is able to escape from the constraint. As an example of partial caging, a circular object moving in the planar hand is considered. We investigate an effect of arrangement of its fingertips, which prevents the object from escaping outside through the gap between the fingertips. Some simulation results show differences of difficulty of escaping for the object according to width of the gap and angle of the fingers. In addition, ease of entering the hand through the gap of the fingers is also evaluated. From these two scores on partial caging, we define an ability index for the hand, which represents the hand can easily capture an object and confine it without any finger motion.

Selective tasks such as harvesting or spraying of single crops are a promising research topic in agricultural automation. Inspired by industrial production, an obvious approach is to use robot manipulators in greenhouses and orchards. To exploit the potential of redundant manipulators in particular, advanced motion planning algorithms are needed. While harvesting, a new trajectory for every fruit has to be planned. Although the scenario is similar for every fruit, it is unique for each harvesting sequence. In this paper we present an efficient online planning approach which takes advantage of a simplified environment model. However, the generated trajectory is not optimal in general w.r.t. joint velocities or might even be unfeasible. Thus, we introduce an optional global offline optimization scheme which is able to find optimal trajectories in a few seconds and takes advantage of the heuristic planning as initial guess. We apply the proposed scheme to a 9-DOF agricultural manipulator for sweet-pepper harvesting and evaluate our method by extensive tests with fruit positions based on real measurements.

The ROS ecosystem is an interconnected web of packages, nodes and people with no efficient means to compare, assess or visualize them. We develop a set of tools consisting of various metrics, a data visualization web app, and an active monitoring system. With these tools, we measure the current state of the ecosystem as well as determine where the community should direct their efforts. We also encourage the community to provide input on potential applications, additional metrics, and further improvements to address the needs of the ROS ecosystem. We incentivize this input by gamifying community contributions to the infrastructure. Encouraging user-driven improvements to the ROS infrastructure through the use of a leaderboard and friendly competition will advance ROS development and community support far into the future.

In this paper we propose a novel method of estimating indoor scenes from a single full-view image. On the one hand, the conventional methods cope with limited field of view images, such as perspective images and hemispherical omnidirectional images, which result in visually open boundary condition, called open geometry. On the other hand, a full-view image results in a visually close boundary condition, called close geometry. In this paper we employ the characteristics of close geometry to explore indoor scene understanding from a single full-view image. The proposed close geometry is tested in comparison with the conventional open geometry. The comparative experiment is also carried out between the proposed method and the state-of-the-art method [13]. The experimental results show that the proposed approach can achieve a better performance, and imply that close geometry plays an important role on the interpretation of indoor scenes.

In this paper, we propose an estimation method of human joint movements from measured EMG signals for assistive robot control. We focus on how to estimate joint movements using multiple EMG electrodes even under sensor failure situations. In real world applications, EMG sensor electrodes might become disconnected or detached from skin surfaces. If we consider EMG-based robot control for assistive robots, such sensor failures lead to significant errors in the estimation of user joint movements. To cope with these sensor failures, we propose a state estimation model that takes uncertain observations into account. Sensor channel anomalies are found by checking the covariance of the EMG signals measured by multiple EMG electrodes. To validate the proposed control framework, we artificially disconnect an EMG electrode or detach one side of an EMG probe from the skin surface during elbow joint movement estimation. We show proper control of a one-DOF exoskeleton robot based on the estimated joint torque using our proposed method even when one EMG electrode has a sensor problem; a standard method with no tolerability against uncertain observations was unable to deal with these fault situations. Furthermore, the errors of the estimated joint torque with our proposed method were smaller than the standard method or a method with a conventional sensor fault detection algorithm.

Bundle Adjustment is the current state of the art method for solving the simultaneous localization and mapping problem. This problem is important for the localization of robots, and most acute for flying robots that cannot rely on ground odometry. The solution requires additional information to resolve scale, and most implementations either assume that relatively accurate pose information exists, or utilize GPS and IMU sensors. This paper presents an alternative approach that incorporates Digital Terrain Model constraints into the Bundle Adjustment algorithm, enabling the correct resolution of scale even in the absence of additional information. It is shown, in multiple test scenarios, that this algorithm provides estimations that do not diverge with time and that exceed, in accuracy, the resolution of the underlying sampled terrain.

To perform many common industrial robotic tasks, e.g. deburring a work-piece, in small and medium size companies where a model of the work-piece may not be available, building a geometrical model of how to perform the task from a data set of human demonstrations is highly demanded. In many cases, however, the human demonstrations may be sub-optimal and noisy solutions to the problem of performing a task. For example, an expert may not completely remove the burrs that result in deburring residuals on the work-piece. Hence, we present an iterative algorithm to estimate a noise-free geometrical model of a work-piece from a given dataset of profiles with deburring residuals. In a case study, we compare the profiles obtained with the proposed method, nonlinear principal component analysis and Gaussian mixture model/Gaussian mixture regression. The comparison illustrates the effectiveness of the proposed method, in terms of accuracy, to compute a noise-free profile model of a task.

This paper explores the impact of communication latency (time delay) on path following for a teleoperated mobile robot. In [1] Vozar developed a human steering model capturing the effects of latency on teleoperated driving performance and introduced the idea of equating path following performances under variable latency to an equivalent constant latency. We repeat Vozar's user experiments on a higher fidelity (dynamic) simulation using different latency distributions. Two key findings are presented. First, user tests support a relationship between path following scores for latency distributions of different shapes. Second, our user tests with the dynamic simulation produced the same trend describing latency's impact on performance as Vozar's results with a kinematic simulation.

As robots continue to create long-term maps, the amount of information that they need to handle increases over time. In terms of place recognition, this implies that the number of images being considered may increase until exceeding the computational resources of the robot. In this paper we consider a scenario where, given multiple independent large maps, possibly from different cities or locations, a robot must effectively and in real time decide whether it can localize itself in one of those known maps. Since the number of images to be handled by such a system is likely to be extremely large, we find that it is beneficial to decompose the set of images into independent groups or environments. This raises a new question: Given a query image, how do we select the best environment? This paper proposes a similarity criterion that can be used to solve this problem. It is based on the observation that, if each environment is described in terms of its co-occurrent features, similarity between environments can be established by comparing their co-occurrence matrices. We show that this leads to a novel place recognition algorithm that divides the collection of images into environments and arranges them in a hierarchy of inverted indices. By selecting first the relevant environment for the operating robot, we can reduce the number of images to perform the actual loop detection, reducing the execution time while preserving the accuracy. The practicality of this approach is shown through experimental results on several large datasets covering a combined distance of more than 750Km.

Many ideas have been proposed to reduce traffic congestion. Driving a platoon of vehicles with constant spacing seems to be a promising idea as it increases traffic density. But keeping constant inter-vehicle spacing requires very reliable communication. Another control policy is to drive the platoon with a time headway between vehicles. It is a robust and well known policy but large inter-vehicle distances in addition to weak stability (unity error gain) near low frequencies make it less practical. We have proposed in [1], [2] a modification of the Constant Time Headway policy (CTH). This modification largely reduces the inter-vehicle distances using only one information shared between all vehicles. In this work, we propose an additional modification of our control law. This modification makes our control law similar, in form, to the classical constant spacing policy, but it requires to share only one information between the vehicles. This modification improves the stability of the platoon and removes the weak stability of the CTH near low frequencies. We prove the robustness of the control law in the presence of actuating lags, sensing and communication delays. This proof can also be used to prove the stability of the classical constant spacing policy in the presence of all previous delays, which makes our result more general than those established in the literature. Safety is also discussed and the maximum acceptable communication delay without losing safety is determined. Simulations have been done in many critical scenarios.

In this paper we propose to track online computed force trajectories to control the energy of various types of pendulum-like objects. The considered pendulum-like objects can be controlled by multiple agents and swing in different oscillation degrees of freedom. Our goal is to excite one specific oscillation, the intended oscillation, while damping all other disturbance oscillations. By approximating the intended oscillation as a simple pendulum oscillation, we can specify a desired force trajectory. Tracking of this force trajectory results in a controlled swing-up of the intended oscillation accompanied by a simultaneous damping of the disturbance oscillations. Simulation experiments with a two-agent trapezoidal pendulum show convincing control performance. A human-robot virtual reality experiment shows the transferability of the control approach to a human interaction partner. The limitations of the approach are discussed based on simulation results obtained for a single-agent double pendulum.

Legged robots offer the potential of locomotion across various types of terrains. Different terrains require different gait patterns to enable greater traversal efficiency. Consequently, as a legged robot transitions from one type of terrain to another, the gait pattern should be adapted so as to maximise traction and energy efficiency. This paper explores the use of power consumption as estimated by the robot in real-time for guiding this gait transition in the case of statically-stable locomotion. While moving, the robot autonomously assesses its power consumption, relates it to the traction, and switches between gaits so as to maximise efficiency. In this way, the robot only needs proprioceptive sensors and consequently does not require velocity estimation, ground imaging or profiling to maintain efficient locomotion across different terrains. The approach has been tested on a hexapod robot traversing a variety of terrain types and stiffness, including concrete, grass, mulch and leaf litter. The experimental results show that gait switching on energetics alone enables traction maintenance and efficient locomotion across different terrains. We also present comparisons between the power consumption metric used in this work and cost of transport which is used in the literature for characterising energetics for legged locomotion.

This paper describes a control method for noncyclic swing motions such as throwing, hitting and kicking in multiple-joint robots by using “time reversal integral.” This method calculates a control input sequence and an initial posture of the robot to reach a designated terminal state by integrating a dynamic system without directly designating trajectories. The terminal end-tip speed is maximized by optimizing the target terminal state under constraints such as friction and the joint position limits. Feasibility of the method is evaluated by ball throwing experiments.

Encoders have been an inseparable part of robots since the very beginning of modern robotics in the 1950s. As a result, the foundations of robot control are built on the concepts of kinematics and dynamics of articulated rigid bodies, which rely on explicitly measuring the robot configuration in terms of joint angles - done by encoders.

Autonomous mobile robots are required to operate in partially known and unstructured environments. It is imperative to guarantee safety of such systems for their successful deployment. Current state of the art does not fully exploit the sensor and dynamic capabilities of a robot. Also, given the non-holonomic systems with non-linear dynamic constraints, it becomes computationally infeasible to find an optimal solution if the full dynamics are to be exploited online. In this paper we present an online algorithm to guarantee the safety of the robot through an emergency maneuver library. The maneuvers in the emergency maneuver library are optimized such that the probability of finding an emergency maneuver that lies in the known obstacle free space is maximized. We prove that the related trajectory set diversity problem is monotonic and sub-modular which enables one to develop an efficient trajectory set generation algorithm with bounded sub-optimality. We generate an off-line computed trajectory set that exploits the full dynamics of the robot and the known obstacle-free region. We test and validate the algorithm on a full-size autonomous helicopter flying up to speeds of 56m/s in partially-known environments. We present results from 4 months of flight testing where the helicopter has been avoiding trees, performing autonomous landing, avoiding mountains while being guaranteed safe.

This paper introduces a novel micro-force sensing approach utilizing an electroplated nickel microspring and a precision linear slider (PLS) for micro-tensile testing applications. After investigating the effects of friction forces in a PLS, an electroplated nickel microspring is designed, fabricated and integrated into the PLS, and the proposed micro-force sensor concept is validated through experimental results. The microspring fabricated in this paper is limited to forces up to 6 mN with the average sensitivity of 36.63 μN/μm. It is shown that the friction forces introduce uncertainties only to the forces less than 500 μN. The proposed approach allows the fabrication of micro-force sensors for the force ranges of up to tens of Millinewtons for different applications.

We previously proposed a motion support robot and conducted experiments in which a C5-level cervical cord injury patient used the system. This paper proposes to offer motion support to a C4-level spinal cord injury patient who suffers from paralysis of the limbs. Electromyogram (EMG) signals are used to determine the user's intentions. The proposed motion assist robot can then support flexion and extension at the elbow joint. Using frequency analysis of the EMG signal, the patient's intention can be estimated in real time, and the coefficient of viscosity is varied in an admittance controller. With the proposed motion assist method, we were able to realize arbitrary upper limb motion of a C4-level cervical cord injury patient.

In this paper, we propose a novel and computationally efficient algorithm for simultaneous exploration and coverage with a vision-guided micro aerial vehicle (MAV) in unknown environments. This algorithm continually plans a path that allows the MAV to fulfil two objectives at the same time while avoiding obstacles: observe as much unexplored space as possible, and observe as much of the surface of the environment as possible given viewing angle and distance constraints. The former and latter objectives are known as the exploration and coverage problems respectively. Our algorithm is particularly useful for automated 3D reconstruction at the street level and in indoor environments where obstacles are omnipresent. By solving the exploration problem, we maximize the size of the reconstructed model. By solving the coverage problem, we maximize the completeness of the model. Our algorithm leverages the state lattice concept such that the planned path adheres to specified motion constraints. Furthermore, our algorithm is computationally efficient and able to run on-board the MAV in real-time. We assume that the MAV is equipped with a forward-looking depth-sensing camera in the form of either a stereo camera or RGB-D camera. We use simulation experiments to validate our algorithm. In addition, we show that our algorithm achieves a significantly higher level of coverage as compared to an exploration-only approach while still allowing the MAV to fully explore the environment.

Autonomous learning through interaction with the physical world is a promising approach to designing controllers and decision-making policies for robots. Unfortunately, learning on robots is often difficult due to the large number of samples needed for many learning algorithms. Simulators are one way to decrease the samples needed from the robot by incorporating prior knowledge of the dynamics into the learning algorithm. In this paper we present a novel method for transferring data from a simulator to a robot, using simulated data as a prior for real-world learning. A Bayesian nonparametric prior is learned from a potentially black-box simulator. The mean of this function is used as a prior for the Probabilistic Inference for Learning Control (PILCO) algorithm. The simulated prior improves the convergence rate and performance of PILCO by directing the policy search in areas of the state-space that have not yet been observed by the robot. Simulated and hardware results show the benefits of using the prior knowledge in the learning framework.